Sampling-Based Safety Filter with Probabilistic Restrictiveness Guarantee

TL;DR

This paper introduces a sampling-based safety filter for autonomous systems that guarantees safety with probabilistic restrictiveness, using control sequence sampling via SV-MPC to override unsafe nominal inputs.

Contribution

It presents a modular safety filter that leverages Stein Variational MPC to probabilistically ensure safety in complex, non-convex environments, with formal restrictiveness guarantees.

Findings

Successfully avoids collisions in cluttered environments.

Effectively overrides nominal control inputs when unsafe.

Demonstrates robustness in multi-vehicle scenarios.

Abstract

Ensuring safety is a critical requirement for autonomous systems, yet providing formal guarantees for nominal controllers remains a significant challenge. In this paper, we propose a modular sampling-based safety filter to ensure the safety of arbitrary nominal control inputs. At each timestep, the filter evaluates the safety of the nominal input by leveraging control sequence samples generated via Stein Variational Model Predictive Control (SV-MPC). This approach approximates a safety-conditioned posterior distribution over control sequences, enabling the filter to effectively capture multimodal safe regions in complex, non-convex environments. The filter guarantees safety by overriding the nominal input when all sampled control sequence candidates are deemed unsafe. By leveraging the scenario approach, the proposed method provides a probabilistic guarantee on its restrictiveness. We validate the filter through collision avoidance tasks in both single- and multi-vehicle settings, demonstrating its efficacy in navigating cluttered environments where nominal controllers may fail.