PSOC™ Edge: The next generation of MCUs for Edge AI
Machine learning-enhanced sensing, low-power, secured, advanced HMI high-performance microcontroller family
PSOC™ Edge is designed for next generation responsive compute and control applications, featuring hardware-assisted machine learning (ML) acceleration. PSOC™ Edge provides hardware accelerated neural net compute support, delivering both "always-on" low power and high-performance operation, in a fully integrated microcontroller with right-sized peripherals, on-chip memories and state-of-the-art security.
The PSOC™ Edge devices are based on high performance Arm® Cortex®-M55, including Helium™ DSP support, paired with Arm® Ethos™-U55 and Cortex-M33 paired Infineon’s ultra-low power NNLite neural network accelerator for Machine Learning and AI applications.
The enhanced intelligence of the PSOC™ Edge series adds support for advanced graphics, audio- and vision-based applications to the extensive set of human interface modes (touch, graphics, voice) available in earlier generation PSOC™ devices. The new series enables easy migration of applications within the family, as well as an upgrade path for earlier generation designs.
Target use cases for PSOC™ Edge include
Robotics
- Vacuum Cleaner & Robots
- Service Robot
- Lawn & Garden Robotics
- Industrial Robotics
- Gesture Control
- Key Word Spotting
Security Camera
- IP Camera
- Doorbell
- Security Camera & Accessories
Smart Home
- Thermostat
- Speaker
- Door Lock
- Gesture Control
- Key Word Spotting
Human Machine Interface (HMI)
- Appliances
- Industrial Device Usability
- Factory Automation
- Gesture Control
- Key Word Spotting
Wearables
- Fitness Watch
- AR/MR/VR Glasses & Accessories
- Audio Accessories
- Key Word Spotting
Explore the offering
PSOC™ Edge E81, E82, E83, E84 microcontrollers
PSOC™ Edge Arm® Cortex® Multicore Subcategories
Featuring multi-domain architecture for high-performance and fine-grained power optimization, along with HMI interfaces and state-of the art security, the PSOC™ Edge E8x series of Arm® Cortex® multi-core MCUs comes in four unique variants designed with specific benefits in mind.
Key Features of all PSOC Edge E8x Devices
- High Performance Cortex-M55 CPU with Helium DSP
- Low-power Cortex-M33 with FPU, DSP and MPU and NNLite
- Memory
- Comprehensive Peripheral Support
- Advanced Integration
- Low Power
- Robust Security
State-of-the-Art-Security
- Lockstep secured enclave in low-power always-on domain
- Infineon Edge Protect Category 4
- Off-the-shelf Trusted Firmware-M enablement and Mbed-TLS for crypto operations
Enablement – Software and AI Ecosystem
ModusToolbox™ Software
Infineon's ModusToolbox™ is a collection of easy-to-use software and tools that enable rapid development of Infineon microcontrollers and AIROC™ Wi-Fi and Bluetooth® devices. It provides both development tools and run-time software for a flexible and comprehensive development experience. The ModusToolbox™ tools package includes desktop programs that enable the creation of new embedded applications, managing software components, configuring device peripherals and middleware, and embedded development tools for compiling, programming, and debugging. The ModusToolbox™ run-time software includes an extensive collection of GitHub-hosted repositories comprised of code examples, board support packages, middleware, and application support.
Zephyr® OS Supported Device
Zephyr is a small, yet scalable, full-featured OS with an architecture that allows developers to focus on applications requiring a real-time OS. It is flexible and customizable, and built with safety and security in mind.
PSOC™ Edge MCUs are supported in the Zephyr® OS Ecosystem through the following kit: KIT_PSE84_EVAL
Zephyr OS support is available on several Infineon platforms, based on code contributions from Infineon, our customers, and the Zephyr community.

DEEPCRAFT™
DEEPCRAFT™ Edge AI suite provides a comprehensive set of tools and software frameworks for developing intelligent edge devices with advanced AI capabilities. With DEEPCRAFT™, developers can simplify the development of Edge AI applications, improve performance, and reduce development time.
DEEPCRAFT™ Studio is an end-to-end solution for AI/machine learning model development and deployment at the edge. The platform is designed to support users in creating robust, high-quality models that are ready for deployment in commercial products.
DEEPCRAFT™ Model Converter lets users optimize proprietary as well as open-source models to run on Infineon hardware. The tool is compatible with many popular AI frameworks.
DEEPCRAFT™ Solutions:
- DEEPCRAFT™ Ready Models are fully tested, market-ready models optimized to work with Infineon's sensors and MCUs
- DEEPCRAFT™ Audio Enhancement enhances speech quality by removing unwanted noise, optimized for power-efficiency on Infineon’s PSOC™ Edge MCUs.
- DEEPCRAFT™ Voice Assistant enables natural voice interfaces to run locally on edge devices, optimized for power and performance on Infineon’s PSOC™ Edge MCUs.
- DEEPCRAFT™ AI Hub is Infineon’s one-stop-shop for Edge AI. Users can get inspiration from open-source models, Infineon software, tools & solutions, and case studies across industrial, consumer & automotive applications
Reference designs & evaluation boards
PSOC™ Edge E84 Evaluation Kit
For functional device for rapid prototyping and evaluation of the PSOC™ Edge E8x family of MCUs.
PSOC™ Edge E84 AI Kit
Evaluate AI capabilities of PSOC™ Edge using a low-cost kit featuring multiple sensors designed to support the creation of Edge AI-powered applications.
Rutronik System Solutions Demonstrator for AI control with radar-based gesture control
AI on the Edge: Radar-based gesture control powered by Infineon's PSOC™ Edge E84
Discover how Edge AI transforms real-world applications.
With sense and reason – and a deep understanding of the requirements in the development of innovative applications for relevant future markets. This is how the experts at Rutronik System Solutions are working on the further development of existing base and adapter boards, as well as their integration into application-oriented demonstrations. The latest example of this is an AI control system with gesture recognition using RAB3 radar and keyword recognition based on Infineon's PSOC™ Edge E84. This microcontroller enables decentralized calculation of neural networks “on the edge”, thus increasing the speed, stability and security of the developed system.
What’s inside the demo:
- Radar Vision: The RAB3 Adapter Board with Infineon’s XENSIV™ 60GHz radar sensor enables precise gesture detection — even through surfaces. Ideal for hygiene-critical or outdoor environments.
- Voice Intelligence: Always-on acoustic activity detection and keyword recognition using Infineon MEMS microphones allow intuitive voice control.
- Motor Control: An Infineon BLDC motor with Hall sensors responds to gestures and voice commands in real time.
- Visual Feedback: A 1024x600 IPS TFT LCD touch display provides a responsive user interface, powered by the PSOC™ Edge E84’s low-power graphics engine.
- Security Features: The demo leverages the PSOC™ Edge E84’s lockstep-secured enclave, Edge Protect Category 4, and hardware-accelerated ML for fast, secure, and reliable operation.
With the “eyes” of Rutronik System Solutions
The demo learns to see through the Rutronik Adapter Board RAB3 - Radar, which is plugged into the Evaluation Kit via the Arduino interface. It features the Infineon XENSIV™ 60GHz radar sensor, a discrete radar IC, and thus the latest radar technology. The advantages of radar sensors include the fact that they can be installed behind certain materials. This makes them invisible and makes it easier to clean the surfaces. This is particularly advantageous for environments with high hygiene requirements.
Furthermore, radar is ideal for outdoor applications because the technology works stably and reliably even in sunlight. The XENSIV™ also impresses with its small form factor and low power consumption. It has one transmitting and three receiving antennas. The L-shaped antenna enables array, horizontal and vertical angle measurements, thus allowing comprehensive radar scanning.
In addition, the Arm® Cortex®-M microcontrollers of the PSOC™ Edge E84 series offer high-performance, secured MCUs with low power consumption and hardware-supported ML acceleration. The PSOC™ Edge devices are based on the powerful Cortex-M55, including Helium DSP support in combination with Arm Ethos-U55, as well as a Cortex-M33 with Infineon's ultra-low-power NNLite hardware accelerator, which powers neural networks in machine learning and AI applications.