Infineon's Innovative MCU Aims ML in IoT, Industrial

Infineon Technologies AG has released its new PSOC™ Edge family of microcontrollers (MCUs) optimized for machine learning (ML) applications. The three new PSOC Edge MCU series are E81, E83, and E84. Accordingly, they offer a scalable and compatible range of performance, features, and memory options.

The company’s comprehensive system design tools and software support the MCUs. Thus, enabling developers to quickly move from concept to product. For that reason, bringing new ML-enabled Internet of Thing (IoT), consumer, and industrial applications to market.

“Next-generation IoT edge devices continue to require more performance without compromising power,” said Steve Tateosian, SVP of Industrial MCUs, IoT, Wireless and Compute Business, Infineon.

In addition,Tateosian said Infineon’s new PSOC Edge E8 series of devices use ML capabilities to compute responsive AI. While at the same time balancing performance and power requirements and providing embedded security for connected home devices, wearables, and industrial applications.

“As a leading provider of MCUs, we are committed to delivering solutions that extend the capabilities of future IoT systems,” said Tateosian.

HMIs in Consumer, Industrial

Infineon’s new PSOC Edge E81, E83 and E84 microcontrollers’ strength lies on the high-performance Arm® Cortex®-M55, including Arm Helium™ DSP support paired with Arm Ethos™-U55. Moreover, they also integrate Cortex-M33 paired with Infineon’s ultra-low power NNLite — a proprietary hardware accelerator intended to accelerate neural networks.

In addition, all three series support extensive peripheral sets, on-chip memory, robust hardware security features, and a variety of connectivity options. This includes USB HS/FS with PHY CAN, Ethernet, WiFi ® 6, BTBLE, and Matter.

The PSOC Edge E81 utilizes the Arm Helium DSP technology along with Infineon NNLite Neural Network (NN) accelerator. Meanwhile, the PSOC Edge E83 and E84 include the Arm Ethos-U55 micro-NPU processor. This provides a 480x improvement in ML performance compared to existing Cortex-M systems. Furthermore, they support the Infineon NNlite neural network accelerator for ML applications in the low-power computing domain.

Target applications for the PSOC Edge E8x series include Human Machine Interface (HMI) in appliances and industrial devices. Moreover, they also suit smart home and security systems, robotics, and wearables applications. All three series support voice/audio sensing for activation and control, while the E83 and E84 MCUs deliver increased capabilities for advanced HMI implementations, including ML-based wake-up, and vision-based position detection and face/object recognition. The PSOC Edge E84 series adds low-power graphics display (up to 1028×768) to the extensive feature set.

System Design Enablement

PSOC Edge E8 MCUs offer designers a full family of system and full software compatible devices. Hardware design support includes an evaluation base board with Arduino expansion header, sensor suite, and BLE connectivity. At the same time, Wi-Fi for smart phone and cloud connectivity.

As with all Infineon MCUs, the series has the support of Infineon’s ModusToolbox™ software platform. Thus, having access to a collection of development tools, libraries, and embedded runtime assets. Thus, having a flexible and comprehensive development experience. ModusToolbox supports a wide range of use cases including consumer IoT, industrial, smart home, and wearables.

Imagimob Studio is an Edge AI development platform, integrated into ModusToolbox, that delivers end-to-end ML development capability, from data into model deployed. Starter projects and Imagimob’s Ready Models make it simple to get started. When used with PSOC Edge, Imagimob makes it possible to rapidly build and deploy state-of-the-art machine learning models for the edge.

-8 April 2024-