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

Dvij Kalaria, Chinmay Maheshwari, Shankar Sastry
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:959-972, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-kalaria25a, title = {$α$-RACER: Real-Time Algorithm for Game-Theoretic Motion Planning and Control in Autonomous Racing using Near-Potential Function}, author = {Kalaria, Dvij and Maheshwari, Chinmay and Sastry, Shankar}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {959--972}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/kalaria25a/kalaria25a.pdf}, url = {https://proceedings.mlr.press/v283/kalaria25a.html}, 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.} }
Endnote
%0 Conference Paper %T $α$-RACER: Real-Time Algorithm for Game-Theoretic Motion Planning and Control in Autonomous Racing using Near-Potential Function %A Dvij Kalaria %A Chinmay Maheshwari %A Shankar Sastry %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-kalaria25a %I PMLR %P 959--972 %U https://proceedings.mlr.press/v283/kalaria25a.html %V 283 %X 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.
APA
Kalaria, D., Maheshwari, C. & Sastry, S.. (2025). $α$-RACER: Real-Time Algorithm for Game-Theoretic Motion Planning and Control in Autonomous Racing using Near-Potential Function. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:959-972 Available from https://proceedings.mlr.press/v283/kalaria25a.html.

Related Material