Robust Spatiotemporal Motion Planning for Multi-Agent Autonomous Racing via Topological Gap Identification and Accelerated MPC

2026-03-10

AI Summary

This work addresses the significant challenge of achieving robust spatiotemporal planning, respecting dynamic constraints, and enabling efficient collision avoidance in high-speed multi-agent autonomous racing. The authors propose a dynamic occupancy corridor framework that integrates topological gap identification with opponent behavior prediction, coupled with a customized pseudo-transient continuation (PTC)-accelerated linear time-varying model predictive control (LTV-MPC) to generate high-frequency, dynamically feasible overtaking maneuvers and trajectories. This approach represents the first integration of topological gap selection with PTC-accelerated LTV-MPC. Evaluated on the F1TENTH platform, it demonstrates substantial performance gains: a 51.6% reduction in total maneuver time in sequential scenarios, an overtaking success rate exceeding 81% in dense bottleneck situations, and a 20.3% decrease in average computational latency.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

High-speed multi-agent autonomous racing demands robust spatiotemporal planning and precise control under strict computational limits. Current methods often oversimplify interactions or abandon strict kinematic constraints. We resolve this by proposing a Topological Gap Identification and Accelerated MPC framework. By predicting opponent behaviors via SGPs, our method constructs dynamic occupancy corridors to robustly select optimal overtaking gaps. We ensure strict kinematic feasibility using a Linear Time-Varying MPC powered by a customized Pseudo-Transient Continuation (PTC) solver for high-frequency execution. Experimental results on the F1TENTH platform show that our method significantly outperforms state-of-the-art baselines: it reduces total maneuver time by 51.6% in sequential scenarios, consistently maintains an overtaking success rate exceeding 81% in dense bottlenecks, and lowers average computational latency by 20.3%, pushing the boundaries of safe and high-speed autonomous racing.

Problem

• multi-agent autonomous racing
• spatiotemporal motion planning
• kinematic constraints
• computational efficiency
• robust planning

Innovation

• Topological Gap Identification
• Accelerated MPC
• Sparse Gaussian Processes
• Pseudo-Transient Continuation
• Multi-Agent Autonomous Racing