α-RACER: Real-Time Algorithm for Game-Theoretic
Motion Planning and Control in Autonomous Racing
using Near-Potential Function

Dvij Kalaria*, Chinmay Maheshwari*, Shankar Sastry
* Equal contribution
University of California, Berkeley
Learning for Dynamics & Control (L4DC) Conference 2025
Supplementary Paper Code Summary

Abstract

Autonomous racing extends beyond the challenge of controlling a racecar at its physical limits. Professional racers employ strategic maneuvers to outwit other competing opponents to secure victory. While modern control algorithms can achieve human-level performance by computing offline racing lines for single-car scenarios, research on real-time algorithms for multi-car autonomous racing is limited. To bridge this gap, we develop game-theoretic modeling framework that incorporates the competitive aspect of autonomous racing like overtaking and blocking through a novel policy parametrization, while operating the car at its limit. Furthermore, we propose an algorithmic approach to compute the (approximate) Nash equilibrium strategy, which represents the optimal approach in the presence of competing agents. Specifically, we introduce an algorithm inspired by recently introduced framework of dynamic near-potential function, enabling real-time computation of the Nash equilibrium. Our approach comprises two phases: offline and online. During the offline phase, we use simulated racing data to learn a near-potential function that approximates utility changes for agents. This function facilitates the online computation of approximate Nash equilibria by maximizing its value. We evaluate our method in a head-to-head 3-car racing scenario, demonstrating superior performance compared to several existing baselines.

Races with baselines rendered in Unity

Note: Unity game engine is only used for rendering here, physics engine of unity is not used here. The physics model followed by the vehicles is the same as described by Eqn (5) in supplementary. Sound effects and skid marks are added based on throttle commands and the slip angles at the tires calculated as per Appendix D

Races with baselines visualized in foxglove (Top-down view, 2X)

Note: The videos are recorded in foxglove studio. The transforms are published through ROS2 based on which foxglove renders a car object there separately. Because of this the car positions may not be completely synced as sometimes it may have take time for the 3d object to load. Hence, sometimes the positions in foxglove videos maybe inconsistent. Please refer to the Unity third person videos also provided for each race which should be synced and accurate.

Methodology

Numerical results

Effect of variation of policy parameters

BibTeX

@article{kalaria2025alpharace,
        title={α-RACER: Real-Time Algorithms for Game-Theoretic Motion Planning and Control in Autonomous Racing using Near-Potential Function},
        author={Kalaria, Dvij and Maheshwari, Chinmay and Sastry, Shankar},
        booktitle={7th Annual Learning for Dynamics & Control Conference (L4DC) 2025},
        year={2025},
        organization={IEEE}
      }