BrainChip Demonstrates Ultra-Low-Power Edge AI At Embedded World North America
2 companies named across 2 categories, one of 3 articles referencing BrainChip. Previous coverage: ABI Research Forecasts Edge AIoT Chipset Market to More Than Triple by 2031 (Sep 2026).
Best suited for
- Seniority
- EVP / SVP / VP / AVP
- Job function
- Chief Technology Officer
- Buyer role
- Decision Maker / Budget Holder
- Buyer journey
- Need to Buy
- Adoption curve
- Early Majority
- Technology maturity
- Operational Expansion
- Industry
- Information Technology / Software & Services / IT Services / Internet Services & Infrastructure
Our classification, not the publisher's statement. Best suited for, not only for.
BrainChip Holdings Ltd. demonstrated three battery-powered edge AI applications at Embedded World North America 2026, including radar classification, human presence detection, and fall detection. The company said the demonstrations show on-device real-time processing for these use cases.
The work was presented through live demonstrations at BrainChip’s booth #6623. BrainChip said it used reference platforms to illustrate a path from proof of concept to deployable products, with each application running entirely on the device in real time.
Radar classification used a Raspberry Pi 5 with an integrated AKD1500 M.2 card and an automotive radar front end to perform micro-Doppler classification in real time. Human presence detection ran on a BrainBoard1500, NICLA-compatible development platform from Neuromorphyx to perform on-device person presence detection by processing sensor data locally. Fall detection used an AkidaTag module from SpanIdea with a Nordic wireless MCU and the AKD1500S chip, performing on-device fall detection for health monitoring and wearable applications.
Steve Brightfield, chief product officer at BrainChip, said, “These aren't lab bench demos — they are battery-powered, field-deployable proofs of concept that developers can retrain with their own data,” and added, “That is the critical step between a lab demo and a product on the market. At Embedded World North America, visitors can see all three applications running in the palm of their hands.” BrainChip also described three hardware platforms for the demonstrations: production AKD1500 M.2 cards, the BrainBoard1500 NICLA development board, and the AkidaTag standalone smart sensor integrating an MCU, an AKD1500 chip, and a companion mobile application. BrainChip said the fall detection module is available for pre-order, and documentation and repositories are publicly available on the BrainChip Developer Hub.
Press release, provided by Globe Newswire on behalf of BrainChip. Read the original.