Stanford Car Can Learn How to Handle Unknown Driving Conditions

By David Cardinal

Autonomous vehicle safety has been grabbing some headlines recently, with Nvidia trumpeting its Safety Force Field (SFF) safety platform, and then being called out by Intel’s MobileEye unit for ripping the idea off by copying elements of its Responsibility-Sensitive Safety (RSS) system. The longer version of the story is that both of those frameworks, and others developed by researchers around the world, depend on vehicle control systems that can dependably execute driving maneuvers as needed.

However, most autonomous vehicle testing gets done on and assumes good weather and road conditions. To operate at the limits of performance under harsh conditions like wet or icy roads means that a great deal of additional sensor information needs to be incorporated into the AI systems in autonomous vehicles.

That’s where work by a team under Stanford Professor and CARS program Lab Director Chris Gerdes comes in. Gerdes’ group has long been at the forefront of autonomous vehicle dynamics, racking up some very impressive high-performance demo drives. In a paper just published in Science Robotics, whose lead author, CARS graduate student Nathan Spielberg focuses on developing ways autonomous vehicles can handle tricky situations safely, the group details how it has been able to implement a control system that can learn from its driving experiences and incorporate them into its future decision-making.

Read more at ExtremeTech