Safe Planning with Game-Theoretic Formulation, Reachability Analysis and Reinforcement Learning

When autonomous vehicles (AVs) share the road with human drivers, the complexity of the interaction significantly increases. Both the AV and the human-driven car need to infer the behaviors of other road users to make their own decisions. In this paper, we study a scenario in which human-driven cars attempt to block AVs while the AVs aim to overtake human-driven cars. This setting plans for the worst-case scenario in which other agents are adversarial. Previous works have developed theoretical frameworks that enable robots to find an optimal and safe trajectory in an adversarial setting. In this paper, we explore three of these frameworks: Hamilton-Jacobi reachability, game-theoretic approaches, and reinforcement learning. We then construct the corresponding overtaken controllers and compare their performances. The robot needs to consider both collision avoidance and task realization. Therefore, the way it infers human behavior is crucial. Our results suggest that game-theoretic methods are able to find optimized and safe trajectories more successfully and faster than other approaches.