BrainChip launches edge AI box ecosystem

BrainChip has launched an ecosystem of applications to run on its Akida neuromorphic chip and box reference design.

The software covers focussing on gestures, cybersecurity, image recognition and computer vision for manufacturing, warehouse, retail, hospitals, energy, automotive, and aviation.  These run on the Akida Edge AI box, an embedded Linux solution with Ethernet, Bluetooth, and USB interfaces to provide a complete edge AI computing platform based on two of Brainchip’s AKD1000 chips.

BrainChip developed the $1499 Akida Edge AI Box in partnership with manufacturer VVDN Technologies in Gurgaon, India and Fremont, California. VVDN produces the Brainchip Akida Edge AI Box Developer Kit and can develop custom versions of the product with OEMs for volume commercial applications.

“The Akida Edge Box is a great platform for running AI in standalone edge environments where footprint, cost and efficiency is critical, while not compromising performance,” said Sean Hehir, CEO of BrainChip. “We look forward to announcing more partners developing edge AI for their customers’ specific use cases and more importantly, we look forward to the ideas these companies will bring to life with the Akida Edge AI Box.”

BrianChip teamed with Edge Impulse, part of XX, for edge AI model training and development to build and deploy custom machine learning models directly on the Akida Edge AI box.

Gesture recognition algorithms have been developed by BeEmotion to enhance interaction, prevent accidents, and bring enjoyment to the everyday use of technology, while AI Labs is using the box for climate change monitoring.

Model evaluation to streamline the AI workflow comes from edge AI developer DeGirum, while cybersecurity comes from Quantum Ventura with the CyberNeuro-RT (CNRT) technology. Computer vision analysis comes from Vedya Labs.