ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
This addresses robustness challenges in autonomous driving for real-world deployment, representing a significant but incremental improvement over existing imitation learning approaches.
The authors tackled the problem of training robust autonomous driving policies via imitation learning, finding that standard behavior cloning with 30 million examples was insufficient for complex scenarios. They proposed ChauffeurNet, which augments imitation learning with synthesized perturbations and additional loss functions, and demonstrated the model driving a real car.
Our goal is to train a policy for autonomous driving via imitation learning that is robust enough to drive a real vehicle. We find that standard behavior cloning is insufficient for handling complex driving scenarios, even when we leverage a perception system for preprocessing the input and a controller for executing the output on the car: 30 million examples are still not enough. We propose exposing the learner to synthesized data in the form of perturbations to the expert's driving, which creates interesting situations such as collisions and/or going off the road. Rather than purely imitating all data, we augment the imitation loss with additional losses that penalize undesirable events and encourage progress -- the perturbations then provide an important signal for these losses and lead to robustness of the learned model. We show that the ChauffeurNet model can handle complex situations in simulation, and present ablation experiments that emphasize the importance of each of our proposed changes and show that the model is responding to the appropriate causal factors. Finally, we demonstrate the model driving a car in the real world.