Search papers, labs, and topics across Lattice.
This paper introduces a hierarchical framework for safe overtaking in autonomous racing that decouples maneuver-level decision-making from safety-certified trajectory control. By employing a Mixed-Integer Quadratic Program (MIQP) for overtaking topology selection and a nonlinear MPC with adaptive Control Barrier Functions (CBFs), the approach reduces conservatism and enhances performance across varying track conditions. Experimental results demonstrate that the adaptive CBF strategy significantly improves success rates and safety-performance trade-offs compared to traditional fixed-decay methods, achieving robust operation without the need for manual tuning.
Adaptive safety margins in autonomous racing can boost overtaking success rates by over 20% while maintaining stringent safety standards.
Autonomous racing overtaking requires balancing competitive performance with safety under nonlinear vehicle dynamics and real-time constraints. Model Predictive Control (MPC) combined with Control Barrier Functions (CBFs) provides a principled mechanism for certifying forward invariance of a safe set. However, commonly used fixed-decay discrete-time CBF formulations can become overly conservative in interactive racing scenarios, limiting overtaking performance and requiring manual tuning across track conditions. This paper proposes a hierarchical overtaking framework that explicitly separates maneuver-level decision making from safety-certified trajectory control, reducing conservatism while preserving safety. A high-level Mixed-Integer Quadratic Program (MIQP) resolves the combinatorial passing-side selection problem by selecting a feasible overtaking topology, while a nonlinear Frenet-frame MPC enforces vehicle dynamics and safety through embedded discrete-time CBF constraints. This decomposition isolates the combinatorial complexity of maneuver selection from the continuous trajectory optimization. To further mitigate the sensitivity of fixed-decay barrier constraints, a reinforcement learning policy adapts the discrete-time CBF decay parameter online, enabling context-dependent modulation of safety margins without directly controlling vehicle inputs. Simulation and scaled-hardware experiments show that no single fixed decay parameter achieves uniformly strong performance across tracks, whereas the adaptive strategy attains the highest aggregate success rate and consistently strong safety--performance trade-offs without per-track tuning, improving robustness to environment variation while maintaining safety constraint satisfaction in nominal operation.
