Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a boundary sampling method using Pontryagin's Maximum Principle (PMP) to efficiently train safety filters for autonomous systems. By characterizing trajectories that narrowly avoid safety violations, the approach guides data collection for Hamilton-Jacobi Reachability, focusing learning on safety-critical states. Results on a shared-control automotive racing application show that PMP-guided sampling leads to faster convergence, lower failure rates, and better safe set reconstruction compared to naive sampling.
Barely avoiding disaster is the secret sauce: sampling trajectories near safety boundaries, guided by Pontryagin's Maximum Principle, dramatically improves the efficiency of learning safety filters.
Safety filters provide a practical approach for enforcing safety constraints in autonomous systems. While learning-based tools scale to high-dimensional systems, their performance depends on informative data that includes states likely to lead to constraint violation, which can be difficult to efficiently sample in complex, high-dimensional systems. In this work, we characterize trajectories that barely avoid safety violations using the Pontryagin Maximum Principle. These boundary trajectories are used to guide data collection for learned Hamilton-Jacobi Reachability, concentrating learning efforts near safety-critical states to improve efficiency. The learned Control Barrier Value Function is then used directly for safety filtering. Simulations and experimental validation on a shared-control automotive racing application demonstrate PMP sampling improves learning efficiency, yielding faster convergence, reduced failure rates, and improved safe set reconstruction, with wall times around 3ms.