A project that combines robotics and light-based computer circuits to create safe self-driving vehicles has been selected for funding through Princeton’s Eric and Wendy Schmidt Transformative Technology Fund.

Led by Paul Prucnal, professor of electrical and computer engineering, and Jaime Fernández Fisac, assistant professor of electrical and computer engineering, this project is one of two Schmidt-funded projects this year, according to a recent announcement.

This project aims to enhance the safety and reliability of autonomous vehicles and robots using processors known as neuromorphic photonic chips, which work in a manner analogous to neurons and perform computations using light, or photons, rather than electrons.

By combining the photonic chips developed by Prucnal with robotic systems developed by Fisac, the researchers aim to build autonomous systems that can rapidly evaluate safety-critical situations, such as a bicycle veering into the vehicle’s path, and choose the correct response, such as swerving to avoid a collision.

Compared to ordinary electronic processors, the neuromorphic photonic chips process information far more quickly, and can evaluate thousands of potential scenarios in real time, allowing the robot to choose the best contingency plan to avoid an accident. The approach will improve the safety of self-driving cars, delivery robots, and other autonomous systems whose safe operation may hinge on split-second decisions.