Formulation and validation of a car-following model based on deep reinforcement learning

Abstract

We propose and validate a novel car following model based on deep reinforcement learning. Our model is trained to maximize externally given reward functions for the free and car-following regimes rather than reproducing existing follower trajectories. The parameters of these reward functions such as desired speed, time gap, or accelerations resemble that of traditional models such as the Intelligent Driver Model (IDM) and allow for explicitly implementing different driving styles. Moreover, they partially lift the black-box nature of conventional neural network models. The model is trained on leading speed profiles governed by a truncated Ornstein-Uhlenbeck process reflecting a realistic leader's kinematics. This allows for arbitrary driving situations and an infinite supply of training data. For various parameterizations of the reward functions, and for a wide variety of artificial and real leader data, the model turned out to be unconditionally string stable, comfortable, and crash-free. String stability has been tested with a platoon of five followers following an artificial and a real leading trajectory. A cross-comparison with the IDM calibrated to the goodness-of-fit of the relative gaps showed a higher reward compared to the traditional model and a better goodness-of-fit.

References in corpus (10)

• Continuous control with deep reinforcement learning
• Congested Traffic States in Empirical Observations and Microscopic Simulations
• Addressing Function Approximation Error in Actor-Critic Methods
• Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving
• Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control
• Modular Multitask Reinforcement Learning with Policy Sketches
• Comparing Numerical Integration Schemes for Time-Continuous Car-Following Models
• Autonomous Ramp Merge Maneuver Based on Reinforcement Learning with Continuous Action Space
• Anti-Jerk On-Ramp Merging Using Deep Reinforcement Learning
• Dampen the Stop-and-Go Traffic with Connected and Automated Vehicles -- A Deep Reinforcement Learning Approach

Cited by in corpus (3)

• Modified DDPG car-following model with a real-world human driving experience with CARLA simulator
• Calibrating Car-Following Models via Bayesian Dynamic Regression
• The Application of Driver Models in the Safety Assessment of Autonomous Vehicles: A Survey