Learning to Obey Traffic Rules using Constrained Policy Optimization

When planning motions for autonomous vehicles, traffic rules must be obeyed to ensure safety and reject liability claims. However, present solutions do not scale well with the complexity of traffic rules or even consider them. To solve this problem, we propose a scalable approach based on constrained policy optimization to improve traffic rule compliance of motion planners for autonomous vehicles. Our approach encodes traffic rules as constraints of the optimization problem and does not require an explicit model of the environment. We evaluate our approach using the highway dataset highD and show that agents trained using our method can effectively learn to reach a goal region while following traffic rules.