Reinforcement Learning with Probabilistic Guarantees for Autonomous Driving
This work addresses safety-critical challenges for autonomous vehicles, offering an incremental improvement by integrating formal methods into RL training.
The paper tackles the problem of ensuring reliable decision-making in autonomous urban driving by proposing a reinforcement learning approach with probabilistic guarantees, resulting in a policy that outperforms rule-based heuristics in efficiency while maintaining strong safety assurances.
Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the performance of the resulting policy. We propose a generic approach to enforce probabilistic guarantees on an RL agent. An exploration strategy is derived prior to training that constrains the agent to choose among actions that satisfy a desired probabilistic specification expressed with linear temporal logic (LTL). Reducing the search space to policies satisfying the LTL formula helps training and simplifies reward design. This paper outlines a case study of an intersection scenario involving multiple traffic participants. The resulting policy outperforms a rule-based heuristic approach in terms of efficiency while exhibiting strong guarantees on safety.