Safe Perception -- A Hierarchical Monitor Approach

TL;DR

This paper introduces a hierarchical monitoring approach for AI perception systems in autonomous vehicles, aiming to ensure safety by detecting detection misses with low false alarms amidst diverse environmental conditions.

Contribution

It proposes a novel hierarchical monitor that validates perception outputs, reliably detects misses, and maintains a low false alarm rate, addressing safety validation challenges in autonomous driving.

Findings

Effective detection of perception misses in diverse conditions

Low false alarm rate achieved by the hierarchical monitor

Enhanced safety validation for autonomous vehicle perception systems

Abstract

Our transportation world is rapidly transforming induced by an ever increasing level of autonomy. However, to obtain license of fully automated vehicles for widespread public use, it is necessary to assure safety of the entire system, which is still a challenge. This holds in particular for AI-based perception systems that have to handle a diversity of environmental conditions and road users, and at the same time should robustly detect all safety relevant objects (i.e no detection misses should occur). Yet, limited training and validation data make a proof of fault-free operation hardly achievable, as the perception system might be exposed to new, yet unknown objects or conditions on public roads. Hence, new safety approaches for AI-based perception systems are required. For this reason we propose in this paper a novel hierarchical monitoring approach that is able to validate the object list from a primary perception system, can reliably detect detection misses, and at the same time has a very low false alarm rate.