BrainChip Demonstrates Ultra-Low-Power Edge AI At Embedded World North America
BrainChip uses live, battery-powered demos to highlight on-device, ultra-low-power edge AI capabilities for mobile, industrial and wearable applications.
Rhea-AI Summary
BrainChip Holdings (BCHPY) is demonstrating three battery-powered, on-device edge AI applications at Embedded World North America 2026 in Anaheim, showing radar classification, human presence detection and fall detection running in real time at booth #6623.
Each demo runs on three hardware platforms: AKD1500 M.2 production cards, the BrainBoard1500 NICLA-compatible development board, and the AkidaTag smart sensor, which integrates an MCU, an AKD1500 chip and a companion mobile app. The showcased systems highlight ultra-low-power, on-device inference for mobile, industrial and wearable uses, aligning with growing demand for cloud-independent edge AI silicon.
Positive
- None.
Negative
- None.
Key Figures
- Demonstrated applications
- 3 applications
- Radar classification, human presence detection and fall detection
- Hardware platforms
- 3 platforms
- AKD1500 M.2 cards, BrainBoard1500 and AkidaTag
- Edge AI chipset market
- $34.4 billion
- 2026 market estimate
- Edge AI chipset market
- $96 billion
- 2031 market estimate
- Unit shipments
- 711 million
- 2026 market estimate
- Unit shipments
- 1.59 billion
- 2031 market estimate
Previous AI Reports
-
AKD1500 M.2 module became available for fanless industrial edge AI upgrades
-
Radar platform added on-device Micro-Doppler classification to traditional radar systems
-
AKD1500 launched with 800 GOPS under 300 mW for battery-powered devices
24h Move is the share-price change in the day after each event; other market factors may also have contributed.
Key Terms
micro-doppler technical
m.2 technical
AI-generated analysis. How Rhea-AI works. Not financial advice.
Live demonstrations of radar classification, human presence detection and fall detection showcase innovation at the edge
ANAHEIM, Calif., Sept. 15, 2026 (GLOBE NEWSWIRE) -- At Embedded World North America 2026, BrainChip Holdings Ltd. (ASX: BRN, OTCQX: BRCHF, ADR: BCHPY), a global leader in ultra-low-power, fully digital, event-based neuromorphic AI, is demonstrating three battery-powered edge AI applications — radar classification, human presence detection and fall detection — running entirely on device in real time at booth #6623.
The live demonstrations use BrainChip’s reference platforms to show how low-power, edge AI applications can move from proof of concept toward deployable products.
Each demonstration runs on three hardware platforms: production AKD1500 M.2 cards; the BrainBoard1500 NICLA development board; and the award-winning AkidaTag, a standalone smart sensor integrating an MCU, an AKD1500 chip and a companion mobile application.
"These aren't lab bench demos — they are battery-powered, field-deployable proofs of concept that developers can retrain with their own data," said Steve Brightfield, chief product officer at BrainChip. "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."
The demonstrations at the BrainChip booth include:
- Radar Classification — A Raspberry Pi 5 with an integrated AKD1500 M.2 card and automotive radar front end performs micro-Doppler classification in real time. Traditional radar can detect an object’s presence; this demonstration also classifies the object by analyzing its micro-Doppler signature.
- Fall Detection — An AkidaTag module from SpanIdea integrates a Nordic wireless MCU and the AKD1500S chip in a device that fits in the palm of your hand. It performs real-time, battery-powered fall detection on device for health monitoring and wearable applications. The module is available for pre-order, with documentation and repositories publicly available on the BrainChip Developer Hub.
- Human Detection — A BrainBoard1500, NICLA-compatible development platform from Neuromorphyx performs real-time, person presence detection entirely on device. By processing sensor data and making inference decisions locally, the system eliminates the need to transmit video streams while maintaining responsiveness and data privacy.
The Backdrop For BrainChip’s Market Momentum
These demonstrations show how BrainChip delivers edge AI intelligence with ultra-low SWaP-C (Size, Weight, Power and Cost) products developers can plug into, run inference on and deploy across mobile, industrial and wearable markets.
That matters for the broader edge AI market, as it moves the category from bench demos to hardware developers can buy, build and deploy in the power- and size-constrained environments where conventional AI silicon can't go.
BrainChip’s momentum also comes as privacy regulations, latency requirements and battery budgets continue to migrate inference away from the cloud and onto the device. It also comes as cloud-independent AI execution is moving from a differentiator to a procurement requirement in defense, industrial and medical sectors.
More broadly, the increase in edge devices, such as industrial sensors, cameras, robots and wearables, is fueling demand for edge AI silicon. ABI Research's 2Q 2026 market update estimates the edge AI chipset market at
About BrainChip Holdings Ltd.
BrainChip is the worldwide leader in edge AI on-chip processing and learning. The company’s first-to-market, fully digital, event-based AI processor, Akida™, uses neuromorphic principles to analyze only essential sensor inputs at the point of acquisition, processing data with unmatched efficiency, precision and energy economy. BrainChip’s technology is deployed across industries including aerospace, defense, industrial IoT, healthcare, consumer devices, and wearables. Explore more at www.brainchip.com.
Follow BrainChip:
X: https://www.twitter.com/BrainChip_inc
LinkedIn: https://www.linkedin.com/company/7792006
Investor Contact
IR@brainchip.com
BrainChip Media Contact
Maddie Coe
FAQ
AI-generated questions and answers. How Rhea-AI works. Not financial advice.
What specific applications is BrainChip demonstrating at Embedded World North America 2026?
BrainChip is demonstrating three edge AI applications running entirely on device in real time: radar classification using micro-Doppler signatures, fall detection for health monitoring and wearables, and human presence detection that performs person presence inference locally without transmitting video streams.
Which hardware platforms are used for the BrainChip edge AI demonstrations?
The demonstrations run on three platforms: AKD1500 M.2 production cards, the BrainBoard1500 NICLA-compatible development board from Neuromorphyx, and the AkidaTag standalone smart sensor, which combines an MCU, an AKD1500 chip and a mobile application.
Where can interested parties see these demos at the event?
The live, battery-powered demonstrations are being shown at Embedded World North America 2026 in Anaheim, California, at BrainChip’s booth #6623.