Normal view

There are new articles available, click to refresh the page.
Before yesterdaySeeed

Introducing Seeed Studio XIAO MG24 (Sense) Variants: Pre-Soldered & 3PCS Pack

18 February 2025 at 12:19

We’re excited to announce new variants of the Seeed Studio XIAO MG24 and XIAO MG24 Sense, now available in Pre-Soldered versions and convenient 3PCS Packs! Whether you’re looking for a hassle-free soldering experience or stocking up for gifting on these Matter-native, ultra-low-power development boards, we’ve got you covered.

XIAO MG24

XIAO MG24 & XIAO MG24 Sense: Now in 3PCS Pack!

For developers and makers who need multiple boards for prototyping or small-scale production, we now offer a 3PCS Pack of both XIAO MG24 and XIAO MG24 Sense, along with other XIAO boards such as XIAO ESP32S3, XIAO ESP32C3, XIAO RP2040 and more—also available in 3PCS Packs. Powered by Silicon Labs’ EFR32MG24 SoC, these tiny yet powerful dev boards support Matter over Thread® and Bluetooth® Low Energy 5.3—perfect for IoT applications.

XIAO MG24 3PCs Pack

Why Choose the 3PCS Pack?

    • More Value – Get three boards at a more cost-effective price.
    • Streamlined Prototyping – Easily deploy multiple units for testing
    • Perfect for Small-Scale Production – Ideal for businesses and advanced developers.

Both variants retain the classic XIAO form factor (21×17.8mm), 4MB onboard Flash, 19 GPIOs, LED, onboard antenna, and ultra-low power consumption (as low as 1.95μA in sleep mode)—making them ideal for battery-powered Matter projects.

Pre-Soldered XIAO MG24 & XIAO MG24 Sense: Plug-and-Play Simplicity!

We’ve heard your feedback—soldering tiny pads is challenging! That’s why we’re introducing pre-soldered variants of XIAO MG24 and XIAO MG24 Sense, along with other XIAO boards, allowing you to dive straight into development without extra setup.

Why Choose the Pre-Soldered Version?

    • No Soldering Needed – Save time and effort—just unbox and get started!
    • Seamless Breadboarding – Easily integrate into your projects.
    • More Durable & Reliable – Factory-soldered headers ensure strong, long-lasting connections.

XIAO MG24 vs. XIAO MG24 Sense – What's the Difference?

While both feature the same high-performance ARM Cortex-M33 @ 78MHz, XIAO MG24 Sense goes a step further with two onboard sensors:

    • Analog Microphone – For voice detection and audio-based applications.
    • 6-Axis IMU – Perfect for motion sensing, TinyML applications, and smart automation.

A Perfect Fit for Battery-Powered Matter Projects

With their ultra-low-power consumption, onboard secure cryptographic engine, and support for multiple IoT communication protocols, the XIAO MG24 variants are ideal for:

    • Smart Home Automation (Matter-enabled lighting, security systems, and sensors)
    • Environmental Monitoring – battery-powered air quality, temperature, and humidity sensors.
    • Remote Sensing & Control – wireless automation and control systems.
    • TinyML & Edge AI Applications – gesture recognition, posture tracking, and voice-based control with XIAO MG24 Sense.

Get Yours Now!

Don’t miss out! Whether you’re an IoT developer, prototyping enthusiast, or TinyML innovator, these new XIAO MG24 options make it easier than ever to build and scale your projects. 

Now available:

Stay tuned for more updates from Seeed Studio XIAO, and keep innovating! 🚀

End Note

Hey community, we’re curating a monthly newsletter centering around the beloved Seeed Studio XIAO. If you want to stay up-to-date with:

🤖 Cool Projects from the Community to get inspiration and tutorials
📰 Product Updates: firmware update, new product spoiler
📖 Wiki Updates: new wikis + wiki contribution
📣 News: events, contests, and other community stuff

Please click the image below👇 to subscribe now!

The post Introducing Seeed Studio XIAO MG24 (Sense) Variants: Pre-Soldered & 3PCS Pack appeared first on Latest Open Tech From Seeed.

Workshop Series at Universidad de Manizales: Innovation and Technological Solutions with SenseCAP and Mission Pack

13 February 2025 at 08:59

On February 7th, the Faculty of Science and Engineering at Universidad de Manizales hosted an intensive series of workshops on IoT, LoRaWAN, and decentralized networks, in collaboration with Seeed Studio. More than 30 students and 5 faculty members from the fields of semiconductors and telecommunications, along with university directors, actively participated in this event, which combined theory, practice, and collaborative prototyping.

Workshop 1: Exploring IoT, LoRaWAN, and DePIN with SenseCAP

The first workshop focused on a theoretical and practical introduction to LoRaWAN, IoT, and DePIN. Participants explored the SenseCAP ecosystem, learning about its connectivity with networks such as Helium and The Things Network. During an interactive session on Miro, they identified challenges within the university campus and proposed solutions using SenseCAP devices.

Among the identified issues, the uncontrolled entry of domestic animals into the campus nature reserve was highlighted, posing risks to wildlife conservation. Additionally, there were concerns about monitoring and preserving water sources, as well as ensuring student safety from encounters with wild animals. Other proposals included monitoring unauthorized parking space usage with sensors such as the SenseCAP S1101 and XIAO ESP32S3 Sense.

20
21
22
23
26
25

Workshop 2: IoT System Architecture and Deployment for the Nature Reserve

In the second session, participants defined system architectures and proceeded with the implementation of a technology-based solution for the nature reserve. The selected devices, SenseCAP S2110 Sensor Builder and SenseCAP S1101, were used for wildlife identification and monitoring, combined with an audible alert system to warn students about the presence of animals.

The workshop included assembling and configuring sensors using the SenseCraft application, setting up SenseCAP CC Portal, and initiating the training of an AI vision model for wildlife identification. Due to adverse weather conditions, the installation in the reserve was postponed, but it will be completed in the coming days, with updates to follow.

24
2
19
17
11
13
14
15

Workshop 3: Mission Pack and Mesh Networks for Emergencies

The third workshop, aimed at faculty and senior students in systems and telecommunications, focused on the Mission Pack, emphasizing its application in smart cities, communities, and institutions. A Meshtastic network was deployed using T1000-E Tracker cards, simulating scenarios with no cellular or WiFi connectivity to evaluate its effectiveness in emergencies.

Use cases from across the Americas were analyzed, including flooding in Los Angeles, where deploying SenseCAP M2 and WM1302 within the reComputer of the Mission Pack could optimize rescue operations and disaster mitigation through real-time environmental monitoring.

7
6
5
8
9
3
4

Impact and Future of the Project

These workshops have enabled students and faculty to explore emerging technologies and prototype solutions for real-world challenges. In the coming days, the final system deployment in the nature reserve will take place in collaboration with the university’s IoT research group. This system will not only benefit the university community but will also provide new opportunities for Data Science students, who can use the collected data for research projects.

Furthermore, a SenseCAP M2 Gateway has been deployed, connecting to the Helium decentralized network, expanding the campus’s connectivity capabilities.

This event marks a significant step forward in adopting IoT technologies in educational settings, demonstrating how open-source hardware and decentralized networks can drive real-world impact in communities.

The post Workshop Series at Universidad de Manizales: Innovation and Technological Solutions with SenseCAP and Mission Pack appeared first on Latest Open Tech From Seeed.

Seeed Monthly Wrap-Up for January 2025: A New Chapter in AI Robotics

By: Ellie Cai
11 February 2025 at 16:32

Hello Community,

Happy Chinese New Year! Wishing you all a joyful, prosperous, and energizing year ahead!

Welcome to the latest edition of Seeed Monthly. This month, we explored advancements in AI-powered robotics, computer vision, and edge computing!

Boost your knowledge with 7 in-depth tech exploration offering expert insight, 3 weekly livestream recap, 7 product and service showcases that will leave you in awe. Plus, prepare for 4 latest Seeed news and event highlights. Dive into the vibrant open-source community with 4 inspiring projects. 

📚 I. In-depth Feature & Tech Exploration

01. How to use the SO-ARM100 robotic arm in Lerobot

The SO-100ARM is a fully open-source robotic arm project launched by TheRobotStudio. LeRobot is committed to providing models, datasets and tools for real-world robotics in PyTorch. This wiki provides the assembly and debugging tutorial for the SO ARM100 and realizes data collection and training within the Lerobot framework. Check Out today.

02. How to Import and Control SO100Arm Kit in Isaac Sim

This wiki provides instructions on how to import the SO100Arm Kit robotic arm into NVIDIA’s Isaac Sim simulation platform and control it using ROS2 and Python scripts. Find more details here.

03. Frigate NVR with Raspberry Pi 5


Frigate NVR is an open-source network video recorder designed for real-time object detection with AI models. Paired with the Raspberry Pi 5, it enables efficient video surveillance at the edge, powered by YOLOv8n. This guide will walk you through the installation and configuration process for an optimal setup. Check out today.

04. Setting Up 4G LTE Connectivity for IIoT with MQTT

The 4G LTE HAT for Raspberry Pi provides reliable, high-speed cellular connectivity, making it essential for remote and IIoT applications. With MQTT, a lightweight messaging protocol, devices can communicate efficiently over cellular networks, even in isolated locations. Learn how use AI commands for communication between the Mosquitto MQTT broker and the Quectel 4G LTE Raspberry Pi HAT. Click for more.

05. Setting Up OpenWrt on Raspberry Pi 5 with a 4G LTE Module

The Raspberry Pi 5, paired with OpenWrt and a 4G LTE HAT , offers a powerful and flexible solution for creating a portable hotspot. this guide will help you transform your Raspberry Pi 5 into a fully functional hotspot powered by OpenWrt and 4G LTE connectivity. Read more.

06. Deploying AI Models on SenseCAP A1102 Using SenseCraft AI

The SenseCAP A1102 is an intelligent camera sensor designed for edge AI applications. This guide will walk you through deploying AI models on the A1102 using SenseCraft AI. Learn more.

07. Getting Start with R2000 Series

reComputer AI R2000 is a powerful Edge AI Computer based on the Raspberry Pi 5. With quad-core Arm Cortex-A76 processor 8GB RAM, M.2 SSD support, and an Hailo-8 AI acceleration module providing up to 26 TOPS. Enabling real-time, low latency & high-efficiency AI inferencing. Read more.

🎬 II. Weekly Livestream: Making Next Gadget

Our livestream “Making Next Gadgets” will feature a different tech theme weekly, with our product dev teams sharing the latest product updates, project demos, and exclusive deals. Join us on a journey through the tech revolution happening right now!

01. 2024 AI Hardware Highlights & 2025 Inspirations

As 2024 draws to a close, our CEO Eric Pan and Community Manager Ray Huang took us to revisit the highlights that made 2024 a remarkable chapter in Seeed Studio’s story. Discover how we’ve pushed the boundaries in computer vision, Local llm, TinyML and AI-powered robotics, and get inspired as we share insights and ideas for 2025. Watch the video now.

02. No-Code Vision AI Workshop: Create Smart Arduino Projects in Minutes!

SenseCraft AI is a no-code platform that makes AI development accessible to everyone, from makers to educators. In this livestream, we demonstrated how to create custom AI vision sensors for your Arduino Uno – all without writing a single line of code with our SenseCraft AI platform. Discover more here.

03. LeRobot, Open-Source End-to-End Learning for AI Robots

In this livestream, we walk you through a collaborative workflow that involves collecting data through teleoperation and simulation in Isaac Lab and storing it in the standard LeRobot Dataset format. Join us and build advanced robotic arms and accelerating research and innovation in AI robotics. Watch the video.

📰 III. Product & Service Showcases

01. SO-ARM100 Low-Cost AI Arm Kit

Start from Imitation Learning with the open-source SO-ARM100 robotic arm kit, with native support from Hugging Face LeRobot. The kit includes servo motors, control board, power supply, and cables, making it easy to get quick-assembly, synchronize teaching tasks, and train advanced architectures like ACT/DiffusionPolicy with its 6DoF leading and following arms. Find out more here.

02. reComputer Mini J4012 with Extension

Meet the reComputer Mini, powered by NVIDIA Robotics Jetson Orin Nano/NX — designed for seamless physical AI development. Whether you’re working on autonomous machines, robotic arms, humanoid robots, or other robotics applications, the reComputer Mini provides the power and versatility to be the “brain” of your system. Read more.

03. Introducing SenseCraft AI, Beginner-Friendly, Web-Based, No-Code Platform for AI Applications

SenseCraft AI is a free, web-based platform designed for beginners, focuing on a no-code approach and an application-orientation. Our goal is to simplify and accelerate the creation of AI applications, making the process beginner-friendly and accessible to all. Discover More.

04. New Product Post – Vision AI Sensor, Supporting LoRaWAN and RS485

SenseCAP A1102 is a IP66 rated LoRaWAN® Vision AI Sensor, ideal for low-power, long-range TinyML Edge AI applications.  RS485 Vision AI Camera is a robust vision AI sensor that supports MODBUS-RS485 protocol and Wi-Fi Connectivity. It is the camera part of the SenseCAP A1102, which adopts the Himax AI Processor for AI performance. Read more.

05. Seeed Studio XIAO Plus, More Castellation IOs for SMD Soldering

Inspired by the cool SMD pins design of the RICK TNY, Seeed Studio XIAO Plus represents a new iteration of our regular XIAO Boards, featuring redesigned 23 castellation pins (20 GPIOs, 3 power pins) and back solder points specifically for projects needing expanded IOs. Read more.

06. Expanding the XIAO Ecosystem: New ePaper Driver, Relay, Power, and Sensor Add-on Modules Released

We’re introducing 4 new add-on modules for Seeed Studio XIAO, including a new relay, an ePaper Driver Board, an expansion board with power supply and meter, and a sensor – all compatible with Seeed Studio XIAO boards! Discover More.

07. Customize Hardware + Deploy Ultralytics YOLO11 with Node-RED Dashboard=Build Vision AI with reCamera

Ready to work with reCamera? Walk through the whole pipeline to discover how reCamera, the tiny yet powerful AI camera, simplifies vision AI development:

  • Modular hardware layers: Customize to fit your needs
  • YOLO11 models native support: Run object detection and counting directly on-device with the Node-RED dashboard, or upload your own model
  • Expand possibilities: Access versatile vision AI applications from the SenseCraft AI model zoo to adapt to different scenarios.

Read more.

👩‍💻 IV. News & Event Highlights

Get the inside scoop on recent events and news. Gain valuable insights, key takeaways, and highlights from industry experts and thought leaders at the forefront of ML innovation.

01. Seeed Studio 2024 Year-in-Review: Your Trusted AI Hardware Partner

As 2024 draws to a close, we at Seeed Studio take pride in reflecting on a transformative year. From launching cutting-edge technologies to empowering communities across the globe, our journey has been defined by innovation, collaboration, and real-world impact. Join us as we revisit some of the highlights that made 2024 a remarkable chapter in Seeed Studio’s story. Watch the recap.

02. Seeed Forms Strategic Partnership with Atianza to Deliver Edge AI Solutions Across Latin America

Seeed Studio is excited to announce a strategic partnership with Atianza Solutions. This collaboration aims to provide cutting-edge Edge AI solutions to industries across Latin America, advancing innovation and Edge AI solutions in the region. More info.

03. Seeed Studio at AWS re:Invent 2024: Empowering Edge AI and IoT Innovation

Seeed Studio at AWS re:Invent 2024: Empowering Edge AI and IoT Innovation 

As AWS re:Invent 2024 wrapped up, the energy and innovation displayed at the event left us inspired and excited about the future of IoT and Edge AI. Seeed Studio was proud to partner with AWS, contributing cutting-edge hardware and expertise to showcase the power of connected technologies in real-world applications. Find out more.

04. Scaling Research in Shenzhen: Maker Camp in Shenzhen-2501 Recap

This January, in partnership with SUSTech School of Design, AIRS, SciArt Co-lab, Chaihuo Makerspace, Immersive Design Group, Anker Innovations, Andone, and the Greater Bay ACM SIGCHI Chapter, we hosted 10 distinguished researchers from MIT (Massachusetts Institute of Technology) for a month-long Research at Scale residency. The program provided participants with a deep dive into Shenzhen’s manufacturing ecosystem, facilitating engagement with industry leaders, academic peers, and local innovators to explore scalable research applications. Read more.

🌈 V. Community Project Spotlight

Celebrate the creativity and ingenuity of our community members with featured projects and ideas in machine learning. From open-source libraries to DIY solutions, there’s no shortage of inspiration to be found among our talented community.

01. ARMOR: Egocentric Perception for Humanoid Robot Powered by XIAO ESP32S3

Daehwa Kim (Carnegie Mellon University), Mario Srouji, Chen Chen, and Jian Zhang (Apple) have developed ARMOR, an innovative egocentric perception hardware and software system for humanoid robots. By combining Seeed Studio XIAO ESP32S3-based wearable depth sensor networks and transformer-based policies, ARMOR tackles the challenges of collision avoidance and motion planning in dense environments. Check it out

02. DIY Water Tank Level Sensor

Is your water tank level always a mystery? Meet this clever DIY Water Tank Level Sensor project by Roland Ortner! Using our XIAO ESP32C6, an ultrasonic distance sensor (JSN-RS04t), and a temperature & humidity sensor (AM2302), this setup tracks your water tank’s level, battery status, and environmental data with precision. Learn more.

03. Build Your Own Cat-Themed Hacking Console

Build Your Own Cat-Themed Hacking Console with DevKitty CutieCat v1 and our XIAO ESP32S3. This DIY companion lets you explore wireless auditing, USB attacks, and more—all in a compact, feline-inspired design. From soldering guides to pre-flashed firmware, this guide by Alex Lynd is packed with resources to help you assemble and customize your own hacking console. Find out more.

04. Conversations with SenseCAP Watcher (OpenAI & ESP32)

Check out MengDu Li’s latest project which showcases the powerful capabilities of our SenseCAP Watcher combined with the OpenAI API to create a real-time voice assistant. Powered by the ESP32-S3, this compact device captures voice input, processes it through OpenAI, and responds naturally—all in real-time. Read more.

That’s all for today, thank you all for reading through this January 2025 Monthly Wrap-up in your spare time. If you wanna share what projects you’re working on, shoot us a tweet @seeedstudio, let us know on LinkedIn and Discord, or publish your project on our Project Hub on Hackster.

 

 

#Notes

If you’re new to this session, here is a brief intro. We have gotten dozens of requests over the years for a Seeed Monthly Newsletter. Although we already have a newsletter for weekly updates, we still need a place to host overall information about what’s happened on a monthly basis. It can offer an efficient and friendly way to get updated for the whole community. And that’s what we expect for our Seeed Monthly Wrap-ups. Instead of putting it as a subscribe-to-read format, we’re publishing them on our blog, so as to keep it as open and accessible as possible for the whole community. For each entry, we will cover awesome projects from the community, campaigns that we are running, new products, IIoT Solutions, and even secret recipes for prototyping and manufacturing.

 

Previous Monthly Wrap-ups:

Year in Review: Seeed in 2024

Year in Review: Seeed in 2023

Year in Review: Seeed in 2022

The post Seeed Monthly Wrap-Up for January 2025: A New Chapter in AI Robotics appeared first on Latest Open Tech From Seeed.

Scaling Research in Shenzhen: Maker Camp in Shenzhen-2501 Recap

By: Ellie Cai
8 February 2025 at 16:54

It’s been a while since the conclusion of Maker Camp in Shenzhen 2401, and as we welcome the new year, we reflect on an exciting milestone—Maker Camp in Shenzhen 2501, an initiative that continues to foster collaboration between academic research and industrial innovation.

This January, in partnership with SUSTech School of Design, AIRS, SciArt Co-lab, Chaihuo Makerspace, Immersive Design Group, Anker Innovations, Andone, and the Greater Bay ACM SIGCHI Chapter, we hosted 10 distinguished researchers from MIT (Massachusetts Institute of Technology) for a month-long Research at Scale residency. The program provided participants with a deep dive into Shenzhen’s manufacturing ecosystem, facilitating engagement with industry leaders, academic peers, and local innovators to explore scalable research applications.

Fostering Cross-Disciplinary Dialogue

The residency commenced with the Scalable HCI Research Symposium, a week-long event designed to bridge the gap between academic research and industrial practice. The symposium featured:

  • Academic presentations from leading researchers
  • Industry talks addressing current trends and challenges in manufacturing and design
  • Cultural and art-tech exhibitions showcasing the intersection of creativity and technology
  • Factory visits providing firsthand exposure to Shenzhen’s world-class manufacturing capabilities

The symposium attracted over 50 researchers, engineers, and designers from 20+ globally recognized institutions, including MIT, Harvard, CMU, NYU, Brown, Stanford, and the University of Chicago. This diverse participation facilitated a global exchange of ideas, positioning Shenzhen as a hub for scalable human-computer interaction (HCI) research and innovation.

“How to Make Almost Anything in Shenzhen”

Eric Pan, CEO at Seeed Studio, provided a comprehensive overview of Shenzhen’s evolving manufacturing landscape, covering topics such as design for manufacturing, supplier relationships, intellectual property considerations, and the emergence of ShenzhenGPT. He also introduced the Open Manufacturing Whitepaper, offering practical insights for researchers and entrepreneurs looking to navigate and leverage Shenzhen’s industrial ecosystem.

MIT Media Lab Research Presentations

Alan Han, Andy Kong, Francisco Ramirez, Jason Hou, Lingdong Huang, Patrick Chwalek, Thomas Sanchez, Vineet Padia, Yuhan Wang and Cedric Honnet from the MIT presented their latest works, engaging with local startups, makers, and industry leaders to explore potential collaborations and applications for their technologies.

From Research to Real-World Application: HuaQiangBei and Factory Visits

A core objective of the residency was to bridge theoretical research with hands-on industry engagement. The HuaQiangBei Electronics Market (HQB) and factory visits provided researchers with invaluable exposure to Shenzhen’s fast-paced hardware ecosystem.

Exploring HuaQiangBei: The Epicenter of Electronics Innovation

HQB is often described as the world’s largest electronics market, offering everything from raw components to finished products and prototyping services. For the MIT researchers, HQB served as a living lab, where they could explore:

  • Rapid prototyping resources: A vast selection of sensors, microcontrollers, and PCB services available off-the-shelf
  • Component sourcing strategies: Direct interaction with suppliers to understand sourcing options, bulk pricing, and lead times
  • Emerging trends in consumer electronics: First-hand exposure to cutting-edge AI-driven hardware, robotics, and IoT devices

By engaging with local vendors, the team gained insights into the speed, flexibility, and affordability that make Shenzhen a global leader in agile hardware development.

Factory Visits: From Concept to Production

Beyond sourcing components, the researchers had the opportunity to visit key manufacturing facilities across Shenzhen and the Greater Bay Area, covering a wide range of production capabilities:

  • PCB Assembly & Flexible PCB Manufacturing: Understanding high-precision board fabrication, surface-mount technology (SMT), and flexible circuits for wearable and embedded applications
  • Injection Molding & Industrial Design: Observing the molding and mass-production processes that transform initial designs into scalable products
  • MicroLED and E-paper Display Production: Gaining insights into next-generation display technologies, including their applications in smart devices and interactive installations
  • Stepper Motors and Servo Systems: Exploring the role of motion control technologies in robotics, automation, and industrial applications

Each visit provided a real-world perspective on the end-to-end product development cycle, reinforcing how research-driven innovations can be translated into scalable, market-ready solutions.

Smart Space Hackathon: Advancing Innovation Through Collaboration

One of the most impactful components of the program was the Smart Space Hackathon, co-hosted by Chaihuo, Seeed, and Anker. The event brought together more than 30 participants, including academic researchers, industry professionals, and members of the local maker community, to develop innovative solutions for smart environments.

In total, 11 projects were developed, with 8 successfully delivering functional prototypes. Concepts ranged from smart interactive devices and robotic workspace assistants to AI-driven privacy protection solutions and sound-responsive environment. The hackathon underscored the importance of multidisciplinary collaboration and demonstrated how rapid prototyping and applied research can drive meaningful innovation.

Maker Camp in Shenzhen 2501 reinforced the value of connecting academia, industry, and the maker community to accelerate real-world impact. Participants left with a deeper understanding of Shenzhen’s manufacturing ecosystem, hands-on experience in sourcing and production, and new perspectives on how to scale their research into tangible innovations.

You can find a vibrant documentation from the MIT students on Seeed Studio’s GitHub Channel (keep updating).

We extend our gratitude to all partners and participants for contributing to this meaningful exchange of knowledge and ideas.

The post Scaling Research in Shenzhen: Maker Camp in Shenzhen-2501 Recap appeared first on Latest Open Tech From Seeed.

Seeed Studio at AWS re:Invent 2024: Empowering Edge AI and IoT Innovation 

By: Elaine Wu
22 January 2025 at 10:05
Acknowledgments
I want to express my heartfelt gratitude to Channa Samynathan, Senior Worldwide Specialist Solutions Architect at AWS, as well as the AWS IoT Robotics team for their valuable contributions to this post. Their insights and expertise were instrumental in delivering the event and this content.

As AWS re:Invent 2024 wrapped up, the energy and innovation displayed at the event left us inspired and excited about the future of IoT and Edge AI. Seeed Studio was proud to partner with AWS, contributing cutting-edge hardware and expertise to showcase the power of connected technologies in real-world applications. Here are some key highlights from our collaborations:

Advancing Disaster Response with Edge AI and IoT

At the Amazon Security and Disaster Response Activation, our hardware played a key role in showcasing the potential of IoT to revolutionize emergency scenarios. Here are some highlights from our collaboration:

1. Disaster Response with Meshtastic Devices and Nvidia Jetson 

We were proud to partner with AWS to demonstrate the power of IoT in disaster response scenarios. Our hardware, including the SenseCAP T1000-E Meshtastic Tracker and reComputer J4012, worked seamlessly with AWS IoT Core to create a private, reliable communication channel.

  • Real-time Data Tracking: Our system showcased the potential for compliant and real-time data tracking during emergencies, paving the way for rapid deployment in disaster scenarios.
  • Synergy of Edge Computing and Cloud Capabilities: This activation exemplifies the synergy of AWS IoT’s cloud capabilities and Seeed’s edge computing solutions to address real-world challenges.

We’re thrilled to see this project advancing toward commercialization to support disaster response efforts globally. At Seeed Studio, we’re committed to empowering innovation and advancing the possibilities of Edge AI and IoT.

LoRaWAN and Real-Time Tracking Across Las Vegas

One of the standout activations was the Amazon Security and Disaster Response Activation, which showcased the potential of AWS IoT in real-world scenarios. Our SenseCAP M2 Multi-Platform LoRaWAN Gateway played a key role in this demonstration, contributing to the creation of a vast LoRaWAN network that covered the entire city of Las Vegas.

Key Highlights:

  • Wide-Area Coverage: Our LoRaWAN gateways facilitated communication with 45 LoRaWAN devices carried by AWS staff, capturing GPS, humidity, and temperature data every two minutes.
  • Real-Time Updates: The data was transmitted through the LoRaWAN gateways to AWS IoT Core for LoRaWAN and published onto an Amazon Location Service map. The map, updated every two minutes, was accessible to attendees via a QR code.
  • Simulated Downstream Processing: By integrating the data with a TAK server, the activation demonstrated how real-time location and environmental information can enhance situational awareness and decision-making in security and emergency scenarios.

The Power of IoT in Critical Events

The successful implementation of this expansive network underscores the potential of IoT in enabling wide-area connectivity and situational awareness during critical events. At Seeed Studio, we’re committed to empowering innovation and advancing the possibilities of IoT.

3. Embodied AI Chess Demo at the Generative AI Pavilion

Another incredible activation was the Embodied AI Chess Demo at the AWS Generative AI Pavilion, which showcased the potential of AI-driven robotics in real-world applications. Our reServers powered the demonstration, ensuring seamless operation throughout the event.

Key Highlights:

  • AI-Powered Robotics: Using inference from foundation models via AWS Bedrock, robot arms performed chess moves based on real-time commands.
  • Flawless Performance: Our reServers of NVIDIA Jetson ensured seamless operation throughout the event, demonstrating the potential of industrial-grade hardware in advanced AI applications.

The Future of Intelligent Automation

This activation sparked engaging discussions about the integration of generative AI with robotics, pushing the boundaries of what’s possible in intelligent automation. At Seeed Studio, we’re committed to empowering innovation and advancing the possibilities of AI and robotics.

4. Hands-On Edge AI Workshop with NVIDIA Jetson and AWS IoT Greengrass

We partnered with AWS on the “Unleash Edge Computing with AWS IoT Greengrass on NVIDIA Jetson” workshop, providing attendees with hands-on experience in deploying and managing edge runtime devices through AWS IoT Core and AWS IoT Greengrass.

Key Highlights:

  • Practical Experience: Attendees gained practical experience in deploying and managing edge runtime devices, showcasing the potential of edge computing and Connected Edge Intelligence (CEI) in real-world use cases.
  • The workshop was using 150 reComputer J4012 and demonstrated the power of edge AI in real-world applications.

 

5. AWS IoT RaceTrack Revolution Builders’ Fair Activation with The Tiny Seeed Studio XIAO

At the AWS Builders’ Fair, the AWS IoT team wowed attendees with the AWS IoT RaceTrack Revolution demo. Our Seeed Studio XIAO ESP32 dev boards, with Wi-Fi capabilities, enhanced the experience by offloading video feeds seamlessly to the Nvidia Jetson device.

Key Highlights:

  • Innovative Demo: The demo showcased the power of AWS IoT in a hands-on, engaging setting, despite Wi-Fi challenges.
  • Seeed Studio XIAO ESP32 Dev Boards: Our dev boards played a crucial role in offloading video feeds, enhancing the overall experience.

Empowering Innovation and Advancing IoT Possibilities

At Seeed Studio, we’re committed to empowering innovation and advancing the possibilities of Edge AI and IoT. Our collaboration with AWS has been a testament to the power of connected technologies in real-world applications, and we look forward to continuing this journey together.

Empowering IoT Innovation Together


At Seeed Studio, we’re thrilled to have played a key role in the AWS re:Invent 2024, where the fusion of cloud computing and cutting-edge hardware unlocked new possibilities. Our collaboration with AWS has been instrumental in showcasing how our solutions can effortlessly integrate with the powerful AWS IoT ecosystem to tackle pressing issues in disaster response, security, AI, and beyond.

We’re committed to driving innovation forward with AWS and look forward to witnessing the real-world impact of these solutions. Stay tuned for more updates as we continue to push the boundaries of IoT and Edge AI together, empowering a smarter and more connected world.

The post Seeed Studio at AWS re:Invent 2024: Empowering Edge AI and IoT Innovation  appeared first on Latest Open Tech From Seeed.

Expanding the XIAO Ecosystem: New ePaper Driver, Relay, Power, and Sensor Add-on Modules Released

By: Lily
20 January 2025 at 14:40

We’ve heard from our community about the limited number of compatible add-on modules for our tiny but powerful Seeed Studio XIAO boards. Starting 2025, we’re addressing this by developing more XIAO add-ons!

Seeed Studio XIAO Add-ons are expansion boards, sensors, connectivity modules, and actuators with a socket where Seeed Studio XIAO dev boards (pre-soldered versions) clip right in. You can explore the full collection on our Seeed Studio XIAO Selector page.

For our first product collection of the year, we’re introducing a new relay, ePaper Driver Board, expansion board, and sensor – all compatible with Seeed Studio XIAO boards!

Compatibility: all Seeed Studio XIAO Pre-Soldered Dev Boards (SAMD21, RP2040, nRF52840, nRF52840 Sense, ESP32C3, ESP32S3, ESP32S3 Sense, ESP32C6, RP2350, RA4M1, The pre-soldered variants for XIAO MG24 and XIAO MG24 Sense will be coming soon)

This ePaper driver board features a 24-pin FPC connector, a built-in charging IC, and a JST 2-pin BAT connector. It’s perfect for creating WiFi-enabled digital photo frames, supporting various ePaper displays (2.13″ Monochrome eInk / ePaper Display with 122×250 Pixels, 2.9″ Quadruple Color eInk / ePaper Display with 128×296 Pixels, 5.83″ Monochrome eInk / ePaper Display with 648×480 Pixels, 2.9″ Monochrome eInk / ePaper Display with 296×128 Pixels).

2.13" Monochrome eInk / ePaper Display with 122x250 Pixels
2.13" Quadruple Color eInk / ePaper Display with 122x250 Pixels
7.5" Monochrome eInk / ePaper Display with 800x480 Pixels
5.83" Monochrome eInk / ePaper Display with 648x480 Pixels
1.54" Flexible Monochrome eInk / ePaper Display with 152x152 Pixels
2.9" Quadruple Color eInk / ePaper Display with 128x296 Pixels

Compared to our 2023 ePaper Breakout Board, this new version includes:

  • JST 2-pin BAT connector
  • Built-in charging IC
  • Onboard power switch
  • Extra 14 IO pins for expansion
  • Standard XIAO add-on dimension (which is the triple size of a XIAO board)

Don’t worry – we’ll keep both versions available to suit different application needs. Currently, this new ePaper Driver Board is available for pre-order at $4.9, with estimated shipping at the end of January 2025.

Compatibility: all Seeed Studio XIAO Pre-Soldered Dev Boards (SAMD21, RP2040, nRF52840, nRF52840 Sense, ESP32C3, ESP32S3, ESP32S3 Sense, ESP32C6, RP2350, RA4M1, The pre-soldered variants for XIAO MG24 and XIAO MG24 Sense will be coming soon)

Need to control DC appliances from your XIAO? This single-channel 5V Relay Add-on Module for XIAO handles all the control with DC. With snap-on compatibility for pre-soldered XIAO boards and screw terminals, no soldering is required! The HF32FA-G relay makes it perfect for IoT and home automation. P.S. Our team also designed a 3D enclosure for this relay add-on with an XIAO dev board and open sourced it on Thingiverse for you to remix.

For dual-load AC control, check out our plug-and-play 2-Channel AC WiFi Relay, based on XIAO ESP32C3. It comes pre-flashed with ESPHome firmware for compatibility with native Home Assistant.

Compatibility: all Seeed Studio XIAO Pre-Soldered Dev Boards (battery voltage monitoring unavailable for XIAO SAMD21 and XIAO RP2040)

Looking for a thumb-size temperature, humidity and light sensor? XIAO Logger Hat gets you covered. Created by Westlake University’s Marcel and scaled through Fusion Co-Create, this thumb-sized environmental sensor includes SHT40 temperature, humidity, and BH1750 light sensors, plus RTC and battery voltage monitoring.

XIAO PowerBread, a Breadboard Power Supply and Meter

Compatibility: Seeed Studio XIAO Pre-Soldered Dev Boards (RP2040, ESP32C3, ESP32S3, ESP32S3 Sense, ESP32C6) (XIAO SAMD21 and XIAO RP2350 support coming soon)

Designed by Nicho D through Seeed Fusion Co-Create, XIAO PowerBread is a compact breadboard power supply with built-in monitoring. It provides stable 3.3V and 5V outputs with real-time voltage, current, and power tracking on its LCD display. It’s open-source with comprehensive documentation and customizable code.

That’s our new product roundup! Tell us which product interests you most or share your suggestions. Want to influence our future products? Join the discussion on our Seeed Studio XIAO Open Roadmap – your input shapes what we build next.

Until next time! 🙂

Notes at the end.

Hey community, we’re curating a monthly newsletter centering around the beloved Seeed Studio XIAO. If you want to stay up-to-date with:

🤖 Cool Projects from the Community to get inspiration and tutorials
📰 Product Updates: firmware update, new product spoiler
📖 Wiki Updates: new wikis + wiki contribution
📣 News: events, contests, and other community stuff

Please click the image below👇 to subscribe now!

The post Expanding the XIAO Ecosystem: New ePaper Driver, Relay, Power, and Sensor Add-on Modules Released appeared first on Latest Open Tech From Seeed.

Seeed establece una alianza estratégica con Atianza para ofrecer soluciones de Edge AI en América Latina

By: Ellie Cai
20 January 2025 at 10:27

Seeed se complace en anunciar una alianza estratégica con Atianza Solutions. Esta colaboración tiene como objetivo proporcionar soluciones innovadoras de Edge AI a diversas industrias en América Latina, promoviendo la innovación y las tecnologías de vanguardia en la región.

Acerca de Seeed Studio

Seeed Studio, un destacado socio en hardware de inteligencia artificial (IA), ha sido una empresa líder en hardware abierto desde 2008, empoderando a más de medio millón de usuarios directos para crear soluciones digitales reales. Gracias a un esfuerzo constante y la confianza ganada, las líneas de productos de Seeed ahora abordan escenarios emergentes de IA, tales como:

  • Redes de sensores para recopilar extensos datos en tiempo real.
  • Computación edge para llevar la inteligencia a nuevas fronteras.

Seeed ofrece módulos y dispositivos listos para la industria, además de facilitar el desarrollo de prototipos y la producción. Innovadores de diferentes sectores trabajan junto a Seeed para hacer que sus creaciones estén ampliamente disponibles en mercados diversos, fomentando el uso de código abierto, la construcción de comunidades y soluciones industriales integradas junto a Seeed.

Acerca de Atianza

Atianza es un equipo multidisciplinario con sede en Santiago de Chile que cuenta con más de 10 años de experiencia en la industria. Con presencia en tres países –Chile, Colombia y España – Atianza cruza fronteras para ofrecer soluciones ágiles y personalizadas.

Especialidades de Atianza:

  • Arquitectura e Ingeniería
  • Diseño y Usabilidad
  • Gestión y Control

En Atianza, la innovación, la experiencia y la agilidad convergen para crear una alianza hacia un futuro más conectado y eficiente. No se trata sólo de desarrollar software, sino de co-crear soluciones que transformen y potencien la visión empresarial.

La Alianza

Seeed y Atianza unen fuerzas para ofrecer soluciones integrales de Edge AI en América Latina. Esta colaboración combina el hardware de última generación de Seeed con la experiencia analítica personalizada de Atianza para satisfacer las diversas necesidades del mercado.

Iniciativas Clave:

  • Distribución de dispositivos Edge AI y kits de desarrollo de Seeed Studio.
  • Soluciones personalizadas de videoanalítica y análisis de datos adaptadas a las industrias de Chile, Colombia y España.

Juntos, Seeed y Atianza buscan crear un futuro más inteligente y eficiente para las empresas de la región, aprovechando sus fortalezas combinadas en hardware, software y experiencia en integración.
¡Contáctanos en support@atianza.com para obtener una solución de IA personalizada que acelere el crecimiento de tu negocio!

The post Seeed establece una alianza estratégica con Atianza para ofrecer soluciones de Edge AI en América Latina appeared first on Latest Open Tech From Seeed.

ARMOR: Egocentric Perception for Humanoid Robot Powered by XIAO ESP32S3

16 January 2025 at 01:31

Daehwa Kim (Carnegie Mellon University), Mario Srouji, Chen Chen, and Jian Zhang (Apple) have developed ARMOR, an innovative egocentric perception hardware and software system for humanoid robots. By combining Seeed Studio XIAO ESP32S3-based wearable depth sensor networks and transformer-based policies, ARMOR tackles the challenges of collision avoidance and motion planning in dense environments. This system enhances spatial awareness and enables nimble and safe motion planning, outperforming traditional perception setups. ARMOR was deployed on the GR1 humanoid robot from Fourier Intelligence, showcasing its real-world applications.

[Source: Daehwa Kim]

Hardwares Used

ARMOR uses the following hardware components:

    • XIAO ESP32S3 microcontrollers: Efficiently collect sensor data and stream it to the robot’s onboard computer via I2C.
    • Onboard Computer: NVIDIA Jetson Xavier NX processes sensor inputs. 
    • GPU (NVIDIA GeForce RTX 4090): Handles ARMOR-Policy’s inference-time optimization for motion planning.
    • SparkFun VL53L5CX Time-of-Flight (ToF) lidar sensors: Distributed across the robot’s body for comprehensive point cloud perception.

How the ARMOR Works

The hardware solution of ARMOR’s egocentric perception system uses distributed ToF lidar sensor networks. Groups of four ToF sensors are connected to Seeed Studio XIAO ESP32S3 microcontrollers, capturing high-precision depth information from the environment. The XIAO ESP32S3 serves as a crucial intermediary controller, efficiently managing real-time sensor data transmission. It streams the collected depth data via USB to the robot’s onboard computer, the NVIDIA Jetson Xavier NX, which then wirelessly transmits the data to a powerful Linux machine equipped with an NVIDIA GeForce RTX 4090 GPU for data processing. This sophisticated data pipeline enables the creation of an occlusion-free point cloud around the humanoid robot, providing essential environmental awareness data for the ARMOR neural motion planning algorithm. The distributed and light-weight hardware setup also ensures enhanced spatial awareness and overcomes the limitations of head-mounted or external cameras, which often fail in cluttered or occluded environments.

Daehwa Kim, one of the core developers of this project, mentions why they selected the Seeed Studio XIAO for this project.

“We might imagine a future where users easily plug and play with wearable sensors for humanoids and augment robots' perceptions in various tasks. XIAO ESP32 series makes the wearable sensor system easily modularizable. We specifically adopted the XIAO ESP32S3 in ARMOR because of its powerful computing and tiny form factor.”
Armor Policy - Transformer-based policy [Source: Daehwa Kim]

The neural motion planning system, ARMOR-Policy, is built on a transformer-based architecture called the Action Chunking Transformer. This policy was trained on 86 hours of human motion data from the AMASS dataset using imitation learning. ARMOR-Policy processes the robot’s current state, goal positions, and sensor inputs to predict safe and efficient trajectories in real-time. The system leverages latent variables to explore multiple trajectory solutions during inference, ensuring flexibility and robustness.

Trained on 86 hours of human motion dataset [Source: Daehwa Kim]

ARMOR was rigorously tested in both simulated and real-world scenarios. It demonstrated remarkable improvements in performance, reducing collisions by 63.7% and increasing success rates by 78.7% compared to exocentric systems with dense head-mounted cameras. Additionally, the transformer-based ARMOR-Policy reduced computational latency by 26× compared to sampling-based motion planners like cuRobo, enabling efficient and nimble collision avoidance.

Real World Hardware Deployment [Source: Daehwa Kim]

Discover more about ARMOR

Want to explore ARMOR’s capabilities? The research team will soon release the source code, hardware details, and 3D CAD files on their GitHub repository. Dive deeper into this cutting-edge project by reading their paper on arXiv. Stay tuned for updates to replicate and innovate on this revolutionary approach to humanoid robot motion planning! To see ARMOR in action, check out their demonstration video on YouTube.

End Note

Hey community, we’re curating a monthly newsletter centering around the beloved Seeed Studio XIAO. If you want to stay up-to-date with:

🤖 Cool Projects from the Community to get inspiration and tutorials
📰 Product Updates: firmware update, new product spoiler
📖 Wiki Updates: new wikis + wiki contribution
📣 News: events, contests, and other community stuff

Please click the image below👇 to subscribe now!

The post ARMOR: Egocentric Perception for Humanoid Robot Powered by XIAO ESP32S3 appeared first on Latest Open Tech From Seeed.

💾

New Product Post – Vision AI Sensor, Supporting LoRaWAN and RS485

By: violet
15 January 2025 at 10:55

Halloo Everyone, welcome to this blog!

The main topic is NEW PRODUCTS! And the keywords are LoRaWAN and Vision AI. You would wonder, “your devices has a camera and it is LoRaWAN?” Yes indeed! I know, I know! You would tell me “You can’t send images or videos via LoRaWAN because the ‘message’ is too large”, or someone else would say “Technically you can, but you need to ‘slice’ the large images or videos to send them ‘bit by bit’ and ‘piece them together’ aferward. Then why bother?”

What if I tell you, you don’t have to send the images or videos? Think about it, the goal is to get the results captured by the camera, not tons of irrelevant footage. In this case, as long as you can get the results, there is no need to send large images or videos.

Without further ado, here comes the intro of our main cast of this post – SenseCAP A1102, an IP66-rated LoRaWAN® Vision AI Sensor, ideal for low-power, long-range TinyML Edge AI applications. It comes with 3 pre-deployed models (human detection, people counting, and meter reading) by default. Meanwhile, with SenseCraft AI platform [Note 1], you can use the pre-trained models or train your customized models conveniently within a few clicks. Of course, SenseCAP A1102 also supports TensorFlow Lite and PyTorch.

This Device consists of two main parts: the AI Camera and the LoRaWAN Data Logger. While different technologies are integrated in this nifty device, I would like to highlight 4 key aspects:

  • Advanced AI Processor

As a vision AI Sensor, SenseCAP A1102 proudly adopted the advanced Himax WiseEye2 HX6538 processor featuring a dual-core Arm Cortex-M55 and integrated Arm Ethos-U55. (The same AI processor as in Grove Vision AI v2 Kit.) This ensures a high performance in vision processing.

Meanwhile, please keep in mind that lighting and distance will affect the performance, which is common for applications that involve cameras. According to our testing, SenseCAP A1102 can achieve 70% confidence for results within 1 ~ 5 meters in normal lighting.

  • Low-Power Consumption, Long-Range Communication

SenseCAP A1102 is built with Wio E5 Module featuring STM32WLE5JC, ARM Cortex M4 MCU, and Semtech SX126X. This ensures low-power consumption and long-range communication, as in SenseCAP S210X LoRaWAN Environmental sensors. Supporting a wide range of 863MHz – 928MHz frequency, you can order the same device for different stages of your projects in multiple continents, saving time, manpower, and costs in testing, inventory management, and shipment, etc.

SenseCAP A1102 opens up new possibilities to perceive the world. The same hardware with different AI models, you have different sensors for detecting “objects” (fruits, poses, and animals) or reading meters (in scale or digits), and many more. With the IP66 rating (waterproof and dustproof), it can endure long-term deployment in outdoor severe environments.

We understand interoperability is important. As a standard LoRaWAN device, SenseCAP A1102 can be used with any standard LoRaWAN gateways. When choosing SenseCAP Outdoor Gateway or SenseCAP M2 Indoor Gateway, it is easier for configuration and provisioning.

  • Easy Set-up and Configure with SenseCraft App

We provide SenseCraft App and SenseCAP Web Portal for you to set up, configure, and manage the devices & data more easily.

At SenseCraft App, you can change settings with simple clicks such as choose the platform, change the frequency for the specific region, change data upload intervals (5 ~ 1440min), or packet policy (2C+1N, 1C, 1N) and other settings. 

You can see the live and historical data of your devices on both SenseCraft App and SenseCAP Web Portal easily.

When using SenseCAP Sensors and SenseCAP gateways, you can also choose to use SenseCAP cloud platform, which is free for 6 months for each devices and then it is 0.99usd/device/month, or you can choose to use your own platform or other 3rd-party platforms. We offer API supporting MQTT and HTTP.

  • Wi-Fi Connectivity for Transmitting Key Frames

Inside the AI Camera part of this device sits a tiny-yet-powerful XIAO ESP32C3, which is powered by new RISC-V architecture. This adds Wi-Fi connectivity to SenseCAP A1102. In the applications, you can get the reference results via LoRaWAN and at the same time get the key frames via Wi-Fi to validate or further analyze.

While we always demonstrate how much we love LoRaWAN for its ultra-low-power consumption and ultra-long-range communication by continuously adding more and more products in the portfolio of our LoRaWAN products family. We also understand some people might prefer other communication protocols. Rest assured, we have options for you. As mentioned above, we value interoperability a lot. Here comes to the intro of another important cast of this post: RS485 Vision AI Camera!

RS485 Vision AI Camera is a robust vision AI sensor that supports MODBUS-RS485 [Note 2] protocol and Wi-Fi Connectivity. Simply put, it is the camera part of the SenseCAP A1102, which adopts the Himax AI Processor for AI performance. Its IP66 rating makes it suitable for both indoor and outdoor applications.

You can use RS485 Vision AI Camera with SenseCAP Sensor Hub 4G Data Logger to transmit the reference results via 4G. If your existing devices or systems support MODBUS-RS485, you can connect it with this RS485 Vision AI Camera for your applications.

In this post, we introduced SenseCAP A1102 and RS485 Vision AI Camera. I hope you like them and will get your hands on these devices for your projects soon! I already envision this device used in different applications from smart home, office, and building managetment to smart agriculture, biodiversity conservation, and many others. And we look forward to seeing your applications!

If you’ve been using Seeed products or following our updates, you might have noticed that the expertise of Seeed products and services is in smart sensing and edge computing. While we’ve developed a rich collection of products in (1) sensor networks that collect different real-world data and transmit via different communication protocols, and (2) edge computing that brings computing power and AI capabilities to the edge. I think we can say that Seeed is strong in smart sensing, communication, and edge computing. 

There are many more new products on the Seeed roadmap for us to get a deeper perception of the world with AI-powered insight and actions. Stay tuned!

Last but not the least, we understand that you might have requirements in product features, functionalities, or form factors for your specific applications, we offer a wide range of customization services based on the existing standard products. Please do not hesitate to reach out to us, to share your experience, your thoughts about new products, wishes for new features, or ideas for cooperation possibilities! Reach us at iot[at]seeed[dot]cc! Thank you!

[Note 1: If you do not know it yet, SenseCraft AI is a web-base platform for AI applications. No-code. Beginner-friendly. I joined the livestream on YouTube with dearest Meilily to introduce this platform last week. If you are interested, check the recording here.]

[Note 2: MODBUS RS485 is a widely-used protocol for many industrial applications. You can learn more here about MODBUS and RS485, and you can explore the full range of all RS485 products here.]

The post New Product Post – Vision AI Sensor, Supporting LoRaWAN and RS485 appeared first on Latest Open Tech From Seeed.

Seeed Forms Strategic Partnership with Atianza to Deliver Edge AI Solutions Across Latin America

By: Ellie Cai
14 January 2025 at 14:59

Seeed Studio is excited to announce a strategic partnership with Atianza Solutions. This collaboration aims to provide cutting-edge Edge AI solutions to industries across Latin America, advancing innovation and Edge AI solutions in the region.

About Seeed Studio

Seeed Studio, a leading AI hardware partner, has been a leading Open Hardware company since 2008, empowering over half a million direct users to create real-world digital solutions. Through relentless efforts and earned trust, Seeed’s ever-growing product lines now form around emerging AI scenarios like like AI Sensing, AI Robotics, Sensor Networks, and Maker.
Seeed provides industrial-ready modules and devices, and open up the capability of prototype development and production. Innovators from different vertical domains co-create with Seeed to make their creations widely available for diversified markets by embracing open source, community building, and integrated vertical industry solutions together with Seeed.

About Atianza

Atianza is a multidisciplinary team based in the heart of Santiago de Chile with more than 10 years of experience in the industry. With a presence in three countries – Chile, Colombia and Spain – Atianza bridges borders to deliver agile and personalized solutions.

Atianza specializes in:

  • Architecture and Engineering
  • Design and Usability
  • Management and Control

At Atianza, innovation, experience and agility come together to create an alliance towards a more connected and efficient future. It is not just about developing software, but about co-creating solutions that transform and enhance business vision.

The Partnership

Seeed and Atianza join forces to deliver comprehensive Edge AI solutions across Latin America. This partnership combines Seeed’s state-of-the-art hardware and Atianza’s tailored analytics expertise to address diverse market needs.

Key Initiatives Include:

  • Distribution of Seeed Studio’s Edge AI devices and development kits. Including:
  1. NVIDIA Jetson™, the leading platform for robotics and embedded edge AI applications, highlights the Seeed Studio reComputer Industrial J3010– Fanless Edge AI Device with Jetson Orin™ Nano 4GB

2. Industrial Raspberry Pi devices, highlights the reTerminal DM, a Panel PC, HMI, IIoT Gateway all-in-one device powered by Raspberry Pi

  • Customized video analytics and data analytics solutions tailored for industries in Chile, Colombia, and Spain.

Together, Seeed and Atianza aim to create a more intelligent and efficient future for businesses across the region, leveraging their combined strengths in hardware, software, and integration expertise.

Get in touch at support@atianza.com today for a tailored AI solution designed to accelerate your business growth!

The post Seeed Forms Strategic Partnership with Atianza to Deliver Edge AI Solutions Across Latin America appeared first on Latest Open Tech From Seeed.

The End and The Beginning of the Year TinyML Workshop

7 January 2025 at 11:30

28 December 2024

A fellow maker friend invited me to do the tinyML Workshop at one of his workplace. At 1st I thought the participants will be consist of his employees but turned out he invited his other friends from other startup. And for sure I will not waste this chance to introduce Seeed Studio’s among the friends.

This workshop a bit different from before because Sensecraft AI have many new feature. So in this session I also cover the MQTT and training part of the Sensecraft AI using the Xiao ESP32S3 Sense.

After the workshop is done, I shared a little about the Lora Sensecap line of product. It gained interest from the participants and a few of them have plans to implement it their future project.

06 January 2025

Happy New Year! to kick off the spirit of New Year at the recess week of my campus I propose to do the tinyML workshop to a few students.

On Monday January 6th 2025 10 AM, the participants are eagerly waiting at a classroom that I already requested to the campus. Since the participants for this session is still in their 1st semester, I explained the basic tinyML 101. Then 2 hour later they already become a beginner tinyML engineer and has successfully created their own custom classification model the Sensecraft AI.

Sadly I am only allowed to use the classroom for hour, so at 12 AM I wrapped the session by giving them the Seeed Studio sticker and promised them that there will be a follow up workshop from this one.

Wrap Up 2024

Huge thanks to Seeed Studio for making 2024 a very fruitful year. I have done 9 workshops, 2 seminar and 1 mentoring session as A Ranger.

In this new year I hope there will be more places to cover for me to share my knowledge in the community.

The post The End and The Beginning of the Year TinyML Workshop appeared first on Latest Open Tech From Seeed.

Seeed Studio XIAO Plus, More Castellation IOs for SMD Soldering

By: Lily
2 January 2025 at 16:20

The beloved Seeed Studio XIAO boards, with their surface-mount device (SMD) design and Castellated Mounting Holes, have become popular integrated system modules in countless creative designs, projects, and even commercial products. Their board-to-board soldering capability allows XIAO boards to be easily integrated into carrier boards, enabling faster assembly and scalable production.

Since launching our first XIAO SAMD21 (formerly Seeeduino XIAO) in 2019, we’ve received countless community requests for more than the standard 14 castellated mounting holes on two edges, as these weren’t sufficient for complex projects requiring additional IOs. Now, please meet Seeed Studio XIAO Plus – our response to this community feedback.

Inspired by the cool SMD pins design of the RICK TNY, Seeed Studio XIAO Plus represents a new iteration of our regular XIAO Boards, featuring redesigned 23 castellation pins (20 GPIOs, 3 power pins) and back solder points specifically for projects needing expanded IOs. We’re launching XIAO Plus versions for three models: XIAO ESP32S3 Plus, XIAO nRF52840 Plus, and XIAO nRF52840 Sense Plus, which are all available for instant order at our webstore and AliExpress Store.

XIAO ESP32S3 Plus
XIAO nRF52840 Plus
XIAO nRF52840 Sense Plus

Why only these three XIAOs?

While we’d love to upgrade all XIAO boards, the limited pins on some integrated chips (SAMD21, RP2040, RA4M1, ESP32-C3, and ESP32-C6) restrict the IO expansion. These three models were selected based on overwhelming user demand for additional castellated IOs. Moreover, the XIAO ESP32S3 Plus also doubles its Flash memory to 16MB, supporting more complex applications.

XIAO ESP32S3 Plus Pinout
XIAO nRF52840 Sense Plus

What's new with the back solder points?

Previously, XIAO boards lacked uniformity in their back-side solder points and layouts, hampering our ability to develop universal expansion boards. Our latest XIAO boards (RP2350, RA4M1, MG24 and MG24 Sense) share nearly identical back layouts. The XIAO Plus boards follow suit, with aligned battery and debugger pads.

This standardization means our upcoming expansion boards (such as the XIAO Clip Board) will work with all seven boards (3 XIAO Plus models, XIAO RP2350, RA4M1, and MG24/Sense). We’re actively working on compatibility solutions for other XIAO boards and will share updates once available.

Is XIAO Plus harder to solder?

The through-holes for 7-pin headers remain unchanged, but the castellated mounting holes are slightly smaller and closer together (13 on the left, 10 on the right). While this does make board-to-board soldering more challenging, our 11-person product team successfully tested it with early samples.

We’ll be honest – it requires more precision, but proper tools make a significant difference. Essential items include a brass sponge, water-soluble flux pen, tweezers, acid brush, and rubbing alcohol. For detailed guidance, check out SparkFun’s excellent tutorial on How to Solder: Castellated Mounting Holes.

Join Seeed Studio XIAO Adopter Program

Ready to showcase your soldering skills? Share your XIAO Plus project ideas in the comments! I’ll select three winners to receive their chosen XIAO Plus board (via coupon). Winners will be announced on January 10, 2025. Share now! To assist developers in adapting their projects to the XIAO Plus quickly, we’re adding all the XIAO Plus Boards to the Seeed Studio XIAO Adopter Program. If you’re an author or maintainer of a popular open-source project on GitHub, or an influencer on platforms like YouTube or Tiktok or Instagram, make sure your users can run your code on the XIAO Plus. Join to receive 2 free boards and technical support to make your code compatible with these exciting new boards.

Notes at the end.

Hey community, we’re curating a monthly newsletter centering around the beloved Seeed Studio XIAO. If you want to stay up-to-date with:

🤖 Cool Projects from the Community to get inspiration and tutorials
📰 Product Updates: firmware update, new product spoiler
📖 Wiki Updates: new wikis + wiki contribution
📣 News: events, contests, and other community stuff

Please click the image below👇 to subscribe now!

The post Seeed Studio XIAO Plus, More Castellation IOs for SMD Soldering appeared first on Latest Open Tech From Seeed.

Pharmaceutical Production with AI-Powered Process Monitoring

31 December 2024 at 14:55

Hardware: reServer Industrial J4012, powered by NVIDIA Jetson Orin NX 16GB

Use Case Provider: NeuroSYS

Application: Abnormal Detection in Production Line

Industrial: Pharmaceutical

Deployment Location: Norway

A global pharmaceutical company sought to enhance the efficiency and accuracy of its production process by integrating advanced AI technologies. Their challenge was to detect anomalies, such as tipped vials on conveyor belts, without disrupting existing workflows or requiring extensive reconfiguration of equipment. That’s how the whole solution got started, combining Seeed reServer Industrial J4012 edge device with NeuroSYS AI software platform together to deliver an innovative solution, transforming their production monitoring with an AI-enabled camera system.

Background

Pharmaceutical production lines often handle vials of varying materials (plastic and glass) and capacities (7 to 100 ml), totaling seven distinct types. Traditionally, the process relied on manual tuning of sensors and equipment reconfiguration for each vial type. These limitations resulted in inefficiencies and downtime, especially when tipped vials reached the filling machine.

The company required a versatile solution to address this challenge—one capable of real-time anomaly detection and performance monitoring while minimizing physical intervention.

Initial Challenge

The key challenges included:

  • Detecting tipped vials on a moving conveyor belt.
  • Minimizing false alarms caused by obstructions or unanticipated scenarios.
  • Ensuring the system can adapt to various vial types without retooling machinery.
  • Developing a scalable, non-intrusive solution that could integrate seamlessly with existing workflows.

Solution

The whole system implemented an advanced vision AI pipeline leveraging a combination of industrial hardware and AI-driven software.

Components

  1. Hardware: An industrial-grade camera integrated with the reServer industrial J4012 edge computing unit, powered by NVIDIA Jetson Orin NX 16GB.
  2. Software: Machine learning models trained on production data to detect anomalies and gather insights.
  3. Dashboard: Custom visualizations for real-time monitoring and historical analysis.

Implementation Process

  1. Optimized Setup:
    • The camera and lens were calibrated to capture high-quality images of vials as they moved along the conveyor belt.
    • During the Proof of Concept (PoC) stage, the system operated behind a plastic curtain to validate functionality without disrupting production.
  2. Real-Time Analysis:
    • Frames captured by the camera were processed on the reServer Jetson device in real-time using convolutional neural networks (CNNs).
    • The system determined vial positions (standing or tipped) and triggered alerts for anomalies.
  3. Data Processing and Visualization:
    • Data was stored in a local database and visualized on dashboards, providing insights into machine performance.
    • A vial counting module tracked both standing and tipped vials for statistical analysis.
  4. Enhanced Alert Mechanisms:
    • Detection of a tipped vial activated a signal tower with visual (light) and auditory (buzzer) alerts.

Challenges Encountered During Implementation

During implementation, the system faced challenges to meet the specific deployment scenarios. for example, there could be some false alarms happening which are caused by operator hands entering the camera’s field of view, it’s finally optimized by retraining the machine learning model with additional obstructed images which includes obstructions. Sometimes the vials getting stuck or tipped at curved conveyor segments could be misclassified, and the dataset gaps that overlooked scenarios involving occlusions and bends. These issues were all addressed by enriching the dataset to improve robustness, ensuring accurate performance in diverse conditions.

Results and Achievements

The system delivered remarkable results, transforming the client’s production process:

  1. Anomaly Detection: Achieved 99.89% accuracy in detecting tipped vials, regardless of material or capacity.
  2. Downtime Monitoring: Enabled precise downtime tracking, counting delays after 10 seconds of no vial movement.
  3. Statistical Insights:
    • Counted tipped vials for quality monitoring and standing vials to assess machine efficiency.
    • Provided metrics for machine cycle optimization.
  4. Scalability:
    • The same hardware setup was enhanced with new functionalities, requiring only software updates.
    • Features like snapshot saving of anomalies allowed for deeper analysis of system performance and false positives.

Additional Benefits

  • Flexibility: Eliminated the need for retooling and physical modifications by enabling remote software updates.
  • Future-Proofing: New scenarios and events can be incorporated into the model as they occur, ensuring continuous improvement.
  • Scalable Solution: With minimal hardware adjustments, the system can evolve to handle additional tasks or integrate with advanced analytics platforms.

This project showcases the transformative potential of AI in industrial automation, setting the stage for smarter and more efficient manufacturing processes. The reServer Jetson edge device not only addressed the pharmaceutical company’s immediate challenges but also provided a robust platform for continuous innovation. By leveraging the Jetson edge vision AI technology, the client gained real-time anomaly detection, improved machine efficiency, and actionable insights into their production process—all while reducing manual intervention and hardware dependency.

By implementing this solution, the client not only resolved their immediate challenges but also gained a robust and scalable system for ongoing innovation and operational excellence.


Seeed NVIDIA Jetson Ecosystem

Seeed is an Elite partner for edge AI in the NVIDIA Partner Network. Explore more carrier boards, full system devices, customization services, use cases, and developer tools on Seeed’s NVIDIA Jetson ecosystem page.

Join the forefront of AI innovation with us! Harness the power of cutting-edge hardware and technology to revolutionize the deployment of machine learning in the real world across industries. Be a part of our mission to provide developers and enterprises with the best ML solutions available. Check out our successful case study catalog to discover more edge AI possibilities!

Discover infinite computer vision application possibilities through our vision AI resource hub!

Take the first step and send us an email at edgeai@seeed.cc to become a part of this exciting journey! 

Download our latest Jetson Catalog to find one option that suits you well. If you can’t find the off-the-shelf Jetson hardware solution for your needs, please check out our customization services, and submit a new product inquiry to us at odm@seeed.cc for evaluation.

The post Pharmaceutical Production with AI-Powered Process Monitoring appeared first on Latest Open Tech From Seeed.

Discover the latest Co-create line-up: Loko GPS Tracker, XIAO PowerBread, XIAO Logger HAT, Smart Citizen Kit, Mech_hexpod, Louder ESP32

27 December 2024 at 10:41

We are thrilled to introduce our latest collection of Co-create products, launched to enhance user experience and foster creativity. This new collection brings together a diverse range of items, each designed in collaboration with our partners. By incorporating valuable insights and ideas directly from our community, we have created a line-up that truly reflects the needs and desires of our users.

Loko is an advanced, ultra-compact offline GPS tracking system utilizing LoRa (Long Range) radio technology for extended-range communication without cellular infrastructure dependency. This dual-unit system comprises a compact transmitter (30 x 22 mm, 14g) and a receiver, offering precise geolocation services with a 15+ km operational radius.

  • Independent Operation: No cellular signal or internet is required, allowing for offline functionality and navigation using pre-downloaded OpenStreetMap areas.

  • Comprehensive Tracking Features: Offers accurate metrics such as latitude, longitude, altitude, and speed, with real-time GPS tracking and data logging capabilities.

  • Multi-Device and Long-Range Support: Capable of tracking up to 30 air units per ground unit over a tested range of 15+ km, with a battery life of up to a year on a single charge.

  • Developer-Friendly and Secure: Open-source design with customizable features, supporting LoRaWAN and LoRa P2P communication, along with AES128 encryption for secure data transmission.

  • Durable and Versatile Applications: Rugged, water-resistant design suitable for various uses such as drone recovery, wildlife tracking, and outdoor adventure sports.

Check out here: https://www.seeedstudio.com/Loko-GPS-Tracker-p-6261.html

XIAO PowerBread is a compact, high-power breadboard supply with built-in monitoring. It offers stable 3.3V and 5V outputs and real-time tracking of voltage, current, and power on its LCD display. Fully compatible with Seeed Studio XIAO dev boards and breadboards, it’s perfect for prototyping with visibility. Fully open-source and actively maintained by the designer, with easy-to-use documentation and customizable code.

Key Features

  • Real-Time Monitoring: Integrated LCD display provides instant access to voltage, current, and power metrics, no multimeter needed.
  • High-Current Output: Supplies up to 1.5A of stable 3.3V power, making it suitable for a variety of breadboard electronics projects.
  • Plug-and-Play Design: Easily connects to standard breadboards for quick prototyping without additional setup.
  • Open-Source Compatibility: Works with various Seeed Studio XIAO dev boards, including  XIAO RP2040XIAO RP2350XIAO ESP32C3XIAO ESP32S3, and XIAO ESP32C6(The support for XIAO SAMD21 and XIAO RA4M1 will be coming soon). It allows for flexible extensions and customizations.
  • Accurate Sensing and Monitoring: Features dual-channel voltage and current sensing, along with precise temperature and humidity readings, ideal for detailed power supply analysis and data logging.

Check out here: https://www.seeedstudio.com/XIAO-PowerBread-p-6318.html

This little hat add-on for XIAO incorporates a Sensirion SHT40 temperature and humidity sensor, the BH1750 ambient light sensor, a PCF8563 real-time clock for accurate timekeeping, and an enableable voltage divider to keep track of the battery voltage.

Key Features

  • Compact Design: The device has a tiny footprint, making it compatible with all Seeed Studio XIAO microcontroller boards, ideal for space-constrained projects.
  • Low Power Consumption: GPIO-powered sensors enable a no-power sleep mode, with the always-on RTC consuming less than 1 µA, suitable for battery-operated data loggers.
  • I2C Communication: Supports easy programming using existing libraries and allows for the addition of multiple sensors on the same I2C bus.
  • On-Board RTC: Features the PCF8563 chip for accurate timekeeping, essential for long-term data logging, with programmable interrupts for waking from deep sleep.
  • Accurate Monitoring and Battery Management: The SHT40 sensor offers precise temperature and humidity readings, while the system allows safe monitoring of battery status through a voltage divider connected to the lithium-ion battery.

Check out here: https://www.seeedstudio.com/XIAO-LOG-p-6341.html

The Smart Citizen Kit 2.3 allows people to easily collect environmental data such as air and noise pollution, visualize it, and share it with the world through the Smart Citizen platform. All this while being completely open source and customizable to your needs. Built by communities for communities.

Key Features

  • Multi-Sensor Capabilities: The new SCK2.3 is compatible with the previous SCK2.1. It brings new sensors, more customization, and exciting features that allow anyone to accurately measure and collect better quality data, including UV readings, an improved PM sensor to better measure air quality, along with the classic sensors from the previous SCK2.1: temperature, humidity, noise and light pollution.
  • User-Friendly Interface: The SCK2.3 is designed to allow anyone to start measuring in no time, making it accessible for beginners,educators, and researchers alike.
  • Open Source Hardware with Customization Options: As with previous versions, the SCK2.3 is fully open source, allowing users to modify and customize its hardware and firmware, tailoring the SCK to meet their specific needs. In addition, Fab Lab Barcelona has a wide range of open-source designs that allow users to 3D print and build their enclosures, recycling them when they are done, and saving some industrial plastic manufacturing in the process.
  • Data Sharing and Visualization: Collected data can be uploaded to the Smart Citizen Platform, where users can visualize their findings through easy-to-read graphs. The Smart Citizen Platform is completely open for people to access, making it easy for anyone to play, experiment, and work with environmental data!
  • Various data-logging options: The SCK2.3 is designed to publish data using your home or office Wi-Fi and can store data in CSV format on a MicroSD. It also includes an internal memory to store more than a month’s worth of data in case the device loses its Wi-Fi connection. Data is published automatically when the connection is recovered.

Check out here: https://www.seeedstudio.com/Smart-Citizen2-3-p-6327.html

Upcoming product: Mech_hexpod

Mech_hexpod is a hexapod robot developed based on Arduino nano. It uses Atmel328p chip as the main control. It is remote controlled via Bluetooth communication using a mobile phone app/joystick. Mech_hexpod can realise 3 types of modes: Dance, Walk, Stance, and at the same time, each type of mode has 8 different styles.

Key Features

  • Arduino-Compatible: Powered by the Atmel328p chip, it supports Arduino programming, allowing easy customization and learning.
  • Bluetooth Control: Controlled via a mobile app or external controller using Bluetooth, providing convenient and user-friendly operation.
  • Multiple Modes: Offers Dance, Walking, and Combat modes, each featuring various gaits, dance poses, and combat moves for diverse gameplay experiences.
  • Durable Servos: Features 12 all-metal MG90S servos, with 2 per leg, ensuring reliable and robust movement stability.
  • Expandable and Customizable: Supports UART for easy integration of additional modules, such as voice or image recognition, enhancing expandability and customization options.

The Mech_hexpod is already list on Taobao and will be soon available at the Seeed Studio Bazaar.

 

Upcoming product: Louder ESP32

Louder-ESP32 combines ubiquitous ESP32 with an I2S DAC with built-in D-class amplifier capable of driving full-size speakers. This combination provides your compact ESP32 module with the necessary memory and RAM capabilities to develop Hi-Fi products.

Key Features

  • Powerful Audio Output: Integrates an I2S DAC with a built-in D-class amplifier, capable of driving full-size speakers for high-quality sound.
  • Hi-Fi Product Development: Combines the ESP32’s processing power with enhanced memory and RAM, making it suitable for developing Hi-Fi audio applications.
  • Compact Design: The Louder-ESP32 maintains a compact form factor while providing robust audio capabilities, ideal for space-constrained projects.
  • Versatile Compatibility: Works seamlessly with various ESP32 projects, allowing for easy integration into existing setups.
  • Easy Audio Streaming: Supports multiple streaming protocols, enabling straightforward audio playback and streaming capabilities.

It’s worth mentioning that the Louder ESP32 is not only a popular selling product on Tindie but will also soon be available at the Seeed Studio Bazaar.

 

Co-create with Seeed Fusion

As we celebrate the launch of our new collection of Co-create products, we invite you to join us in this exciting journey. Your insights, creativity, and feedback are invaluable in shaping the future of our offerings. Together, we can create products that truly meet the needs of our community. 

Seeed Fusion is dedicated to elevating your innovative ideas into products and solutions for various verticals. With the full range of open-source modules and industry-grade devices, expertise in product design, experience in production, and resources in glocal community and marketing. We’re your go-to partner from 0 to ∞Co-Create with Seeed Fusion, you can leverage Seeed’s capabilities in PrototypeProduce, and Promote, ranging from custom design, manufacturing to selling, covering the full product lifecycle from idea to delivery and iteration!

Let’s work together to innovate and develop solutions that resonate with all of us. 

Visit here to learn more about how you can participate in the Co-create! Your voice matters, let’s turn ideas into reality!

The post Discover the latest Co-create line-up: Loko GPS Tracker, XIAO PowerBread, XIAO Logger HAT, Smart Citizen Kit, Mech_hexpod, Louder ESP32 appeared first on Latest Open Tech From Seeed.

2024 reCamera reCap – AI Camera Growing on the Way

26 December 2024 at 15:00

Dear All,

It’s been four months since our tiny AI superstar, reCamera, first stepped into the spotlight among our developer community. From its humble beginnings to the milestones we’ve achieved together, reCamera has become the trusted companion, continually inspiring creativity and innovation in edge AI and robotics. Now, as we look back at the journey so far, it’s the perfect moment to revisit how it all started, celebrate the progress we’ve made, and explore the exciting possibilities that await in the next chapter!

Have you heard about reCamera? What makes it unique?

reCamera comes with its processor and camera sensor. It’s the first open-source, tiny AI camera, programmable and customized, powered by an RISC-V SoC, delivering 1TOPS AI performance with video encoding 5MP@30fps. The modular hardware design gives you freedom to change various camera sensors and diverse interfaces baseboard as requirement, offering the most versitile platform for developers tackling vision AI systems.

Hardware checking list

  • Core board: CPU, RAM, 8GB/64GB eMMC, and wireless module as customized antenna on-board
  • Sensor board: currently compatible with OV5647/IMX335/SC130GS camera sensor, and continuously supporting more on the list, along with other sensors: mic, speaker, actuator, LED.
  • Base board: determines the communication ports at reCamera’s bottom, we have USB2.0, ethernet, and serial port by default, open to be customized as you want – PoE/CAN/RS485/Display/Gyro/Type-C/vertical Type-C, etc.
  • Core board covering by metal mainframe, along with the rubber ring wrapped inside the grooves for waterproofing and excellent temperature maintainance below 50℃.

OS & Dashboard

Well, the very first and important impression you should get from reCamera is that it’s already a computer. We set up the build root system, a lightweight customized Linux system in multi-thread, running all tasks without worrying about the conflicts. It supports Python and Node.js directly from console. You can also easily deploy the compiled executive files from C/Rust, so, very programming-friendly.

Just in case you’d prefer to forget about all programming scripts and complex configurations 🙂 we’ve pre-built Node-RED integration for you, to build up your whole workflow in NO-CODE. It’s completely simple to start by choosing the customized nodes for reCamera pipeline, linking each other to call the camera API, and using the NPU to load AI models directly onto the device. Finally, a web UI or mobile dashboard could show up seamlessly and help verify results effortlessly.

So far, what we’ve done

Ultralytics & reCamera

Besides the standard reCamera as a standalone device only with hardware combination and Node-RED integration, we also provide you another option that can be more seamless to build your vision AI project – reCamera pre-installed with Ultralytics YOLO11 model (YOLO11n)! It comes with the native support and licensing for Ultralytics YOLO, offering real-world solutions such as object counting, heatmap, blurring, and security systems, enhancing efficiency and accuracy in diverse industries.

Application demos

1. reCamera voice control gimbal: we used Llama3 and LLaVA deployed on reComputer Jetson Orin. The whole setup is fully local, reading live video streamed from reCamera to get the basic perception of the current situation, and delivering instructions through Jetson “brain” thinking. Now, you can ask reCamera to turn left to check how many people are there and describe what it sees!

2. reCamera with Wi-Fi HaLow: We’ve tested reCamera with Wi-Fi HaLow long-range connectivity, linear distance could be up to 1km in stable!

3. Live-check reCamera detecting results through any browser: With pre-built Node-RED for on-device workflow configuration, you can quickly build and modify your applications on it, and check out video streams with various platforms.

4. reCamera with LeRobot arm: We used reCamera to scan ArUco markers to identify specific objects and utilized the ROS architecture to control the robotic arm.

Milestone – ready to see you in the real world!

July: prototype in reCamera gimbal

August: First show up: in Seeed “Making Next Gadget” Livestream

September: Introduce reCamera to the world

October: unboxing

November: first batch shipping on the way

December: “gimbal” bells coming – reCamera gimbal alpha test

Where our reCamera has traveled

  • California, US – K-Hacks0.2 humanoid robotics hackathon 12/14-15
  • Shanghai, China – ROSCON China 2024 12/08
  • Barcelona, France – Smart City Expo World Congress 2024 11/05-07
  • California, US – MakerFaire Bay Area 10/18-20
  • Madrid, Spain – YOLO Vision 2024 09/27

Wiki & GitHub resources

Seeed Wiki:

Seeed GitHub:

Appreciate community contribution on reCamera resources from our Discord group:

Listen to users: upon Alpha Test reviews

Based on insights from the Alpha test and feedback during the official product launch, we’ve gained invaluable input from our developer community. Many of you have voiced specific requests, such as waterproofing the entire device, integrating NIR infrared, thermal imaging, and night vision camera sensors with reCamera. These features are crucial, and we’re committed to diving deeper into their development to bring them to life. Your enthusiasm and support mean the world to us—thank you for being part of this journey.

Some adorable moments~

In addition, we’ve selected four Alpha testers to explore fresh ideas and contribute to hardware iterations by trying out the reCamera gimbal. Stay tuned for our updates, and continue to join us as we embark on this exciting path of growth and innovation!

Warm Regards,

AI Robotics Team @ Seeed Studio

The post 2024 reCamera reCap – AI Camera Growing on the Way appeared first on Latest Open Tech From Seeed.

Seeed Studio XIAO, Now Solder-Free

By: Lily
24 December 2024 at 14:11

Hey XIAO enthusiasts! If you’re one of those dedicated fans who’ve collected all 12 XIAO Dev Boards (as of December 2024), you’ve probably noticed that only the classic XIAO SAMD21 (Seeedduino XIAO) comes in a pre-soldered option. We’ve heard your feedback loud and clear – soldering these thumb-sized boards can be quite challenging!

Great news to freshen the week: We’re thrilled to announce pre-soldered versions across our entire XIAO lineup! Here’s what’s coming:

Why pre-soldered? Simple! No more fiddling with soldering irons on such tiny soldering pads- just unbox and start creating. These boards are ready to work with all XIAO add-ons (sensors, connectivity modules, actuators, and Grove Expansions) in a quick snap, perfect for breadboard prototyping or direct project integration.

Take our XIAO Starter Kit, for example. Just snap your pre-soldered XIAO onto the Expansion Board, and you’ve instantly got access to over 300 Grove modules plug and play. Perfect for education, rapid prototyping, or anyone who wants to jump straight into their project!

What’s your favorite XIAO board? Which pre-soldered XIAO will you try first? We’d love to hear about your project ideas with these new updates. Comment below to let us know!

P.S. This update comes straight from your feedback through the Seeed Studio XIAO Open Roadmap on GitHub, an open collaborative platform on GitHub where the community decides what we build next (explore more details here). Have more ideas for the XIAO ecosystem? Join the discussion on our open roadmap – we’re always listening!

Notes at the end.

Hey community, we’re curating a monthly newsletter centering around the beloved Seeed Studio XIAO. If you want to stay up-to-date with:

🤖 Cool Projects from the Community to get inspiration and tutorials
📰 Product Updates: firmware update, new product spoiler
📖 Wiki Updates: new wikis + wiki contribution
📣 News: events, contests, and other community stuff

Please click the image below👇 to subscribe now!

The post Seeed Studio XIAO, Now Solder-Free appeared first on Latest Open Tech From Seeed.

Introducing the NVIDIA Jetson Orin™ Nano Super Developer Kit: Redefining Generative AI for Small Edge Devices

By: Elaine Wu
20 December 2024 at 21:29

As an Elite partner of the NVIDIA Partner Network, Seeed is excited to announce the release of the NVIDIA Jetson Orin™ Super Developer Kit. Delivering up to 67 TOPS of AI performancea 1.7x improvement over its predecessor—this compact platform enables seamless execution of generative AI models, including vision transformers, large language models (LLMs), and vision-language models.

Generative AI is transforming industries, but significant challenges remain:

  • High costs for cutting-edge hardware.
  • Cloud dependency with escalating fees.
  • Software optimization complexities.

At just $249, Orin Nano Super Developer Ki provides developers, students, and makers with the most affordable and accessible platform with the support of the NVIDIA AI software and a broad AI software ecosystem to democratize generative AI at the edge.

Existing Orin Nano Developer Kit users can unlock this performance boost with a simple software upgrade, enabling everyone to explore new possibilities with generative AI. Orin Nano Super Developer Kit is an exceptional platform for AI-powered robotics. Its compact size and robust performance make it ideal for state-of-the-art diffusion models, end-to-end robotic control systems, and applications such as autonomous navigation, object detection, and real-time sensor processing. Developers can leverage the NVIDIA Isaac™ robotics platform to streamline robotics workflows and build intelligent machines capable of operating in complex environments, unlocking innovations across industries of logistics, healthcare, and agriculture.

Jetson runs the NVIDIA AI software stack, providing access to powerful frameworks tailored to specific use cases:

  • NVIDIA Isaac™: Robotics applications.
  • NVIDIA Metropolis™: Vision AI development.
  • NVIDIA Holoscan™: Real-time sensor processing.
  • NVIDIA Omniverse™ Replicator: Synthetic data generation.
  • NVIDIA TAO Toolkit: Fine-tuning pre-trained AI models from the NGC™ catalog.

With the support of a robust software ecosystem, including NVIDIA’s TRT- LLM, developers benefit from accelerated inferencing, reduced latency, and enhanced efficiency.

The reference carrier board supports all Orin Nano and Orin NX modules, offering a versatile platform for various edge AI applications. Rich I/O options, including 2x MIPI CSI-2 connectors, M.2 expansion slots, and USB 3.2 ports, make it ideal for prototyping robotics, vision AI, and more.

The Jetson Orin Nano Super Developer Kit provides an affordable, high-performance alternative to cloud-based solutions, empowering developers to explore generative AI without recurring costs.

Technical Highlights

AI Performance67 INT8 TOPS
GPUNVIDIA Ampere architecture with 1024 CUDA cores and 32 tensor cores
CPU6-core Arm® Cortex®-A78AE v8.2 64-bit CPU 1.5MB L2 + 4MB L3
Memory8GB 128-bit LPDDR5
102 GB/s
StorageSupports SD card slot and external NVMe
Power7W–25W

Empowering Developers with a Thriving Ecosystem

As an Elite Partner in the NVIDIA Jetson Ecosystem, Seeed ensures developers have access to:

  • Cutting-edge hardware platforms tailored to the Jetson Orin Nano Super Developer Kit.
  • Expert support for cameras, sensors, and custom carrier boards.
  • A global network of AI-focused partners to accelerate your journey from prototype to product.

Seeed’s partnership with NVIDIA reflects our commitment to empowering developers with tools, support, and guidance for innovation in edge AI and generative AI.

Unlock Your Generative AI Playground

From robotics to video analytics and beyond, the Jetson Orin Nano Super Developer Kit is the ultimate platform for exploring the potential of generative AI. Whether you’re a student, maker, or developer, this solution makes innovation more accessible than ever before.

About Seeed

Seeed is a global leader in open hardware innovation and an NVIDIA Elite Partner, We specialize in cutting-edge open hardware platforms.We aim to democratize technology through IoT and AI, empowering developers worldwide to break barriers in hardware innovation.

The post Introducing the NVIDIA Jetson Orin™ Nano Super Developer Kit: Redefining Generative AI for Small Edge Devices appeared first on Latest Open Tech From Seeed.

Seeed Studio at the 2nd UIC TrainRail Hackathon: Advancing Innovation in the Railway Industry

By: Ellie Cai
13 December 2024 at 09:17

From November 23rd to 24th, 2024, the 2nd UIC TrainRail Hackathon Asia-Pacific Regional Competition took place at Southwest Jiaotong University in China. The event attracted over 200 talented students from across the Asia-Pacific region, forming 42 teams to explore solutions for the future of the railway industry. With themes centered on enhancing passenger experience, strengthening freight capacity, and optimizing operational efficiency, the competition brought fresh perspectives and innovative technologies to the sector.

Committed to nurturing innovation and driving industry progress, Seeed Studio was thrilled to support the competition, together with other institutions such as Khon Kaen University in Thailand and Yamanashi University in Japan.

We were happy to provide comprehensive support throughout the competition, including pre-competition technical guidance and a wide range of hardware resources such as XIAO series, Grove sensors, Arduino kits, LoRa E5 modules, and Raspberry Pi modules, etc, empowering participants to rapidly prototype their ideas and overcome technical challenges.

Teams from Southwest Jiaotong University and Shijiazhuang Railway University claimed the top prizes for their exceptional projects. They will represent the Asia-Pacific region at the global finals in April 2025.

Highlights of Winning Projects

Participants showcased a range of innovative projects that directly addressed real-world railway challenges. Notable projects included:

  • Railway Wind and Snow Disaster Early Warning and Response System: This system provides real-time monitoring and early warnings for railway operations under adverse weather conditions, enhancing safety and efficiency.
  • Automated Barrier-Free Platform System: Designed to improve accessibility for passengers with disabilities, this intelligent platform solution optimizes barrier-free services in railway transportation.
  • Contact Network Arc Intelligent Monitoring System: Employing vision and sensor technologies, this system offers an intelligent solution for railway equipment maintenance, significantly improving efficiency and accuracy.
  • AI-Powered Real-time Rail Defect Detection: Using AI models to analyze rail conditions in real-time for enhanced safety monitoring.
  • Smoke Purification Device for Trains: Improving air quality within train cabins for a more comfortable passenger experience.
  • Vibration-Based Railway Construction Personnel Monitoring: Employing vibration wave technology to monitor the dynamic changes in construction environments and enhance worker safety.
  • Real-time Monitoring of Load Distribution in Freight Trains: Ensuring the smooth operation and safety of freight trains by monitoring load distribution during transit.
  • Computer Vision-Based Pantograph Modal Analysis: Optimizing pantograph monitoring through visual technology to improve the efficiency of electrified railway operations.

The hackathon underscores the vital connection between education, international collaboration, and industry development. Seeed Studio is proud to have been a part of this event and is committed to empowering young innovators to drive the digital transformation of the railway industry.

Congratulation to all participants for their hard work and creativity!

The post Seeed Studio at the 2nd UIC TrainRail Hackathon: Advancing Innovation in the Railway Industry appeared first on Latest Open Tech From Seeed.

From Idea to Reality: Seeed and Flux.ai Speed Up Your Way to the Next Level!

11 December 2024 at 14:49

As many of you know, Seeed has always been committed to providing makers with easy-to-use and innovative products, services, and solutions. Over the past year, our partnership with Flux.ai has grown stronger than ever! 

Mind-blowing! Check Out What We've Created

For developers, Flux and Seeed have created a streamlined path from concept to reality. As an AI-driven design tool, Flux accelerates the PCB design process, while Seeed Studio Fusion provides rapid prototyping-PCB manufacturing & assembly services

This partnership has already empowered developers to bring their innovative ideas to life. By combining our expertise, we’ve been able to deliver exceptional results and generate significant visibility for these projects.  You can check them on our organization page at Flux!

We hope that our small support will bring significant changes to the areas and causes in need. Inspired by these projects? You’ll love what’s coming next!

LED Remix: Design the Next Generation

In order to invite more developers to co-create with us, we kickstart a campaign called LED Remix: Design the Next Generation!

ℹ How to Apply?

Step 1: Please fill out the form to submit your bravo project!

         🌟 Each participant is limited to two PCBA boards 100% completely FREE for one design, including PCB fabrication, the cost of parts, assembly, and shipping.

         🌟 Free usage of Flux.ai for 2 months

The project must include a LED design and a Xiao module, and use Flux.ai as the design tool❗

Step 2: After submitting your application, our team will promptly assess your design. Kindly await our team’s contact.

📅 Duration: 12th Dec. 2024- 12th Mar. 2025

By participating in this event, you agree to review your experience with us and allow us to share it and the design with the community on our social media platforms (Facebook, Twitter, blog, etc.).

ℹ If you’re currently short on ideas, don’t worry, we’re here to help!  

To provide you with some inspiration, we’ve invited Goku to design two mother projects below, which are designed by Flux.ai and manufactured at Seeed Studio Fusion

Feel free to build upon these projects and create your unique designs!🙌✊

It’s inspired by the character Destined One from “Black Myth: Wukong.” For this project, Goku uses 37 tiny pixel LEDs along with the Seeed Studio XIAO ESP32-C3 microcontroller, which will program with WLED.

➡Clone at Flux: https://www.flux.ai/gokux/black-myth-wukong

➡Detailed Tutorial: https://www.instructables.com/Lets-Make-a-Black-Myth-Wukong-LED-Art-PCB/

Ready to turn your Xiao ESP32-S3 into a smart lighting controller? WLED is the perfect tool for the job. This open-source web server lets you control both digital and analog LED strips, and even integrate with smart home platforms like Alexa and Google Assistant. Let’s get started!

➡Clone at Flux: https://www.flux.ai/seeedstudio/wled-rgb-led-driverp

➡Detailed Tutorial: https://www.instructables.com/WLED-ON-XIAO-ESP32/

Tips: You can find most of the components needed at Flux. If there are any questions during the design process, you can ask for help using the co-pilot. You can also go to Goku’s project file to view his designs, and it is possible to clone his project and make your own changes. We are ready to illuminate and spread your ideas coupled with projects anytime!​

Combining Flux’s AI-driven Auto-Layout with Seeed’s example projects makes it easy to create something uniquely yours quickly. Here’s how you can do it:
  • Step 1: Clone the Project
    • Start with a Seeed example project in Flux to avoid designing from scratch.
  • Step 2: Customize the Design
    • Use Flux’s editor and part library to customize the design, swap components, or add new functionality.
  • Step 3: Run the Auto-Layout
    • Let Flux’s AI optimize the placement and routing of components, ensuring your design is manufacturable and ready to go.

Auto-Layout uses AI to optimize component placement and routing while considering your design constraints. This ensures the layout is both functional and ready for manufacturing. Whether you’re adjusting an LED configuration or refining a component layout, Auto-Layout simplifies the process, allowing you to focus on your design.

Scale up your Creation with Seeed Studio Co-Create Program!

We will invite well-received LED Remix projects to the Seeed Studio Co-Create Program, where your products can be listed, sold and shipped directly by Seeed on the Seeed Studio Bazaar. We will also support designers to reach thousands of like-minded customers and distributors with Seeed’s global sales channels and social media presence.

Don’t hesitate! It’s a great chance to show off your ideas and skills. Join and fuel your passion now!

The post From Idea to Reality: Seeed and Flux.ai Speed Up Your Way to the Next Level! appeared first on Latest Open Tech From Seeed.

Matter vs Zigbee vs Thread: Which Is the Best Choice for Your Smart Home?

11 December 2024 at 13:03
Matter vs Zigbee vs Thread

With the rapid growth of the smart home market, devices and brands are becoming increasingly diverse. The key to an efficient and seamless smart home experience lies in how these devices communicate effectively and reliably. Among the many communication protocols, Matter, Zigbee, and Thread are the current mainstream options.

It’s important to understand the distinction between protocols and standards in this context. Communication protocols are the underlying technical specifications that define how devices communicate with each other. They outline the rules, formats, and procedures for data exchange. In contrast, standards provide a common framework to ensure interoperability between devices, often by leveraging one or more underlying protocols.

This article will introduce Matter, Zigbee, and Thread, three key technology options in the smart home domain. Matter is an emerging communication standard, while Zigbee and Thread are underlying communication protocols. We will delve into their respective characteristics and provide recommendations for your selection.

Core Parameter Comparison: Matter, Zigbee, and Thread

This table highlights the key differences between Matter, Zigbee, and Thread. It’s worth noting that Zigbee and Thread are underlying communication protocols, while Matter is a cross-platform standard that can utilize technologies like Thread and Wi-Fi.

Key Factors Zigbee Thread Matter
Protocol Base IEEE 802.15.4 (Low Power, Mesh Network) IPv6 (Low Power, Mesh Network) Relies on Thread, Wi-Fi, and Ethernet for transport
Network Topology Mesh Mesh Mesh
Internet Integration Requires a bridge for IP communication Requires a border router for internet and cloud integration Uses Thread and Wi-Fi for internet and cloud integration
Latency Moderate Low Low
Security AES-128 encryption, Zigbee Alliance standards Self-healing Mesh Network, IPv6 authentication Enhanced device authentication, encryption, and privacy protection
Market Adoption High—widely used in traditional smart home devices Growing—gaining traction in IoT devices Emerging—strong cross-platform compatibility and rapid adoption
Power Consumption Low Extremely low Varies by protocol base

Zigbee: The Classic Choice for Traditional Smart Home Devices

Zigbee is a mature wireless communication protocol designed for applications requiring low power and low data transmission. It is based on the IEEE 802.15.4 standard and typically operates in the 2.4 GHz band. In some regions, it also supports 868 MHz (Europe) and 915 MHz (US) frequencies, making it versatile for various use cases.

 

Advantages of Zigbee

  • Low Power Consumption: Extends device battery life, making it ideal for sensors, lighting, and other long-running devices.
  • Mesh Networking: Allows devices to relay signals to each other, ensuring wide coverage and reliable connectivity.
  • Strong Security: Utilizes AES-128 encryption to safeguard data communication.

 

Use Cases

  • Suitable for small local networks within a home, without complex internet integration.
  • Ideal for users who already own a significant number of Zigbee devices.

 

Recommended Devices:

Thread: The Communication Protocol for the Future

Thread is a next-generation wireless protocol backed by tech giants like Google, Apple, and Amazon. Built on IPv6, it provides efficient internet connectivity for smart home and IoT devices while supporting self-healing Mesh networks.

 

Advantages of Thread

  • Low Latency, High Reliability: Performs well in real-time applications such as voice assistants and live monitoring.
  • Self-Healing Mesh Network: Automatically reroutes signals in case of device failure, ensuring network stability.
  • IPv6-Based Local Network: Enables seamless device-to-device communication within a local area network. However, internet access requires a border router.

 

Use Cases

  • Suitable for fast-response applications, such as smart speakers and smart locks, that require stable and low-latency communication.
  • Ideal for building localized smart home networks where reliability and security are priorities.

 

Recommended Devices

Matter: The Future of Cross-Platform Smart Homes

Matter, developed by the Connectivity Standards Alliance (CSA), aims to solve compatibility issues among smart home devices with a unified standard. It not only supports Thread but is also compatible with Wi-Fi and Ethernet, enabling seamless cross-brand collaboration.

 

Advantages of Matter

  • Cross-Platform Compatibility: Allows devices from different brands to interoperate effortlessly.
  • Enhanced Security: Features upgraded device authentication and encryption mechanisms for privacy protection.
  • Simplified Setup: Reduces connection and configuration complexity with standardized protocols.

 

Use Cases

  • Perfect for building smart home ecosystems that integrate devices from multiple brands, enabling unified control through Matter.
  • Ideal for developers creating smart devices like lighting systems or smart plugs that seamlessly operate across platforms (e.g., Google Nest, Apple HomeKit, Amazon Alexa).

 

Recommended Devices

  • Seeed Studio XIAO MG24:A compact, low-power microcontroller for Matter over Thread and BLE. Ideal for battery-operated IoT devices.
  • Seeed Studio XIAO ESP32 Series:
    • Models: XIAO ESP32C3, XIAO ESP32S3, and XIAO ESP32C6.
    • Based on Espressif’s ESP-IDF (IoT Development Framework), the XIAO ESP32 Series supports Matter device development using robust ESP32 microcontrollers. This series is optimized for IoT development and provides a powerful platform for exploring Matter’s potential. Perfect for developers aiming to create Matter-enabled devices leveraging Wi-Fi, BLE, or Thread capabilities while enjoying the flexibility of ESP-IDF.

How to Choose: Zigbee, Thread, or Matter?

  • Choose Zigbee:
    • If you already own many Zigbee devices and don’t need internet integration.
    • Perfect for smart lighting systems or a home sensor network where devices communicate directly within a closed local environment.
  • Choose Thread:
    • If you need low-latency, highly reliable devices connected directly to the internet.
    • Ideal for smart locks, real-time cameras, or voice assistants requiring fast responses and stable communication.
  • Choose Matter:
    • If you need a future-proof, cross-platform solution with seamless integration.
    • Best for those building a smart home ecosystem from scratch or looking to unify devices from different manufacturers under one protocol.

Future Trends: Will Matter Become the Mainstream?

With growing support from tech giants like Google, Apple, and Amazon, Matter’s ecosystem is expanding rapidly. While Matter’s cross-platform compatibility is a significant advantage, Zigbee and Thread’s established ecosystems will continue to play vital roles in specific scenarios. In the future, these three protocols may coexist, excelling in different applications.

Summary

  • Zigbee: Ideal for traditional smart home devices with low power consumption and high stability.
  • Thread: A modern, IP-compatible solution suitable for IoT applications.
  • Matter: The future standard for solving compatibility issues across platforms.

 

In summary, Zigbee and Thread are underlying communication protocols, while Matter is a higher-level interoperability standard. In practical applications, we need to choose the appropriate underlying protocol based on specific requirements and ensure it supports the Matter standard, in order to achieve a cross-brand smart home ecosystem.

Visit Seeed Studio Bazaar now to explore high-quality hardware supporting Matter, Zigbee, and Thread, and build your ideal smart home effortlessly!

The post Matter vs Zigbee vs Thread: Which Is the Best Choice for Your Smart Home? appeared first on Latest Open Tech From Seeed.

❌
❌