Silicon Labs uses Matter to bring AI to edge

  • January 24, 2022
  • Steve Rogerson

Texas-based electronics company Silicon Labs is bringing AI and machine learning to the edge with a platform that uses the Matter smart-home connectivity standard.

The BG24 and MG24 2.4GHz wireless systems-on-chip (SoCs) are for Bluetooth and multiple-protocol operations, respectively. This hardware and software platform should help bring AI and ML applications and wireless high performance to battery-powered edge devices.

Matter-ready, the low-power families support multiple wireless protocols and incorporate PSA level-three Secure Vault protection, suitable for diverse smart home, medical and industrial applications.

The SoCs use integrated AI and ML accelerators, and have support for Matter, Zigbee, OpenThread, Bluetooth Low Energy, Bluetooth mesh, proprietary and multi-protocol operation.

There is also a software toolkit designed to help developers quickly build and deploy AI and machine learning algorithms. It uses some of the most popular tool suites such as TensorFlow.

“The BG24 and MG24 wireless SoCs represent an awesome combination of industry capabilities including broad wireless multiprotocol support, battery life, machine learning and security for IoT edge applications,” said Matt Johnson, CEO of Silicon Labs.

IoT product designers see the potential of AI and machine learning to bring even more intelligence to edge applications such as home security systems, wearable medical monitors, sensors monitoring commercial facilities and industrial equipment. But those considering deploying AI or machine learning at the edge are faced with steep penalties in performance and energy use that may outweigh the benefits.

The BG24 and MG24 are designed to alleviate those penalties. The hardware is designed to handle complex calculations quickly and efficiently, with internal testing showing up to a four-times improvement in performance along with up to a six-times improvement in energy efficiency. Because the ML calculations are happening on the local device rather than in the cloud, network latency is eliminated for faster decision-making and actions.

The families also have large flash and ram capacities. This means they can evolve for multi-protocol support, Matter and trained ML algorithms for large datasets. PSA level-three-certified Secure Vault, the highest level of security certification for IoT devices, provides the security needed in products such as door locks, medical equipment and other sensitive deployments where hardening the device from external threats is paramount.

In addition to supporting TensorFlow natively, Silicon Labs has partnered with s AI and ML tools providers such as SensiML and Edge Impulse to ensure developers have an end-to-end toolchain that simplifies the development of machine-learning models optimised for embedded deployments of wireless applications. Using this AI and ML toolchain with Silicon Labs’s Simplicity Studio and the BG24 and MG24 SoCs, developers can create applications that draw information from various connected devices, all communicating with each other using Matter to make intelligent machine-learning-driven decisions.

For example, in a commercial office building, many lights are controlled by motion detectors that monitor occupancy to determine if the lights should be on or off. However, when typing at a desk with motion limited to hands and fingers, workers may be left in the dark when motion sensors alone cannot recognise their presence. By connecting audio sensors with motion detectors through the Matter application layer, the additional audio data, such as the sound of typing, can be run through a machine-learning algorithm to allow the lighting system to make a more informed decision about whether the lights should be on or off.

ML computing at the edge enables other intelligent industrial and home applications, including sensor-data processing for anomaly detection, predictive maintenance, audio pattern recognition for improved glass-break detection, simple-command word recognition, and vision use cases such as presence detection or people counting with low-resolution cameras.

More than 40 companies representing various industries and applications have already begun developing and testing this platform in a closed alpha programme.

Global retailers are looking to improve the in-store shopping experience with more accurate asset tracking, real-time price updating and other uses. Participants from the commercial building management sector are exploring how to make their building systems, including lighting and HVAC, more intelligent to lower owners’ costs and reduce their environmental footprint. Finally, consumer and smart home providers are working to make it easier to connect various devices and expand the way they interact to bring features and services to consumers.

The single-die BG24 and MG24 SoCs combine a 78MHz Arm Cortex-M33 processor, 2.4GHz radio, 20bit ADC, combination of flash up to 1536kbyte and RAM up to 256kbyte, and an AI and ML hardware accelerator for processing machine-learning algorithms while offloading the Cortex-M33, so applications have more cycles to do other work.

The SoCs in 5 by 5mm QFN40 and 6 by 6mm QFN48 packages are shipping today to alpha users and will be available for mass deployment in April 2022. Multiple evaluation boards are available to designers developing applications. Modules based on the SoCs will be available in the second half of 2022.