Infineon intros PSoC Edge MCUs

Infineon Technologies AG has released a new family of PSoC microcontrollers (MCUs) for power-efficient machine learning (ML) at the edge. The new PSoC Edge are Arm Cortex-based MCUs that enable next-generation responsive compute and control applications and feature hardware-assisted ML acceleration.

The PSoC Edge MCU family features ML-enhanced sensing, low power, secured and advanced HMI performance. Privacy and safety protection is provided through Infineon’s Edge Protect technologies. Applications include IoT and industrial segments such as smart home, security systems, wearables, robotics and HMI applications.

(Source: Infineon Technologies Inc.)

The new MCUs enable end products to be more intelligent and intuitively usable, lowering the barrier in human-machine interaction and adding contextual awareness to applications, Infineon said. The enhanced intelligence extends support for advanced graphics, voice, audio and vision-based applications to the existing PSoC portfolio. It also enables easy migration of applications within the family and an upgrade path from existing designs.

Offering scalable power and performance, extensive HMI capabilities and security, the PSoC MCUs are based on high performance Arm Cortex-M55, including Helium DSP support paired with Arm Ethos-U55 and Cortex-M33, combined with Infineon’s ultra-low-power NNLite hardware accelerator that accelerates neural networks used in ML and AI. The family provides on-chip memories, including non-volatile RRAM, and high speed, secured external memory support. It also enables software reuse and portability.

For development support, Infineon’s ModusToolbox software provides development tools, libraries and embedded runtime assets for a range of applications including industrial, smart home and wearables. Imagimob Studio AI solution, an edge AI development platform, is integrated into the ModusToolbox, providing end-to-end ML development. Starter projects and Imagimob’s Ready Models, with PSoC Edge, enable the deployment of ML models for the edge.

PSoC Edge is currently available for early access customers.