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 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.

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:

• • XIAO MG24 3PCS Pack –  $19.35
  • XIAO MG24 Sense 3PCS Pack –  $27.00
  • XIAO MG24 Pre-Soldered –  $8.90
  • XIAO MG24 Sense Pre-Soldered –  $11.90

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

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.

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.

[Source: Daehwa Kim]

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

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.

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.

Imagine turning your everyday clothes into smart motion-tracking tools. That’s exactly what a team of researchers at Cornell University has achieved with SeamPose. This innovative project, led by Catherine Tianhong Yu and Professor Cheng Zhang uses conductive threads sewn over the seams of a shirt to transform it into an upper-body pose-tracking device by unleashing the power of XIAO nRF52840. Unlike traditional sensor-laden garments that change the clothing’s appearance and comfort, SeamPose blends seamlessly into everyday wear without compromising aesthetics or fit.

This project offers exciting potential applications in areas like health monitoring, sports analytics, AR/VR, and human-robot interaction by making wearable tracking more accessible and comfortable.

Hardwares

To build SeamPose, the following key hardware elements were used:

• • Long-sleeve T-shirt with machine-sewn conductive thread along the seams.
  • Customized Sensing Board:
    • XIAO nRF52840 
    • A 36x31mm board with two FDC2214 capacitance-to-digital converters
    • 3.7V 290mAh LiPo battery

How SeamPose Works

SeamPose operates by transforming ordinary seams in a long-sleeve shirt into capacitive sensors, enabling real-time tracking of upper-body movements. Conductive threads, specifically insulated silver-plated nylon, are machine-sewn along key seams—such as the shoulders and sleeves—without altering the garment’s appearance or comfort. As the wearer moves, the seams stretch and shift, causing variations in their capacitance. These signals are captured by a customized sensing board integrated with two FDC2214 capacitance-to-digital converters and the XIAO nRF52840 microcontroller. The XIAO nRF52840 transmits the data wirelessly via Bluetooth Low Energy (BLE) to a nearby computer for processing.

The transmitted signals are fed into a deep learning model that maps the seam data to 3D joint positions relative to the pelvis. This allows the system to interpret complex upper-body movements using only eight sensors distributed symmetrically along the shirt. During testing, SeamPose achieved a mean per joint position error (MPJPE) of 6.0 cm, comparable to more invasive tracking systems. The XIAO nRF52840 ensures seamless real-time data transmission, making SeamPose a breakthrough in wearable technology by combining comfort with precise motion tracking.

Source: Cornell University Team

What’s Next for SeamPose?

SeamPose offers a glimpse into the future of smart clothing, where everyday garments become powerful tools for motion tracking without sacrificing comfort or design. However, challenges like real-world deployment considerations and smart-clothing manufacturing at scale need to be addressed for broader adoption. The research team plans to explore improved seam placement and enhanced sensor calibration for even more accurate tracking in the future.

If you’re excited about SeamPose and want to dive deeper, check out their paper on ACM Digital Library