FuzzRisk: Online Collision Risk Estimation for Autonomous Vehicles based on Depth-Aware Object Detection via Fuzzy Inference
This work addresses safety monitoring for autonomous vehicles, offering an incremental improvement by integrating depth-aware detection with existing methods.
The paper tackles the problem of estimating collision risk for autonomous vehicles by monitoring inconsistencies between two object detection methods, using fuzzy inference to map these inconsistencies to a risk indicator. They validated their approach on the nuScenes dataset and in simulations, showing it can safeguard vehicles effectively.
This paper presents a novel monitoring framework that infers the level of collision risk for autonomous vehicles (AVs) based on their object detection performance. The framework takes two sets of predictions from different algorithms and associates their inconsistencies with the collision risk via fuzzy inference. The first set of predictions is obtained by retrieving safety-critical 2.5D objects from a depth map, and the second set comes from the ordinary AV's 3D object detector. We experimentally validate that, based on Intersection-over-Union (IoU) and a depth discrepancy measure, the inconsistencies between the two sets of predictions strongly correlate to the error of the 3D object detector against ground truths. This correlation allows us to construct a fuzzy inference system and map the inconsistency measures to an AV collision risk indicator. In particular, we optimize the fuzzy inference system towards an existing offline metric that matches AV collision rates well. Lastly, we validate our monitor's capability to produce relevant risk estimates with the large-scale nuScenes dataset and demonstrate that it can safeguard an AV in closed-loop simulations.