Combining Reinforcement Learning with Model Predictive Control for On-Ramp Merging
arXiv:2011.08484
Abstract
We consider the problem of designing an algorithm to allow a car to autonomously merge on to a highway from an on-ramp. Two broad classes of techniques have been proposed to solve motion planning problems in autonomous driving: Model Predictive Control (MPC) and Reinforcement Learning (RL). In this paper, we first establish the strengths and weaknesses of state-of-the-art MPC and RL-based techniques through simulations. We show that the performance of the RL agent is worse than that of the MPC solution from the perspective of safety and robustness to out-of-distribution traffic patterns, i.e., traffic patterns which were not seen by the RL agent during training. On the other hand, the performance of the RL agent is better than that of the MPC solution when it comes to efficiency and passenger comfort. We subsequently present an algorithm which blends the model-free RL agent with the MPC solution and show that it provides better trade-offs between all metrics -- passenger comfort, efficiency, crash rate and robustness.
arXiv comment8 pages, 6 figures
References in corpus (10)
- Continuous control with deep reinforcement learning
- Playing Atari with Deep Reinforcement Learning
- Congested Traffic States in Empirical Observations and Microscopic Simulations
- Safe Reinforcement Learning Using Robust MPC
- Baidu Apollo EM Motion Planner
- Data-Efficient Reinforcement Learning with Probabilistic Model Predictive Control
- Combining Deep Reinforcement Learning and Safety Based Control for Autonomous Driving
- Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic
- Autonomous Ramp Merge Maneuver Based on Reinforcement Learning with Continuous Action Space
- Anti-Jerk On-Ramp Merging Using Deep Reinforcement Learning