MIT engineers have invented a new photorealistic simulation engine to help driveless cars navigate a host of worse-case scenarios before cruising down real streets.
According to its creators, the new simulation system could help vehicles learn how to drive in the real world and recover from near-crash scenarios.
Control systems for autonomous vehicles largely rely on real-world datasets of driving trajectories from human drivers.
From these data, they learn how to emulate safe steering controls in a variety of situations.
But real-world data from hazardous ‘edge cases’ – such as nearly crashing or being forced off the road or into other lanes – are fortunately rare.
MIT is hoping to change that with its Virtual Image Synthesis and Transformation for Autonomy (VISTA) system.
The system uses only a small dataset – captured by humans driving on a road – to synthesize a practically infinite number of new viewpoints from trajectories that the vehicle could take in the real world.
The controller is rewarded for the distance it travels without crashing, so it must learn by itself how to reach a destination safely.
In doing so, the vehicle learns to safely navigate any situation it encounters, including regaining control after swerving between lanes or recovering from near-crashes.
In tests, a controller trained within the VISTA simulator safely was able to be safely deployed onto a full-scale driverless car and to navigate through previously unseen streets.
In positioning the car at off-road orientations that mimicked various near-crash situations, the controller was also able to successfully recover the car back into a safe driving trajectory within a few seconds.
“It’s tough to collect data in these edge cases that humans don’t experience on the road,” says first author and MIT CSAIL PhD student Alexander Amini.
“In our simulation, however, control systems can experience those situations, learn for themselves to recover from them, and remain robust when deployed onto vehicles in the real world.”
Going forward, the scientists are hoping to simulate all types of road conditions from a single driving trajectory, such as night and day, and sunny and rainy weather.
Image and content: MIT News