Risk-Based Safety Envelopes for Autonomous Vehicles Under Perception Uncertainty

TL;DR

This paper introduces a probabilistic safety envelope method for autonomous vehicles that accounts for perception uncertainty, enabling adjustable safety levels and improved safety assurance in uncertain environments.

Contribution

It extends existing safety envelopes like RSS to incorporate perception uncertainty through a probabilistic framework, providing a formal risk-based safety assessment method.

Findings

The approach effectively manages safety-performance trade-offs based on risk levels.

Simulation results demonstrate improved safety under perception uncertainty.

The method allows formal safety guarantees considering perception errors.

Abstract

Ensuring the safety of autonomous vehicles, given the uncertainty in sensing other road users, is an open problem. Moreover, separate safety specifications for perception and planning components raise how to assess the overall system safety. This work provides a probabilistic approach to calculate safety envelopes under perception uncertainty. The probabilistic envelope definition is based on a risk threshold. It limits the cumulative probability that the actual safety envelope in a fully observable environment is larger than an applied envelope and is solved using iterative worst-case analysis of envelopes. Our approach extends non-probabilistic envelopes - in this work, the Responsibility-Sensitive Safety (RSS) - to handle uncertainties. To evaluate our probabilistic envelope approach, we compare it in a simulated highway merging scenario against several baseline safety architectures. Our evaluation shows that our model allows adjusting safety and performance based on a chosen risk level and the amount of perception uncertainty. We conclude with an outline of how to formally argue safety under perception uncertainty using our formulation of envelope violation risk.