Search papers, labs, and topics across Lattice.
This paper introduces a hybrid architecture that integrates game-theoretic reasoning into a sampling-based motion planner for autonomous racing, addressing the challenge of balancing vehicle dynamics with strategic decision-making in competitive environments. By employing an offline-learned potential function based on an $\alpha$-potential game formulation, the method captures multi-agent interactions and refines these interactions online through gradient-based optimization to create an Interaction Reference Path. Evaluation in a high-fidelity simulation shows that the approach effectively induces defensive behaviors such as blocking while maintaining computational efficiency, outperforming traditional full dynamic game solvers.
Game-theoretic guidance allows autonomous racers to effectively block opponents without the heavy computational load of traditional dynamic game solvers.
Autonomous racing demands planning algorithms that balance vehicle dynamics at the limits of handling with strategic decision-making in competitive multi-agent scenarios. Game theory provides a mathematical framework for modeling these interactions, enabling interactive trajectory planning and strategic behaviors, such as blocking. However, directly solving full dynamic games online is computationally prohibitive and challenging to integrate into robust, high-frequency autonomous software stacks. This paper proposes a hybrid architecture that integrates game-theoretic reasoning into a sampling-based motion planner, combining strategic interactions with robust trajectory generation. Building upon an $\alpha$-potential game formulation, we utilize an offline-learned potential function to capture multi-agent interactions. During online operation, a gradient-based optimization dynamically refines interaction parameters to generate an \textit{Interaction Reference Path}. This path serves as a dynamic cost bias within a high-frequency sampling planner. We evaluate our approach in a high-fidelity simulation environment on the Yas Marina Circuit. Qualitative and quantitative results demonstrate that our approach successfully induces defensive behaviors like blocking without carrying the computational burden of full dynamic game solvers.
