embedded award 2023: Artificial intelligence nominees

A shower monitoring sensor, versal adaptive SoCs and a shared network

AI IR shower monitoring sensor wireless module

Exhibitor: AITAD GmbH c/o Silicon Labs
Hall/Booth: 4A/4A-128-129

Bathroom faucets in domestic and public areas have great potential for water saving, but also for comfort and user safety, which have been identified and solved as follows: In the domestic area, one can pay attention to person size or movement patterns, so that one makes corresponding flow and control speeds intelligent, individual and adaptive through the control system.

For elderly people in wheelchairs, it must be recognized that in the event of another caregiver in the shower zone, the shower will stop or not start till he is leaving. In public areas with several showers arranged in a room, on the other hand, it is only important whether a person is standing under the shower faucet or not, so that the showers are switched off for the purpose of sustainability when not in use. In this way, prescribed hygienic heat rinses can also be carried out automatically without people under the faucet.

In any case, the more precise, low-fluctuation and situational control is possible, since body points can be focused on and evaluated at the detected persons, in order to be able to regulate body temperature appropriately. This means that depending on the situation (e.g. chilled person after jogging outdoors or person from sauna with heated body) other control temperature curves are automatically selected for the purpose of comfort feeling.

Until now, all this was neither cheap nor wireless and privacy-compliant (i.e. not camera-based) feasible.

What is unusual about this product is its size, price, and self-sufficient conductivity. Fully-local embedded AI solutions like this in size and capability have only been around for a few years. Note that both the data stream from the sensor, the preprocessing, the machine learning recognition model itself, the scoring and evaluation of the results, and the wireless transmission all happen in real time in milliseconds on the module.

This is enabled by the unique AITADs embedded AI process with proprietary conversion algorithms to the AI/ML acceleration unit of Silicon Labs' EFR32MG24 SoC/MCU (with an Cortex-M33 core). The module can be connected directly via LIN and comparable data buses or wirelessly via the 2.4GHz RF unit integrated in the EFR32MG24. The 2.4GHz wireless solution with integrated chip antenna (f.i. ZigBee, Matter) allows any battery-powered (low-power) remote mounting on walls, ceilings or in fittings. Another special feature is the absence of a camera and the use of a low-resolution IR grid sensor, thus addressing privacy concerns in the shower.

Depending on the use case, the solution is scalable in terms of resolution, starting at 8x8 or 16x16 pixels up to three-digit pixel numbers. The same applies to the sensor field of view, consisting of ROI distance and angle. The overall ML-flexibility of the module for comfort and sustainability in public areas, for comfort and individual programs in private shower areas as well as for disabled persons is amazing.

Versal AI Edge Series

Exhibitor: AMD

Hall/Booth: 2/2-411

Today’s advanced applications for industrial automation, smart cities, automotive safety, and healthcare require intelligence at the edge to make real-time decisions. The need to continuously improve performance to meet increasing demands without compromising in other areas is a challenge for customers.

AMD’s Versal AI Edge Series is a strategic product group within its unique adaptive computing portfolio, which enables customers to embed intelligence into a broad array of applications from cloud to edge thanks to its unparalleled performance, adaptability, and ease of use.

The FPGA-based adaptive platform enables AI-powered, high-performance computing that dramatically improves productivity as complexity increases. With 4X the AI performance-per-watt versus GPUs and 10X greater compute density versus previous-generation adaptive SoCs, the Versal AI Edge series is the world’s most scalable and adaptable portfolio for next-generation sensor systems.
Whether customers need to support robotics, machine vision, or IoT applications in industry; medical AI and surgical robotics applications in healthcare; or ADAS, software-defined cockpit, and infotainment applications in automotive.

The Versal AI Edge series is uniquely designed to enable AI innovation from the edge to the endpoint. Versal adaptive SoCs are fully software-programmable, with performance and flexibility that far exceed that of competing CPUs and GPUs for automotive applications. It features AMD’s second generation of AI Engines, boasting 2x compute density for AI inference workloads, hardware sparsity support, and an enhanced memory architecture for enabling greater compute efficiency across the array.

The series allows developers to rapidly evolve their sensor fusion and AI algorithms while leveraging the world’s most scalable device portfolio for diverse performance and power profiles from edge to endpoint. AI-enabled automated systems require high compute density that can accelerate whole applications from sensor to AI to real-time control.

The Versal AI Edge series was developed for the highest AI performance/watt in power- and thermally constrained systems spanning automotive, robotics, healthcare, and aerospace applications. Accessible to both hardware and software developers, Versal AI Edge adaptive SoCs provide a design-entry point for any developer, including Vivado design tools for hardware developers, the Vitis unified software platform for software developers, Vitis AI for data scientists, and domain-specific operating systems, frameworks, and acceleration libraries for the platform’s target applications.

According to Dan Mandell, senior analyst, IoT and Embedded Technology at VDC Research, “The market opportunity at the edge is growing exponentially and AI chipsets that serve these unique applications are expected to more than double from 2021 to 2025. By creating a design for AI-specific tasks that focuses on performance acceleration while remaining scalable and with low power, the AMD Xilinx Versal AI Edge series is a compelling solution to address these critical markets.” AMD is still in the early days of this product – but have begun shipping early samples to lead customers in the automotive sector.

AWS IoT Core for Amazon Sidewalk

Exhibitor: AWS

Hall/Booth: 4/4-550

Due to the high connectivity cost, power consumption, or limited range and coverage of existing networks, innovation of IoT solutions from developers has historically been limited, which has resulted in narrow availability for end users. While cellular companies have wide network coverage, the higher cost of this coverage reduces the feasibility of many use cases.

Other technologies (e.g. LoRaWAN) that offer low-cost and high-power solutions don’t provide the necessary network coverage or security. Similarly, technologies like WiFi, BLE, Thread, ZigBee, and Z-Wave are well-established smart home solutions, but fall short due to limited range when connectivity is required beyond the home.

Today, IoT devices drop off the internet at astonishingly high rates and frequently never get reconnected, which in turn drives reliability and performance issues for IoT products in the field.

Amazon Sidewalk is a shared network that helps devices like the Amazon Echo, Ring security cameras, and motion sensors work better at home and beyond the front door. When enabled, the network can support other Sidewalk devices in your community, and can be used for applications such as sensing your environment and alerting you when there's a water leak.

Amazon Sidewalk provides redundant coverage for many devices on the network. Therefore, when a Sidewalk device becomes disconnected from one gateway, it can re-establish connectivity by automatically connecting to another available gateway; no intervention is required of end-user. The typical range for many Amazon Sidewalk bridges is one half mile/one kilometer. AWS IoT Core for Amazon Sidewalk provides cloud services that you can use to connect the Sidewalk devices to the AWS Cloud and use other AWS services.

With AWS IoT Core for Amazon Sidewalk, you can build intelligent applications that are capable of increasing the efficiencies across all types of facilities. Sidewalk-enabled sensors can be deployed across buildings, cities, or other types of infrastructure to monitor and control smart systems. With instant connect capabilities, these Sidewalk-enabled devices can simply ‘power-on’ and immediately begin sending data to the cloud. No complex app setup or on-boarding flow required.