Search papers, labs, and topics across Lattice.
This paper introduces a novel framework combining Topological Gap Identification and Accelerated Model Predictive Control (MPC) for robust spatiotemporal motion planning in multi-agent autonomous racing. The approach predicts opponent behaviors using Stochastic Gaussian Processes (SGPs) to construct dynamic occupancy corridors for optimal overtaking gap selection. A Linear Time-Varying MPC, accelerated by a customized Pseudo-Transient Continuation (PTC) solver, ensures strict kinematic feasibility and high-frequency execution, leading to significant performance gains in maneuver time, overtaking success rate, and computational latency compared to state-of-the-art baselines on the F1TENTH platform.
Autonomous racecars can now overtake rivals 51% faster and with 81% success by predicting their moves and planning dynamically feasible trajectories.
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.
