The post Seeed Monthly Wrap-up for October 2024: Pushing Boundaries in Smart Sensing appeared first on Latest Open Tech From Seeed.

Join Seeed Studio at Smart City Expo World Congress (SCEWC) 2024 in Barcelona! As urban areas worldwide continue to evolve, the demand for smarter, more connected solutions is driving advancements in AI hardware and edge AIoT.

From November 5-7 at Gran Via, Hall 2, Booth F71, we’re excited to showcase our latest lineup of sensing, networking, and edge AI devices, designed to transform cities through real-time data, seamless connectivity, and high-speed AI processing at the edge.

1. AI Sensors: Multimodal Sensing for a Smarter Environment

A smart city depends on the ability to sense, monitor, and respond to its surroundings. Our AI sensors offer versatile environmental monitoring, long-range connectivity, and advanced scene detection. With over 100 open-source, pre-trained models, these sensors bring multimodal sensing to urban spaces, capturing data from air quality to traffic flow in real time to support an adaptable and responsive city environment.

Stay Connected in Remote Areas

Offering 4G, 5G, or WiFi connection even in remote areas, SenseCAP Card Tracker T1000-E is the world’s first IP65-rated Meshtastic device. Compact and card-sized, it easily fits in your pocket or attaches to assets, operating seamlessly on the Meshtastic LoRa mesh network. It offers high-precision, low-power positioning and communication. Additionally, the T1000-E features onboard sensors to provide temperature and light data, making it ideal for remote connectivity in unpredictable environments.

2. AI Gateways for Seamless Connectivity and Control

Cities are powered by data, and our AI IoT gateways function as hubs for data collection and connectivity. These gateways provide versatile connectivity options and advanced AI capabilities, collecting, processing, and distributing data across urban areas. By facilitating real-time adjustments and insights, our AI gateways help cities operate more efficiently and respond instantly to changing conditions.

3. Generative AI at the Edge with reThings Devices Powered by NVIDIA Jetson Orin

With reThings, powered by NVIDIA Jetson Orin modules, you can now deploy generative AI directly to the edge. Supporting advanced generative AI models such as Llama, LLaVA, and VLA, these devices push the boundaries of robotics intelligence and multimodal interactions. The deployment of generative AI at the edge enables cities to integrate more interactive and autonomous systems, streamlining everything from traffic management to public safety.

Develop Generative AI-Powered Visual AI Agents for the Edge

Powered by NVIDIA Jetson Orin modules, which deliver up to 275 TOPS AI performance for edge AI and robotics, visual AI agents can help unlock new possibilities for real-time video analytics in urban settings. These agents can analyze both recorded and live video, answer questions in natural language, summarize scenes, trigger alerts, and extract actionable insights. They support a wide range of applications, from object detection to security monitoring, making it easier to maintain safety and efficiency across city landscapes.

Jetson Platform Services (JPS) provides an AI service that allows optimized visual language models (VLMs) to run locally on the NVIDIA Jetson platform. This AI service can be combined with other components of JPS to build a mobile app integrated alert system. This system is capable of monitoring live streams for user-defined events and sending push notifications when the VLM detects the events.
Combined Vision AI and Generative AI with reCamera and Jetson Orin.

reCamera, our newly released vision AI platform, delivers next-gen video intelligence when paired with Jetson Orin. This configuration, running NVIDIA Metropolis software development kits for vision AI applications and VLMs, provides building blocks to quickly deploy fully functional systems for vision and other edge AI applications. Using the “TinyML + LLM” architecture demonstrated at NVIDIA GTC earlier this year, reCamera captures critical frames while Jetson Orin extracts insights through a VLM. For instance, if a user asks, “How many objects are in front of me on the right?”, the system will automatically adjust the camera with a gimbal, capture an image, and respond via speaker: “There are 3 objects in front of you on the right.” This seamless integration of vision and generative AI provides real-time, context-aware insights.

Join Us at Smart City Expo 2024

Explore how Seeed Studio’s AI hardware and edge AIoT solutions can transform urban spaces at Smart City Expo 2024. From multimodal sensing to generative AI at the edge, Seeed is here to empower the cities of tomorrow. Stop by Booth F71 in Hall 2 to see our demonstrations, connect with our team, and discover how our hardware solutions can help create a more connected, efficient, and responsive urban landscape.
Date: November 5-7, 2024
Location: Gran Via, Hall 2, Booth F71

We look forward to connecting with you at SCEWC 2024 and advancing the future of smart cities!

The post Seeed Studio at Smart City Expo 2024: Empowering the Future of Urban AI Hardware Solutions appeared first on Latest Open Tech From Seeed.

This October has been tremendously packed with my duty as Seeed Studio’s Ranger. From OSHWA to Pycon APAC 2024, every event left a great spot on my mind. Here is the recap for my activity this October 2024.

1. October 3rd 2024, OSHWA 24 Hours Membership Drive Show & Tell

This live online session is initiated by OSHWA and runs 24 hours straight. My session is scheduled to run at 6 PM local time. After rushing to be at home before my schedule, I managed to get on time and share my open-source projects on Hackster. After sharing my open-source projects, I introduce the Seeed Studio Co-Create Gadget campaign to the audience.

2. October 17th 2024, Transforming IoT with Edge Intelligence Seminar

This seminar is initiated by the student organization on my campus and has two speakers. The other speaker is one of my ex student whom now work as a cloud engineer. It is the perfect opportunity to introduce Seeed Studio to my campus while also giving the students insight into the latest technology in AI, Machine Learning, IoT, and Edge Computing.

In the seminar, I mainly focus on the next step of IoT which is the inclusivity of Machine Learning in IoT solutions and how reComputer could be a small compact solution to implement it.

3. October 25th 2024, Pycon APAC 2024

This is my highlight of the month because the Python Indonesia community is becoming the host for this year’s annual Python Conference of the Asia Pacific area. In total, there are 80 Speakers from across Asia pacific with hundreds of participants.

At Pycon I managed to schedule a workshop session on 25th October 2024 titled “Building IoT and Camera Project with XIAO ESP32S3 and Micropython”.

In this workshop, I shared various things that the XIAO ESP32S3 can do with Micropython such as basic input and output, camera stream, displaying JSON weather data on the OLED screen, and interacting with the Grove Vision AI V2 sensor.

4. November 2nd 2024, Internet of Things Seminar at Universitas Banten Jaya

A friend from another campus has invited me to this seminar. The location of campus is in Serang, a neighboring city from where I live and it is a 2-hour drive from home.

The material that I shared in this seminar is the same as what I shared at my previous seminar on my campus. The organizer told me that they don’t have much insight regarding IoT on campus, so this seminar could be a huge step for advancing the knowledge on their campus.

The post Hacktober Recap, Workshop and Seminar for Open Source Community appeared first on Latest Open Tech From Seeed.

The post Students and Faculty Explore New Frontiers of Design with Artificial Intelligence and XIAO ESP32S3 Sense at the Catholic University of Luis Amigó, Manizales appeared first on Latest Open Tech From Seeed.

The post Transforming City Fountain Management with SenseCAP LoRaWAN Weather Monitoring-Based Automation in Slovakia appeared first on Latest Open Tech From Seeed.

The post Meet Seeed Studio XIAO MG24, Tailored for Battery-Powered Matter Applications appeared first on Latest Open Tech From Seeed.

Hi Community,

First, we want to extend a heartfelt thanks to each of you for your interest and support for the SenseCAP T1000-E. Since its release, we’ve been thrilled to see it being widely adopted within the Meshtastic community, helping enthusiasts like you enhance your connectivity projects. Your feedback has been invaluable to us, highlighting what you love about the device and where we can make it even better.

FAQs and Debugging Tips

We’ve received a lot of insightful feedback from the community, and our team is actively investigating each single of them. We are committed to ensuring that your experience with the T1000-E is smooth and reliable.

To support you further, we’ve compiled a few common FAQs and tips:

1. Accidentally updated the wrong firmware

Before you update the firmware, please check the firmware file carefully and DO NOT FLASH ANY FIRMWARE OTHER THAN T1000-E FIRMWARE, this may cause unexpected errors.

– Solution:

If you accidentally update the wrong firmware, please flash the bootloader first, and then flash the application firmware.

2. Device bricked

a. The device can still enter the DFU mode

– Solution:

Flash the bootloader first, and then flash the application firmware.

b. The device can not enter the DFU mode, but you can see the serial port of your device

– Solution:

Using a serial tool, set the baud rate to 1200, and then click connect, try this process multiple times until the green light of the device is solid, once the device is restored to DFU mode, you can follow a. solution then.

3. Battery drop issue

Following our battery discharge test, we found that the T1000-E battery performs as expected. We’re enhancing the battery discharge curve report to provide users with a clearer and more accurate performance overview.

For more details, please check the T1000-E wiki, if your issues still cannot be solved, feel free to contact our tech support team at sensecap[at]seeed.cc !

Last but Not Least: New Meshtastic-Compatible Products

• SenseCAP Indicator for Meshtastic, Coming SOON

A 4-inch touch screen driven by ESP32-S3 and RP2040 Dual-MCUs. With the compatibility with Meshtastic, SenseCAP Indicator can be another game changer as your Meshtastic phone or you name it.

• XIAO ESP32S3 for Meshtastic & LoRa, Available for Pre-Order

A mini size LoRa Dev Kit with XIAO ESP32S3 and Wio-SX1262 LoRa module, with pre-flashed Meshtastic firmware, it’s ready for you to embark your journey with Meshtastic once it’s powered on.

– Get Started with XIAO ESP32 for Meshtastic

We’re Here for You

We are truly grateful for your dedication to improving the T1000-E. Your feedback has allowed us to make adjustments that benefit the entire Meshtastic community. If you have any further questions, suggestions, or ideas, don’t hesitate to share your insights with us on our discord.

Thank you once again for being part of the journey with us. Let’s keep pushing the boundaries of what’s possible together!

The post SenseCAP T1000-E for Meshtastic Update: FAQs, and Debugging Tips appeared first on Latest Open Tech From Seeed.

The post SeamPose Powered by XIAO nRF52840, Repurposing Seams for Upper-Body Pose Tracking with Smart Clothing appeared first on Latest Open Tech From Seeed.

The post Meet OpenUC2 10x AI Microscope, Making Advanced Microscopy Accessible to Everyone appeared first on Latest Open Tech From Seeed.

The post Seeed Studio and Blynk Expand Partnership to Enhance IoT Integration with LoRaWAN and MQTT appeared first on Latest Open Tech From Seeed.

Since we released the Wio Tracker 1110 Dev Kit and SenseCAP Card Tracker T1000-E, we’ve gotten a lot of feedback from the community to include a smaller, more affordable Meshtastic powered product. And our answer is the XIAO ESP32S3 for Meshtastic & LoRa. Sized as small as your thumb, and priced at only $9.9, it‘s the smallest dev kit for prototyping your first Meshtastic and LoRa/LoRaWAN projects.

XIAO ESP32S3 + Semtech SX1262 LoRa

Featuring the powerful thumb-sized XIAO ESP32S3 Dev Board and a Wio-SX1262 Extension Board, the XIAO ESP32S3 Dev Kit for Meshtastic & LoRa is a super mini LoRa dev kit supporting LoRa (862-930MHz) with a 5km LoRa range. It also supports WiFi, BLE for wireless communication with a range of 100m+. Built on the XIAO ESP32S3, the kit comes with a built-in power management systems, and can be expanded via IIC, UART, and other GPIO interfaces. Compatible with Arduino IDE, it’s available for pre-order now at $9.9, with an estimated shipping in November, 2024.

Key Features of XIAO ESP32S3 for Meshtastic and LoRa Dev Kit

• Meshtactic works out of the box: Pre-flashed with Meshtastic firmware, it is ready to work once powered on.
• Outstanding RF performance: Supports LoRa(862-930MHz) 2.4GHz Wi-Fi and BLE 5.0 dual wireless communication, support 2~5km(LoRa) and 100m+(Wi-Fi/BLE) remote communication when connected with U.FL antenna.
• Thumb-sized Compact Design: 21 x 18mm, adopting the classic form factor of Seeed Studio XIAO, suitable for space-limited projects.
• Powerful MCU Board: Incorporate the ESP32S3 32-bit, dual-core, Xtensa processor running at up to 240MHz, mounted multiple development ports, Arduino / MicroPython supported.
• Elaborate Power Design: Includes a Type-C USB interface and lithium battery charge management.
• Same Hardware for Multiple Applications: Can be developed as a Meshtastic node or router, a single-channel LoRaWAN gateway, or a LoRa & LoRaWAN sensor.

Applications of XIAO ESP32S3 for Meshtastic & LoRa

1.  Tap into Meshtastic for Off-Grid Communication

Meshtastic is an open-source, off-grid, decentralized LoRa mesh network designed for affordable, low-power devices. This XIAO ESP32S3 Dev Kit offers a flexible and cost-effective solution for Meshtastic developers. You can build a Meshtastic device at an affordable price and use it as an emergency communication tool, similar to the SenseCAP T1000-E, but simpler in function. Moreover, thanks to the amazing Seeed Studio XIAO Product Ecosystem, it’s compatible with the XIAO Expansion Board and the Grove Expansion Board for adding screens, sensors, and over 300+ Grove modules, allowing you to customize your unique Meshtastic devices. You can even design your own casing.

2.  Configure It as a LoRa/LoRaWAN Sensor Node

It can be set up as a LoRa node, enabling the XIAO ESP32S3 Dev Kit to connect with various sensors and transmit data using LoRaWAN. This offers flexibility for different applications, like home automation. Essentially, the XIAO ESP32S3 Dev Kit can serve as a data collection and transmission node, allowing for communication and control among smart home devices.

3.  The Most Cost-Effective Single-Channel LoRa/LoRaWAN Gateway

Thanks to the powerful Semtech SX1262 LoRa Chip, you can turn it into a single-channel gateway, making it the most cost effective single-channel LoRaWAN gateway in the world. It receives LoRa packets on a specific setting and share them with the LoRaWAN network. By using the XIAO ESP32S3 Dev Kit, you can set it up to connect to The Things Network or Chripstack. This kit is great for those who want to learn about LoRa technology and connect to a LoRa Network Server (LNS).

Some Useful Links

Here are some guides for you to get started:

1. Get Started for Meshtastic
2. Get Started for LoRa
3. Connect to TTN
4. Connect to Chripstack

Pre-Order Now at $9.9

Available for pre-order now at just $9.9, the XIAO ESP32S3 Dev Kit is one of our solutions to provide the community more affordable and flexible products for you to build your LoRa-based IoT projects. Stay tuned for more updates on our Meshtastic-powered and LoRaWAN products. If you have any ideas or suggestions about our Meshtastic-compatible products, feel free to share them in the comments!

The post Introducing XIAO ESP32S3 for Meshtastic, The Smallest LoRa Dev Kit in The World appeared first on Latest Open Tech From Seeed.

The post WatchThis: A Wearable Point-and-Ask Interface Powered by Vision-Language Models and XIAO ESP32S3 Sense appeared first on Latest Open Tech From Seeed.

ZBT-1 USB Device Now Available! We are pleased to announce that we have received the latest batch of quality-approved ZBT-1 USB devices from Nabu Casa.
Updated on October 23

---

You may have heard about Nabu Casa’s announcement regarding a non-conforming part in the ZBT-1 USB device. As a partner of Nabu Casa, Seeed Studio is committed to quickly addressing this issue. We are working closely with the official team to provide effective after-sales support. Once we receive your returned product, we will arrange for a replacement device to be shipped to you at no additional cost or offer you a refund.

Replacement Program Details:

Eligibility:
To qualify for the replacement program, please ensure the following:
● Your order was placed directly through the Seeed Studio online store.
● The order was made before October 1; any devices ordered after this date are unaffected, as the issue has already been resolved.
● The product in question is the Home Assistant ZBT-1, and not the Home Assistant SkyConnect.

SkyConnect (left) and ZBT-1 (right) branded devices, SkyConnect are unaffected by this issue.

All ZBT-1 branded devices produced, as of October 2024, are believed to have this fault. You can tell if your device is a ZBT-1 by checking the white label on the back for “ZBT-1”. There is no need to test if your device is affected by this fault.

Replacement Process:

If you wish to participate in the replacement program, kindly reach out to us by emailing techsupport@seeed.io.

• Please include a photo of your product along with your order number in your email. This will help our team confirm if your product is part of the affected batch.

• After confirmation, you will need to return the original ZBT-1 unit to us and Seeed Studio will cover all associated costs. Please note that you only need to return the blue USB device; there’s no need to return any other accessories or packaging.

• Once we receive your returned product, we will arrange for a replacement device to be shipped to you at no additional cost or offer you a refund. However, due to customs policies, you may need to cover any applicable duties or taxes associated with the replacement. To support you, we will provide a coupon as compensation.

Extended Replacement Period:

Because the issues caused by the non-conforming part may only arise in certain setups, Nabu Casa will offer the replacement program for 60 months. This allows users who are currently using their ZBT-1 without problems to have peace of mind, knowing they can replace their affected device free of charge at any time within the next 60 months.

For more details, please refer to Nabu Casa’s official announcement here:Home Assistant Blog

Thank you for your understanding and continued support. We are here to assist you every step of the way!

The post Important Update: ZBT-1 USB Device Free Replacement Program appeared first on Latest Open Tech From Seeed.

The post MFSZ24 Factory Hi Tour: Step into the future of Shenzhen manufacturing appeared first on Latest Open Tech From Seeed.

The post Seeed Studio Sponsors MakeUC 2024 to Empower Innovation appeared first on Latest Open Tech From Seeed.

The post Simulate Your XIAO ESP32 Projects with Wokwi NOW appeared first on Latest Open Tech From Seeed.

Explore the best smart audio devices and microphones designed for seamless integration with Home Assistant, and partial compatibility with Amazon Alexa and Google Assistant. Whether you’re building a voice-activated smart home or a DIY audio project, these products offer high-performance sound capture and voice control.

Why You Need a Smart Speaker for Home Assistant

In a smart home setup, audio devices such as microphones and speakers play a critical role in enhancing voice control and automation. These products integrate seamlessly with Home Assistant, while some may also be compatible with Amazon Alexa or Google Assistant through additional setup. Here, we’ll explore the top ReSpeaker and Grove products that enable robust voice interaction and sound management for DIY smart home systems.

Best Smart Speakers for Home Assistant

1.  ReSpeaker Lite with XIAO ESP32S3

The ReSpeaker Lite with XIAO ESP32S3 is a powerful development kit designed for voice interaction and smart home projects. Featuring dual microphones for far-field voice capture and onboard AI algorithms, this kit is ideal for integrating with Home Assistant via ESPHome and works seamlessly with Amazon Alexa and Google Assistant.

Key Features:

• Pre-soldered XIAO ESP32S3 controller for easy development
• Dual microphone array for capturing speech up to 3 meters
• AI NLU algorithms for noise cancellation and echo suppression
• Compatible with popular platforms such as Arduino, PlatformIO, and MicroPython
• Onboard RGB LED for visual feedback

Price: Available now for just $29.90.

2.  ReSpeaker 2-Mics Pi HAT

The ReSpeaker 2-Mics Pi HAT is designed for Raspberry Pi projects and features two analog microphones with high-definition voice capture capabilities. It is equipped with Voice Activity Detection and Direction of Arrival algorithms, making it perfect for local voice recognition tasks with Home Assistant and other DIY voice interaction applications.

Key Features:

• Dual analog microphones and WM8960 Audio Codec for high-quality sound
• Voice Activity Detection, Direction of Arrival, and Keyword Spotting capabilities
• RGB LED and programmable button for customized control
• Simple assembly with Raspberry Pi

Price: Starting at $12.90, get yours today.

3.  Mono Enclosed Speaker

This high-performance speaker is ideal for audio output in various smart home projects. It integrates easily with devices like the ReSpeaker Lite to enhance audio quality for voice commands, notifications, or media playback in Home Assistant setups.

Key Features:

• Compact, enclosed design for enhanced sound quality
• Suitable for smart home audio systems, robot voice output, and DIY audio projects
• Easy to integrate with Home Assistant

Price: Currently priced at $2.00, a budget-friendly option.

4.  ReSpeaker USB Mic Array

The ReSpeaker USB Mic Array is perfect for far-field voice recognition in larger spaces. It includes four microphones and advanced speech algorithms such as Beamforming, Noise Suppression, and Acoustic Echo Cancellation, making it ideal for voice-controlled smart home environments.

Key Features:

• Plug-and-play functionality, no drivers required
• Far-field voice capture with four microphones
• Advanced speech processing algorithms
• Compatible with Windows, macOS, Linux, and Android

Price: Grab it now for only $69.00.

5.  ReSpeaker Mic Array v2.0

An upgrade to the original ReSpeaker Mic Array, the ReSpeaker Mic Array v2.0 is equipped with XMOS’s XVF-3000 chip and supports far-field voice capture. This version improves voice recognition accuracy, making it a robust solution for adding a voice interface to your existing or future smart home products.

Key Features:

• Far-field voice recognition with four microphones
• USB Audio Class 1.0 compatibility
• Includes advanced algorithms like Voice Activity Detection, Direction of Arrival, and Noise Suppression
• Compatible with all major operating systems

Price: Available at $64.00, offering premium performance.

6.  ReSpeaker Lite

Powered by the XMOS XU316 AI Sound chip, this development board excels in audio processing and speech recognition. With its dual microphone array and support for external power supplies, it is a perfect solution for DIY smart home audio systems or voice-controlled projects.

Key Features:

• Dual microphone array for far-field voice capture
• Onboard AI algorithms for noise suppression and echo cancellation
• Supports I2S and USB connections
• Compatible with XIAO ESP32S3, Adafruit QT Py, Raspberry Pi, and PC
• Programmable RGB LED for visual feedback

Price: Now available for $24.90, offering great value.

7.  Grove – Speaker

The Grove – Speaker module is perfect for DIY projects, providing sound amplification and voice output. Its on-board potentiometer allows for loudness control, and it is compatible with Arduino platforms for building custom sound systems or music boxes.

Key Features:

• Simple module for voice output and sound generation
• Compatible with Arduino for easy project integration
• Adjustable loudness via onboard potentiometer

Price: Get it for only $5.90, an excellent choice for simple integrations.

How to Choose the Best Smart Speaker for Home Assistant

When choosing an audio device for your smart home or DIY project, consider the following:

1. Voice Recognition Capability: Devices like the ReSpeaker USB Mic Array and ReSpeaker Mic Array v2.0 are ideal for far-field voice recognition in noisy environments.
2. Platform Compatibility: Ensure the product supports the platform you’re using, whether it’s Home Assistant, Amazon Alexa, or Google Assistant. Most of these devices are compatible with ESPHome for Home Assistant integration.
3. Budget: From the affordable Mono Enclosed Speaker to the feature-rich ReSpeaker Mic Array v2.0, there are options for all budgets.
4. Customizability: Products like the ReSpeaker Lite offer flexibility for developers, with open-source compatibility and support for multiple programming platforms.

Use Case Ideas for Home Assistant Speakers

1. Home Automation with Voice Control: Integrate the ReSpeaker Lite with XIAO ESP32S3 with Home Assistant to control smart devices like lights, thermostats, or security systems via voice commands.
2. Audio Alerts and Notifications: Use the Mono Enclosed Speaker or Grove – Speaker to generate audio alerts for events like door openings or motion detection in your smart home.
3. Far-Field Voice Recognition: With the ReSpeaker USB Mic Array, capture voice commands from across the room, ideal for large, open living spaces.

Conclusion

These ReSpeaker and Grove products offer robust solutions for building voice-activated smart homes or custom audio systems. While they seamlessly integrate with Home Assistant, some products may also work with Amazon Alexa or Google Assistant, though additional setup or configurations might be required. These devices provide the flexibility and performance needed to bring your DIY smart home projects to life.

Explore our range of Home Assistant-compatible speakers and take your home automation to the next level!

The post Home Assistant Speaker: Enhance Your Smart Home with the Right Devices appeared first on Latest Open Tech From Seeed.

The post MONOKEY, The One-Button Bluetooth Keyboard Powered by XIAO ESP32C3 appeared first on Latest Open Tech From Seeed.

Ver+Escuchar, Comprender y Reaccionar | IA Integrada | ChatGPT / LLM | Interacción por

Voz | Animación | Implementación Privada | HTTP | + Sensores.

un espacio específico; entonces, los LLM podrían entender lo que está sucediendo allí.

Por ejemplo, puede detectar a una persona sosteniendo un Nintendo Switch frente a un

estante o a dos personas con trajes leyendo. Esta capacidad podría desencadenar

automáticamente muchas acciones basadas en las escenas, como sugerir los juegos más

recientes a la persona con el Switch o enviar un mensaje al vendedor para que venga a

ayudar.

Así que, traer los LLMs al mundo físico puede elevar significativamente la inteligencia

en edificios y hogares inteligentes. Sin embargo, ¿cómo añadir esta capacidad a los

sistemas de automatización existentes de manera fácil?

Nuestra solución es SenseCAP Watcher, el primer agente físico LLM del mundo para

espacios inteligentes.

SenseCAP Watcher está construido sobre ESP32S3, incorporando un chip de IA

Himax WiseEye2 HX6538 con Arm Cortex-M55 & Ethos-U55, que sobresale en el

procesamiento de imágenes y datos vectoriales. Equipado con una cámara, micrófono y

altavoz, SenseCAP Watcher puede ver, oír y hablar. Además, con la suite SenseCraft

habilitada por LLM, SenseCAP Watcher entiende tus comandos, percibe su entorno y activa

acciones en consecuencia.

Simplemente PRONUNCIA tu comando

Simplemente habla con Watcher, dile qué observar, y te notificará cuando ocurra el evento

especificado.

Puedes enviar comandos fácilmente presionando para hablar o desde la aplicación

SenseCraft.

Entendiendo lo que vé

Con modelos de IA integrados en el dispositivo, SenseCAP Watcher puede detectar

diferentes cosas: personas, manzanas, mascotas, etc. Sin embargo, la característica más

destacada de Watcher es su integración con LLMs.

Al aprovechar los LLMs, Watcher puede capturar los eventos precisos que especificaste, lo

que significa ir más allá de las simples detecciones de objetivos, ya que analiza

completamente comportamientos y estados. Como “perro + jugando con la pelota, 0

personas + en la habitación”, o “La persona + con uniforme de DHL ha llegado”, etc.

¡Watcher realmente entiende la escena bajo su vigilancia!

Llamar constantemente a los LLMs como ChatGPT genera un costo elevado. Por

lo tanto, utilizamos una arquitectura de IA en el dispositivo + LLMs. El modelo de IA en el

Watcher detecta el objetivo, que luego es analizado por LLM para generar ideas precisas y

accionables.

Con la tarea “dime si el perro está rompiendo papel”, cuando el modelo del dispositivo

detecta perros, esta escena clave se envía al LLM para un análisis más profundo: ¿está

rompiendo papel? Los LLM no se activarán por personas, gatos, ardillas u otros. Esto

reduce enormemente el costo de los LLM.

Responde por voz

Después de detectar el evento especificado, Watcher puede interactuar con los objetivos a

través de la voz. Por ejemplo, puedes configurarlo de la siguiente manera:

Evento especificado: alguien toma el teclado rosa;

Dos reacciones especificadas:

1. una respuesta por voz que diga: ‘¡Buena elección! Esta es nuestra versión más

reciente, inspirada en la máquina de escribir Pink Royal’;

2. la otra reacción es un mensaje de texto a los vendedores: ‘¡Alguien está interesado

en el teclado más reciente! Por favor, vayan al estante lo antes posible’.

Colocar Watcher en diferentes escenarios permite respuestas versátiles. Al ver un perro

rompiendo pañuelos, dile “¡Para, Cooper!”, o si ve a una persona fumando en áreas donde

no está permitido, dile “¡No fumar!”

¿Cómo mejorar tus sistemas? Solo necesitas un complemento

sencillo.

Una vez detectado el evento objetivo, puede activar diferentes acciones, por ejemplo, enviar

mensajes push en la aplicación SenseCraft o hacer que las luces LED de Watcher

parpadeen. Por supuesto, entendemos que quieres ir más allá de las funcionalidades en la

app o el dispositivo. ¡No hay problema! ¡Hay infinitas posibilidades para explorar!

Añade Watcher a Home Assistant.

Conectado a plataformas IoT como Home Assistant, tu Watcher actúa como un

sensor de comportamiento, activando acciones personalizadas en diversos contextos. Por

ejemplo, cuando detecta personas, Watcher analiza la situación y automáticamente

desencadena acciones: luces encendidas para leer y luces apagadas para dormir.

Más que un sensor de visión, Watcher se puede ampliar con otros sensores

para habilitar la detección multimodal. En la parte trasera de Watcher, el I2C está

reservado para acomodar más de 100 sensores Grove. Esta flexibilidad permite queWatcher integre una amplia gama de fuentes de datos para un análisis exhaustivo y

acciones apropiadas. Podrás construir aplicaciones como detectar la temperatura de la

habitación y ajustar el aire acondicionado en consecuencia: cambiarlo a 22°C cuando llevas

traje, o a 26°C cuando estás en shorts.

Añade Watcher a tu flujo de Node-RED

A solo 3 bloques de distancia, puedes transmitir los resultados detectados por tu Watcher a

cualquier lugar en internet a través de Node-RED, ¡tan fácil como hacer clic!

Añade Watcher a tu Arduino | ESP32 y otros sistemas de

hardware.

¿Quieres añadir un agente de IA a los MCU y SBC populares como

Arduino/ESP32/Raspberry Pi? Simplemente conéctalo a Watcher a través de UART, HTTP o

USB, y podrás explorar la nueva frontera de la inteligencia.

Dato curioso: Aquí en Seeed, Watcher tiene el apodo de “Nobody,” simbolizando

un robot sin cuerpo. Esto transmite un mensaje poderoso: ¡Dale a Watcher un cuerpo!

¡Watcher puede ser una cabeza genial para tu robot!

Para los fans de XIAO, ¡tenemos un paquete especial! Apoya a SenseCAP

Watcher y podrás añadir un XIAO ESP32C6 por solo $1.

XIAO ESP32C6 es un MCU compacto, nativo de Matter, para hogares inteligentes. Basado

en ESP32-C6 de Espressif, soporta diversas conectividades inalámbricas: Wi-Fi 6 a 2.4

GHz, BLE 5.0, Zigbee y Thread.

Por ejemplo, puedes hacer un sensor de emociones añadiendo Watcher a XIAO.

Al detectar tu mal humor, florece para animarte.

Dale emociones únicas a tu Watcher

SenseCAP Watcher se adapta a tus comandos con “modos” únicos. Primero ESCUCHA tus

instrucciones, luego cambia al modo de VIGILANCIA para proteger el espacio designado,

etc. ¡Pero la diversión no termina aquí! Puedes subir tus propios diseños de emociones

para darle a tu Watcher una personalidad única. ¡Prepara un archivo PNG y súbelo a

Watcher en segundos! ¡Es tu decisión!

Los emojis predeterminados de Watcher están inspirados en C-3PO, en homenaje a uno de

nuestros mayores ayudantes.

Puedes subir los tuyos fácilmente en formato .PNG

Incluso puedes diseñar una interfaz de usuario (UI) única para tu SenseCAP

Watcher. Nuestra interfaz actual está impulsada por Squareline.

Open Source y despliegue On-Premise.

Como un dispositivo de IA, es fundamental respetar la privacidad. Y adoptamos e

implementamos dos estrategias clave en este ingenioso dispositivo.

1. SenseCAP Watcher es de código abierto, lo que te brinda acceso completo para

entender a fondo cómo funciona.

2. Soporta despliegue on-premise. La columna vertebral de SenseCAP Watcher es la

suite de software SenseCraft, que se utiliza para configurar Watcher, interpretar tus

comandos y acceder a los LLMs. Por lo tanto, todo está almacenado y ejecutándose

de manera privada, garantizando que tus modelos y datos no se envíen a ningún

LLM o nube pública. SenseCraft puede ejecutarse en Windows/MacOS/Linux. Dado

que SenseCraft contiene LLMs, ciertos criterios de rendimiento son necesarios para

la computadora, como se detalla a continuación.

Puedes desplegar SenseCraft en tus computadoras de repuesto. Sin embargo, si

buscas aplicaciones que requieran confiabilidad a nivel comercial y bajo consumo de

energía, la combinación de SenseCAP Watcher + NVIDIA® Jetson AGX Orin es perfecta

para ti.

En comparación con las tarjetas gráficas de consumo (como la RTX 4090) para

tareas de IA, NVIDIA® Jetson AGX Orin destaca con ventajas clave:

1. Confiabilidad a nivel industrial: Diseñada para aplicaciones industriales y

comerciales, la serie Jetson AGX cuenta con un MTBF (tiempo medio entre fallas)

más largo. Diseñada para operar las 24 horas del día, ofrece una confiabilidad

superior para aplicaciones de funcionamiento continuo, en comparación con las

tarjetas gráficas de consumo.

2. Compacta y de bajo consumo: Con aplicaciones de computación embebida y en el

borde en mente, la serie Jetson AGX está diseñada en un formato más pequeño y

consume más de 3 veces menos energía que las tarjetas gráficas de consumo. Es

adecuada para espacios reducidos, genera menos calor y ayuda a reducir los costos

operativos. Esto es crucial para los sistemas embebidos.

¿Suscripción? ¡Tú decides!

Los Servicios de IA de SenseCraft están diseñados para tus necesidades.

Empieza con Basic, completamente GRATIS para baja frecuencia: 15 minutos/solicitud para

análisis de imágenes, 200 chats/mes con LLMs.

¿Necesitas más? Solo $6.90 para la versión Pro, paga solo por lo que consumes, ¡SIN

compromiso de tarifas recurrentes! Además, ¡cada dispositivo NUEVO incluye un

paquete Pro GRATIS de $6.90! Recarga según sea necesario.

¿Quieres evitar tarifas por completo? Elige On-Premise. Simplemente despliega y usa sin

costos adicionales.

Dos modelos

Soporte para varios métodos de montaje.

Se puede colocar sobre un escritorio o montarlo en paredes como una expansión

inteligente. O también se puede transformar en la cabeza de un robot.

Otros lo usaron como

Personalización – El camino más rápido para construir hardware

con IA.

El próximo dispositivo debería estar impulsado por IA. ¡El hardware con IA incorporada

conectada a LLMs es la tendencia!

Con SenseCAP Watcher, hemos desarrollado un marco revolucionario que lleva potentes

LLMs al borde del mundo físico. Este marco acelera el prototipado de hardware con IA. Con

nuestros servicios de personalización, ¡puedes dar vida a tu hardware de IA más rápido que

nunca!

¡Es hora de aumentar la inteligencia de tu espacio! Estamos en

Discord.

¡Bienvenido a unirte a nuestra comunidad! Si tu prefieres escribirnos, puedes hacerlo por

medio del correo electrónico sensecap@seeed.cc.

Riesgos y desafíos

Hemos realizado pruebas exhaustivas con SenseCAP Watcher, y estamos completamente

comprometidos a entregarlo a tiempo a nuestros patrocinadores, con todo funcionando sinproblemas. No obstante, como sucede con cualquier nuevo producto, existen riesgos

potenciales asociados al lanzamiento.

Sin embargo, como una empresa consolidada con un historial probado de éxito en el

desarrollo de cientos de productos, sabemos cómo superar estos desafíos. Ten la seguridad

de que, si surgen problemas de producción, seremos completamente transparentes con

nuestros patrocinadores y los mantendremos informados durante todo el proceso.

Uso de la IA

Tengo pensado usar contenido generado por IA en mi proyecto.

¿Qué partes de tu proyecto utilizarán contenido generado por IA? Responde con la

mayor precisión posible.

Usaremos contenido generado por IA de MidJourney para crear imágenes que destaquen

las características de nuestro producto y muestran cómo puede ser usado en escenarios

reales. Además, utilizaré ChatGPT para la corrección de estilo de nuestra campaña.

¿Tienes el consentimiento de los propietarios de los trabajos que se usaron (o se

usarán) para producir la parte de tu proyecto generada por IA? Por favor, explica.

Para las imágenes que necesitamos, primero buscaremos en bibliotecas existentes en

Google. Si encontramos imágenes que puedan ser usadas directamente, verificaremos sus

licencias para determinar los pasos apropiados a seguir. Si las imágenes no pueden ser

usadas directamente, generamos nuestras propias imágenes.

The post SenseCAP Watcher – El Agente de IA Física para Espacios Inteligentes appeared first on Latest Open Tech From Seeed.

The ReSpeaker Lite Voice Assistant Kit has been available to community for some time, and thanks to your feedback, we’re thrilled to introduce several exciting updates! These enhancements make it even easier for voice assistant enthusiasts and DIYers to build their projects.

We recommend purchasing products from the ReSpeaker Lite Voice Assistant Kit, which includes:

1）ReSpeaker Lite

2） ReSpeaker Lite with XIAO ESP32S3

3）Mono Enclosed Speaker – 4R 5W

4）Acrylic Enclosure for ReSpeaker Lite

You can mix and match as you like.、

Firmware Update for Better Performance

We’ve updated the firmware to boost performance across the board. Be sure to download the latest version that matches your setup:

• USB version (for the ReSpeaker Lite):

respeaker_lite_usb_xmos_v2.0.5.bin

• I2S version (for the ReSpeaker Lite with XIAO ESP32S3):

respeaker_lite_i2s_xiao_1.0.7.bin

Check out our Firmware Upgrade Guide for step-by-step instructions.

Enclosure Installation Instruction

We’ve also added a detailed, easy-to-follow enclosure installation guide to help you safely assemble your ReSpeaker Lite setup. Watch the video and ensure your device is perfectly housed and ready to use:

Custom Enclosure Design Recommendations

If you’re designing your own enclosure, here are some important guidelines to ensure optimal audio performance:

1. Ensure that the distance between the speaker and the two microphones is uniform, and minimize the transmission of speaker vibrations to the microphones to maintain audio clarity.
2. The enclosure should allow human voice to reach each microphone without obstruction, ensuring direct sound (as opposed to reflected sound) can evenly reach both microphones for accurate sound capture.
3. If you are designing a sealed microphone chamber, avoid creating a resonant cavity that is narrow at both ends and wide in the middle, as this can interfere with front-end signal processing. If a sealed chamber is not feasible, incorporate multiple perforations in the enclosure to prevent sound reflections from bouncing inside before reaching the microphones. This helps to maintain signal integrity.

Beginner Tips for Easier Soldering

For beginners, we recommend using pin headers when soldering components. This makes the process smoother and helps reduce errors—perfect for those just getting started.

Get Involved and Stay Updated

We’re continuously working on more improvements, so stay tuned for future updates! In the meantime, check out our wiki for in-depth technical details. Have questions, suggestions, or ideas for new features or products? Drop them in the comments below—we’d love to hear from you!

For hardware customization, bulk orders, or distribution inquiries, please contact us at iot@seeed.cc.

The post ReSpeaker Lite Updates: New Firmware, Enclosure Tips and Installation Guide! appeared first on Latest Open Tech From Seeed.