Last Updated: 16 December 2024
BrainChip, the first company to commercially produce ultra-low power, fully digital neuromorphic AI, announced a significant milestone today. Frontgrade Gaisler, a leading provider of radiation-hardened microprocessors for space applications, has licensed BrainChip’s Akida™ technology.
Through this partnership, they plan to integrate Akida™ into space-grade, fault-tolerant system-on-chip (SoC) solutions, enhancing AI performance for space missions.
This licensing agreement is a crucial step forward for deploying AI chips in space. Akida™ was chosen because it can process data streams in real-time with high resilience, autonomy, and accuracy, all while using minimal power, mass, and volume. These features are essential for space missions, where every gram and watt counts. By incorporating Akida™, Frontgrade Gaisler ensures that AI systems onboard spacecraft are both efficient and dependable.
The European Space Agency (ESA) has been leading efforts to bring neuromorphic computing to the forefront of AI applications in space.
"While many fields no doubt can benefit from neuromorphic computing, one essential area is computer vision applications where current FPGA or GPU technology does not bring satisfactory results for edge deployments when considering mass, volume and power constraints.”
Laurent Hili, a microelectronics and data handling engineer at ESA
ESA’s collaboration with Frontgrade Gaisler and BrainChip highlights the practical benefits of neuromorphic solutions, particularly in areas where traditional technologies fall short. This endorsement emphasizes the potential of Akida™ to redefine data processing in space.
BrainChip’s neuromorphic AI is set to significantly improve space-borne, on-board computers. The technology offers superior power efficiency and inference performance while maintaining compatibility with existing Convolutional Neural Networks (CNNs).
This means that spacecraft can handle more complex data processing tasks directly onboard, reducing the need to rely on ground-based systems. As a result, missions can achieve greater autonomy and efficiency, which is vital for long-duration space explorations.
“For the last 20 years, Gaisler’s space-grade microprocessors have been successfully deployed to every planet of our solar system in missions from ESA as well as most other space agencies.”
Sandi Habinc, General Manager at Frontgrade Gaisler
By licensing Akida™ IP, Frontgrade is enhancing its already impressive lineup of space-grade processors.
This strategic move ensures that future space missions will benefit from advanced AI capabilities, further solidifying Frontgrade’s role in the space industry.
Frontgrade Technologies is the premier provider of high-reliability and radiation-assured solutions for defense, space, intelligence, commercial, and civil applications. As a Frontgrade company, Frontgrade Gaisler specializes in radiation-hardened microprocessors and IP cores for critical applications, particularly in the space industry. The company’s products are designed to perform in the harshest environments, ensuring reliability, fault tolerance, and radiation resistance for any space mission or high-reliability application.
“This collaboration with Frontgrade Gaisler to license Akida IP for implementation into space SoCs represents an important step in satisfying the market demand for space-based AI deployments, turning into reality what once was considered unattainable.”
Sean Hehir, CEO of BrainChip
BrainChip is a global leader in Edge AI, specializing in on-chip processing and learning. Their flagship product, Akida™, mimics the human brain to efficiently analyze essential data directly from sensors. This technology allows AI to learn on the chip itself, eliminating the need for cloud processing. As a result, Akida™ reduces delays, enhances privacy, and improves data security. It can be integrated into any system-on-chip (SoC) technology, providing significant benefits for applications like connected cars, consumer electronics, and industrial IoT. BrainChip is proving that placing AI close to the sensor is the future of smart technology.
Source: Business Wire
