Stefan Mileschin

Getting the parts cost down with a neural net

Intel and Accenture announced they are supporting an Intel Neuromorphic Research Community (INRC) project to develop a wheelchair-mounted robotic arm to assist pediatric patients with spinal injuries.

The project is led by the Neuro-Biomorphic Engineering Lab at the Open University of Israel in partnership with ALYN Hospital. The device will be clinically evaluated and tested with children at the Hospital, which is Israel’s most advanced adolescent rehabilitation center.

While such devices exist today, the cost is incredibly high, making them virtually inaccessible to most people who need them. This is largely due to the expensive parts needed to enable the arm to adapt to the user and the environment in real time.

Researchers from Accenture Labs and Intel Labs are working with researchers at Open University of Israel to build a neural network model and apply it to Intel’s neuromorphic computing hardware.

Intel’s neuromorphic research chip, Loihi, shows potential to reduce the cost of creating and operating such devices. By using Loihi’s real-time learning, researchers predict they can implement adaptive control to enhance the arm’s functionality, while using affordable parts that could reduce the cost by more than 10x. Loihi’s power efficiency also shows promise for making adaptive assistive robotics more useful and effective in real-world situations.

https://fudzilla.com/news/51383-inte...ot-arm-project