ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst
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.
Code (4)
Tasks
Autonomous DrivingImitation LearningSimilar Papers 제목 키워드 기반
Learning to Drive by Observing the Best and Synthesizing the Worst
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, ev…
Autonomous DrivingImitation LearningSpeech Synthesis with Mixed Emotions
Emotional speech synthesis aims to synthesize human voices with various emotional effects. The current studies are mostly focused on imitating an averaged style belonging to a specific emotion type. In this paper, we see…
AttributeEmotional Speech SynthesisSpeech Synthesistext-to-speech+1A data-driven approach to beating SAA out-of-sample
While solutions of Distributionally Robust Optimization (DRO) problems can sometimes have a higher out-of-sample expected reward than the Sample Average Approximation (SAA), there is no guarantee. In this paper, we intro…
Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control
Recent progress on physics-based character animation has shown impressive breakthroughs on human motion synthesis, through imitating motion capture data via deep reinforcement learning. However, results have mostly been …
Deep Reinforcement LearningHierarchical Reinforcement Learningmotion predictionMotion Synthesis+3Simultaneous Policy Learning and Latent State Inference for Imitating Driver Behavior
In this work, we propose a method for learning driver models that account for variables that cannot be observed directly. When trained on a synthetic dataset, our models are able to learn encodings for vehicle trajectori…