Massachusetts Institute of Technology (MIT) has developed a new simulation system to help train autonomous vehicles before testing on public roads.
Control systems, or “controllers,” 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.
MIT said real-world data from hazardous “edge cases,” such as nearly crashing or being forced off the road or into other lanes, are — fortunately — rare.
Some computer programs, called “simulation engines,” aim to imitate these situations by rendering detailed virtual roads to help train the controllers to recover.
But the learned control from simulation has never been shown to transfer to reality on a full-scale vehicle.
The MIT researchers tackle the problem with their photorealistic simulator, called Virtual Image Synthesis and Transformation for Autonomy (VISTA).
It 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.
After successfully driving 10,000 kilometers in simulation, the researchers apply the learned controller onto their full-scale autonomous vehicle in the real world. The researchers say this is the first time a controller trained using end-to-end reinforcement learning in simulation has successfully been deployed onto a full-scale autonomous car.
A paper describing the system has been published in IEEE Robotics and Automation Letters and is due to be presented at the upcoming International Conference on Robotics and Automation (ICRA) conference in May.
“It’s tough to collect data in these edge cases that humans don’t experience on the road,” says first author Alexander Amini, a PhD student in the Computer Science and Artificial Intelligence Laboratory (CSAIL).
“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.”
Next, the researchers hope to simulate all types of road conditions from a single driving trajectory, such as night and day, and sunny and rainy weather. They also hope to simulate more complex interactions with other vehicles on the road.
VIDEO: MIT Autonomous Vehicle: Learning Robust Sim-to-Real Control Policies