Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation

Jay Sarva, Jingkang Wang, James Tu, Yuwen Xiong, Sivabalan Manivasagam, Raquel Urtasun
Proceedings of The 7th Conference on Robot Learning, PMLR 229:1316-1334, 2023.

Abstract

Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate how the SDV interacts on a corpus of synthetic and real scenarios and to verify good performance. However, they primarily only test the motion planning module of the system, and only consider behavior variations. It is key to evaluate the full autonomy system in closed-loop, and to understand how variations in sensor data based on scene appearance, such as the shape of actors, affect system performance. In this paper, we propose a framework, Adv3D, that takes real world scenarios and performs closed-loop sensor simulation to evaluate autonomy performance, and finds vehicle shapes that make the scenario more challenging, resulting in autonomy failures and uncomfortable SDV maneuvers. Unlike prior work that add contrived adversarial shapes to vehicle roof-tops or roadside to harm perception performance, we optimize a low-dimensional shape representation to modify the vehicle shape itself in a realistic manner to degrade full autonomy performance (e.g., perception, prediction, motion planning). Moreover, we find that the shape variations found with Adv3D optimized in closed-loop are much more effective than open-loop, demonstrating the importance of finding and testing scene appearance variations that affect full autonomy performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-sarva23a, title = {Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation}, author = {Sarva, Jay and Wang, Jingkang and Tu, James and Xiong, Yuwen and Manivasagam, Sivabalan and Urtasun, Raquel}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {1316--1334}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/sarva23a/sarva23a.pdf}, url = {https://proceedings.mlr.press/v229/sarva23a.html}, abstract = {Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate how the SDV interacts on a corpus of synthetic and real scenarios and to verify good performance. However, they primarily only test the motion planning module of the system, and only consider behavior variations. It is key to evaluate the full autonomy system in closed-loop, and to understand how variations in sensor data based on scene appearance, such as the shape of actors, affect system performance. In this paper, we propose a framework, Adv3D, that takes real world scenarios and performs closed-loop sensor simulation to evaluate autonomy performance, and finds vehicle shapes that make the scenario more challenging, resulting in autonomy failures and uncomfortable SDV maneuvers. Unlike prior work that add contrived adversarial shapes to vehicle roof-tops or roadside to harm perception performance, we optimize a low-dimensional shape representation to modify the vehicle shape itself in a realistic manner to degrade full autonomy performance (e.g., perception, prediction, motion planning). Moreover, we find that the shape variations found with Adv3D optimized in closed-loop are much more effective than open-loop, demonstrating the importance of finding and testing scene appearance variations that affect full autonomy performance.} }
Endnote
%0 Conference Paper %T Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation %A Jay Sarva %A Jingkang Wang %A James Tu %A Yuwen Xiong %A Sivabalan Manivasagam %A Raquel Urtasun %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-sarva23a %I PMLR %P 1316--1334 %U https://proceedings.mlr.press/v229/sarva23a.html %V 229 %X Self-driving vehicles (SDVs) must be rigorously tested on a wide range of scenarios to ensure safe deployment. The industry typically relies on closed-loop simulation to evaluate how the SDV interacts on a corpus of synthetic and real scenarios and to verify good performance. However, they primarily only test the motion planning module of the system, and only consider behavior variations. It is key to evaluate the full autonomy system in closed-loop, and to understand how variations in sensor data based on scene appearance, such as the shape of actors, affect system performance. In this paper, we propose a framework, Adv3D, that takes real world scenarios and performs closed-loop sensor simulation to evaluate autonomy performance, and finds vehicle shapes that make the scenario more challenging, resulting in autonomy failures and uncomfortable SDV maneuvers. Unlike prior work that add contrived adversarial shapes to vehicle roof-tops or roadside to harm perception performance, we optimize a low-dimensional shape representation to modify the vehicle shape itself in a realistic manner to degrade full autonomy performance (e.g., perception, prediction, motion planning). Moreover, we find that the shape variations found with Adv3D optimized in closed-loop are much more effective than open-loop, demonstrating the importance of finding and testing scene appearance variations that affect full autonomy performance.
APA
Sarva, J., Wang, J., Tu, J., Xiong, Y., Manivasagam, S. & Urtasun, R.. (2023). Adv3D: Generating Safety-Critical 3D Objects through Closed-Loop Simulation. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:1316-1334 Available from https://proceedings.mlr.press/v229/sarva23a.html.

Related Material