Search papers, labs, and topics across Lattice.
This paper introduces Sampling-based Game-Theoretic Planning (SGTP), a novel framework designed for real-time planning in multi-vehicle autonomous racing that effectively balances strategic diversity and computational efficiency. By leveraging GPU-accelerated sampling of control sequences and incorporating game-theoretic reasoning, SGTP ranks sampled trajectories using a game-aware cost, ensuring diverse and competitive racing behaviors while adhering to safety constraints. The method achieves impressive performance metrics, including a 95.24% win rate and a 99.35% task-completion ratio across challenging racing scenarios, demonstrating its effectiveness in high-stakes environments with multiple agents.
Achieving a 95.24% win rate in multi-vehicle racing, SGTP redefines real-time planning by integrating game-theoretic principles with GPU-accelerated sampling.
Autonomous multi-vehicle racing requires real-time planning of diverse competitive behaviors in intense interactions. Existing planners often struggle to balance strategic diversity and computational efficiency. To address this challenge, we propose Sampling-based Game-Theoretic Planning (SGTP), a real-time framework that combines game-theoretic reasoning with GPU-accelerated sampling of control sequences and dynamics rollouts. Sampled trajectories are ranked using a game-aware cost to capture competitive interactions and generate diverse racing behaviors. Our planner then performs feasibility selection by explicitly enforcing track-boundary and dynamic collision-avoidance constraints, ensuring safe and reliable transitions between racing strategies. Extensive simulations on challenging tracks show that SGTP achieves a 95.24% win rate and a 99.35% task-completion ratio in highly interactive races, with a mean computational time of 0.095 s over multiple iterative solving steps. We also demonstrate the successful application of SGTP in large-scale scenarios with up to 10 agents. We release our code and provide an open-source benchmark of multi-agent autonomous racing algorithms to facilitate future research. Project page: https://sgtp-racing.github.io/.
