Even though virtual testing of Autonomous Vehicles (AVs) has been well recognized as essential for safety assessment, AV simulators are still undergoing active development. One particularly challenging question is to effectively include the Sensing and Perception (S&P) subsystem into the simulation loop. In this article, we define Perception Error Models (PEM), a virtual simulation component that can enable the analysis of the impact of perception errors on AV safety, without the need to model the sensors themselves. We propose a generalized data-driven procedure towards parametric modeling and evaluate it using Apollo, an open-source driving software, and nuScenes, a public AV dataset. Additionally, we implement PEMs in SVL, an open-source vehicle simulator. Furthermore, we demonstrate the usefulness of PEM-based virtual tests, by evaluating camera, LiDAR, and camera-LiDAR setups. Our virtual tests highlight limitations in the current evaluation metrics, and the proposed approach can help study the impact of perception errors on AV safety.
@article{arxiv.2302.11919,
title = {PEM: Perception Error Model for Virtual Testing of Autonomous Vehicles},
author = {Andrea Piazzoni and Jim Cherian and Justin Dauwels and Lap-Pui Chau},
journal= {arXiv preprint arXiv:2302.11919},
year = {2024}
}
Comments
12 pages, 10 figures. This is a preprint, and version 2 only updates the title and the reference to the final published article, which can be found at DOI: 10.1109/TITS.2023.3311633