Interactive Decision Making for Autonomous Vehicles in Dense Traffic
This addresses safe navigation for autonomous vehicles in crowded urban environments, representing an incremental improvement by applying game theory to a specific bottleneck.
The paper tackles the problem of autonomous vehicle motion planning in dense traffic merges where gaps are smaller than the ego vehicle, proposing a game theoretic framework to generate and respond to interactive behaviors, with results including a computationally tractable game-tree decision making approach and a stochastic rule-based traffic agent for benchmarking.
Dense urban traffic environments can produce situations where accurate prediction and dynamic models are insufficient for successful autonomous vehicle motion planning. We investigate how an autonomous agent can safely negotiate with other traffic participants, enabling the agent to handle potential deadlocks. Specifically we consider merges where the gap between cars is smaller than the size of the ego vehicle. We propose a game theoretic framework capable of generating and responding to interactive behaviors. Our main contribution is to show how game-tree decision making can be executed by an autonomous vehicle, including approximations and reasoning that make the tree-search computationally tractable. Additionally, to test our model we develop a stochastic rule-based traffic agent capable of generating interactive behaviors that can be used as a benchmark for simulating traffic participants in a crowded merge setting.