Deep Reinforcement Learning for Human-Like Driving Policies in Collision Avoidance Tasks of Self-Driving Cars
arXiv:2006.04218
Abstract
The technological and scientific challenges involved in the development of autonomous vehicles (AVs) are currently of primary interest for many automobile companies and research labs. However, human-controlled vehicles are likely to remain on the roads for several decades to come and may share with AVs the traffic environments of the future. In such mixed environments, AVs should deploy human-like driving policies and negotiation skills to enable smooth traffic flow. To generate automated human-like driving policies, we introduce a model-free, deep reinforcement learning approach to imitate an experienced human driver's behavior. We study a static obstacle avoidance task on a two-lane highway road in simulation (Unity). Our control algorithm receives a stochastic feedback signal from two sources: a model-driven part, encoding simple driving rules, such as lane-keeping and speed control, and a stochastic, data-driven part, incorporating human expert knowledge from driving data. To assess the similarity between machine and human driving, we model distributions of track position and speed as Gaussian processes. We demonstrate that our approach leads to human-like driving policies.
References in corpus (11)
- Continuous control with deep reinforcement learning
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- End to End Learning for Self-Driving Cars
- Prioritized Experience Replay
- A Survey of Deep Learning Techniques for Autonomous Driving
- DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills
- Deep Reinforcement Learning: An Overview
- On a Formal Model of Safe and Scalable Self-driving Cars
- MIT Advanced Vehicle Technology Study: Large-Scale Naturalistic Driving Study of Driver Behavior and Interaction with Automation
- Quantifying Generalization in Reinforcement Learning
- Simulated Car Racing Championship: Competition Software Manual