Refining Obstacle Perception Safety Zones via Maneuver-Based Decomposition

TL;DR

This paper introduces a maneuver-based decomposition method to refine safety zones in autonomous driving, significantly reducing zone size while maintaining safety guarantees by leveraging ego maneuver information.

Contribution

It proposes a novel maneuver-based approach using temporal convolution to produce smaller, more precise safety zones for autonomous vehicles.

Findings

Zones reduced by up to 76% in size

Maintains safety completeness despite reduction

Numerical experiments validate effectiveness

Abstract

A critical task for developing safe autonomous driving stacks is to determine whether an obstacle is safety-critical, i.e., poses an imminent threat to the autonomous vehicle. Our previous work showed that Hamilton Jacobi reachability theory can be applied to compute interaction-dynamics-aware perception safety zones that better inform an ego vehicle's perception module which obstacles are considered safety-critical. For completeness, these zones are typically larger than absolutely necessary, forcing the perception module to pay attention to a larger collection of objects for the sake of conservatism. As an improvement, we propose a maneuver-based decomposition of our safety zones that leverages information about the ego maneuver to reduce the zone volume. In particular, we propose a "temporal convolution" operation that produces safety zones for specific ego maneuvers, thus limiting the ego's behavior to reduce the size of the safety zones. We show with numerical experiments that maneuver-based zones are significantly smaller (up to 76% size reduction) than the baseline while maintaining completeness.