Edge deploys Edge AI models to Arm microcontrollers tools

8th March 2024

Edge Impulse

Sheryl Miles

0 0

Edge Impulse, the platform for building, refining, and deploying machine learning models and algorithms to Edge devices, has launched a direct integration with Arm Keil MDK that provides easy access to cutting-edge AI and machine learning models and makes it simpler and faster for embedded engineers to collaborate with other cross-disciplinary teams to build edge AI products and bring them to market.

Keil MDK is an embedded development solution with more than 300,000 embedded developers worldwide using this tool suite to develop firmware for industrial, IoT, and wearable products. Collaborating across disciplines to create and deploy Edge AI firmware – from data science to ML development to embedded engineering – enables developing an ML pipeline that can perform well within the given hardware constraints. The new Edge Impulse integration brings its universe of powerful edge AI tooling directly to the Keil ecosystem via native Common Microcontroller Software Interface Standard (CMSIS) Pack support, bridging the gap between embedded and ML engineers in order to:

Improve time-to-market by enabling embedded engineers and ML teams to work together seamlessly to significantly shortcut the development and validation of edge AI products.

Easily integrate state-of-the-art Edge Impulse AI and ML models optimised for edge devices into embedded firmware.

Take full advantage of the combination of the latest Arm Compiler with Edge Impulse’s EON Compiler to reduce the memory footprint and improve code performance.

Remove hardware lock-in by leveraging edge AI support for the broad range of over 10,000 Arm-based MCUs that are supported by CMSIS.

“ML and AI functionality are becoming more widely adopted for edge use cases, and embedded developers need tools to navigate these complexities,” said Reinhard Keil, Senior Director of Embedded Technology at Arm. “Keil MDK is the most trusted and widely deployed embedded development environment in the ecosystem. Integrating Edge Impulse’s edge AI tools within it brings additional capabilities to a vast community of developers enabling them to build sophisticated edge AI firmware faster than ever on Arm.”

"Serving embedded engineers with new tools that help them get started with AI and ML projects quickly is an important priority to us, and working with Arm to support Keil Studio enables us to impact one of the largest communities in edge development," said Jan Jongboom, Co-Founder and CTO at Edge Impulse. "It's our hope this partnership will lead to greater utilisation of AI to improve the critical firmware powering industrial, IoT, and wearable environments."

Edge Impulse's native CMSIS Pack for Keil MDK is available.