Imitating Driver Behavior with Generative Adversarial Networks

Abstract

The ability to accurately predict and simulate human driving behavior is critical for the development of intelligent transportation systems. Traditional modeling methods have employed simple parametric models and behavioral cloning. This paper adopts a method for overcoming the problem of cascading errors inherent in prior approaches, resulting in realistic behavior that is robust to trajectory perturbations. We extend Generative Adversarial Imitation Learning to the training of recurrent policies, and we demonstrate that our model outperforms rule-based controllers and maximum likelihood models in realistic highway simulations. Our model both reproduces emergent behavior of human drivers, such as lane change rate, while maintaining realistic control over long time horizons.

8 pages, 6 figures

References in corpus (9)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Congested Traffic States in Empirical Observations and Microscopic Simulations
• End to End Learning for Self-Driving Cars
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Benchmarking Deep Reinforcement Learning for Continuous Control
• Generative Adversarial Imitation Learning
• Memory-based control with recurrent neural networks
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
• Model-Free Imitation Learning with Policy Optimization

Cited by in corpus (3)

• InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
• Learning Temporal Strategic Relationships using Generative Adversarial Imitation Learning
• Selective Sampling and Mixture Models in Generative Adversarial Networks