The potential applications span numerous industries. Smart cameras could autonomously monitor industrial processes, warehouses, or border areas. Mobile robots could make safe decisions even when operating alongside humans. The technology also addresses growing cybersecurity and privacy concerns, as processing data locally reduces the need to transmit sensitive information over networks.

Mika Laiho, Chief Technology Officer at Kovilta, emphasises the commercial potential: “A superior ability to observe the surroundings and accurately interpret observations is a must for robots and vehicles to operate independently and safely among people.” Kovilta plans to apply the accelerator architectures developed in MISEL to autonomous robotics and vehicle technology.

Applications spanning real-time sensory processing, robotics, and adaptive control represent the near-term opportunities for neuromorphic computing. The technology could prove particularly valuable in healthcare, where neuromorphic systems are being explored for diagnostics, prosthetics, and personalised medicine.

As the project nears completion, the next step involves leveraging these results in new projects and VTT’s pilot production lines. “In the future, these results can be used in autonomous devices that see, think, and act as independently and energy-efficiently as a fruit fly,” Flak concludes.

The breakthrough comes at a crucial time, as the demand for artificial intelligence at the edge continues to grow whilst concerns about energy consumption and environmental impact intensify. Neuromorphic systems’ efficiency could reduce carbon footprints by cutting energy demands compared to traditional GPU-based processing, aligning with global decarbonisation targets.

The MISEL project demonstrates how inspiration from biology, combined with cutting-edge engineering, can address some of technology’s most pressing challenges—creating devices that are simultaneously more intelligent, more efficient, and more independent than ever before.