SGTP: Sampling-based Game-Theoretic Planning for Real-Time Multi-Vehicle Autonomous Racing

Hugging Face Daily Papers Papers
autonomous-racing game-theoretic-planning sampling-based multi-vehicle real-time gpu-acceleration

Summary

SGTP is a real-time sampling-based game-theoretic planning framework for multi-vehicle autonomous racing, achieving 95.24% win rate and 99.35% task completion with low computational time. The authors release code and an open-source benchmark.

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/.
Original Article
View Cached Full Text

Cached at: 08/03/26, 09:31 AM

Paper page - SGTP: Sampling-based Game-Theoretic Planning for Real-Time Multi-Vehicle Autonomous Racing

Source: https://huggingface.co/papers/2607.25388

Abstract

Autonomousmulti-vehicleracingrequiresreal-timeplanningofdiversecompetitivebehaviorsinintenseinteractions.Existingplannersoftenstruggletobalancestrategicdiversityandcomputationalefficiency.Toaddressthischallenge,weproposeSampling-basedGame-TheoreticPlanning(SGTP),areal-timeframeworkthatcombinesgame-theoreticreasoningwithGPU-acceleratedsamplingofcontrolsequencesanddynamicsrollouts.Sampledtrajectoriesarerankedusingagame-awarecosttocapturecompetitiveinteractionsandgeneratediverseracingbehaviors.Ourplannerthenperformsfeasibilityselectionbyexplicitlyenforcingtrack-boundaryanddynamiccollision-avoidanceconstraints,ensuringsafeandreliabletransitionsbetweenracingstrategies.ExtensivesimulationsonchallengingtracksshowthatSGTPachievesa95.24%winrateanda99.35%task-completionratioinhighlyinteractiveraces,withameancomputationaltimeof0.095sovermultipleiterativesolvingsteps.WealsodemonstratethesuccessfulapplicationofSGTPinlarge-scalescenarioswithupto10agents.Wereleaseourcodeandprovideanopen-sourcebenchmarkofmulti-agentautonomousracingalgorithmstofacilitatefutureresearch.Projectpage:https://sgtp-racing.github.io/.

View arXiv pageView PDFProject pageGitHubAdd to collection

Get this paper in your agent:

hf papers read 2607\.25388

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.25388 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.25388 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.25388 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

GTA: Generating Long-Horizon Tasks for Web Agents at Scale

arXiv cs.AI

This paper introduces GTA, a scalable framework for automatically generating long-horizon, multi-hop web agent tasks with executable trajectories, addressing the lack of process-level supervision in web agent benchmarks. The framework integrates crawling, retrieval-based seeding, and automated quality control to produce realistic tasks across multiple websites.

Threat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement Learning

arXiv cs.AI

This paper proposes Threat-guided Policy-aware Scene Perturbation (TPSP), a method that augments online reinforcement learning for safe autonomous driving by perturbing scenes in a policy-aware, targeted manner to generate high-value safety-critical experiences. Experiments on NAVSIM v2 show improved safety learning efficiency with about 4 million kilometers of simulated driving data.