Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles

Alec Farid, Sushant Veer, Boris Ivanovic, Karen Leung, Marco Pavone
Proceedings of The 6th Conference on Robot Learning, PMLR 205:1959-1969, 2023.

Abstract

In modern autonomy stacks, prediction modules are paramount to planning motions in the presence of other mobile agents. However, failures in prediction modules can mislead the downstream planner into making unsafe decisions. Indeed, the high uncertainty inherent to the task of trajectory forecasting ensures that such mispredictions occur frequently. Motivated by the need to improve safety of autonomous vehicles without compromising on their performance, we develop a probabilistic run-time monitor that detects when a "harmful" prediction failure occurs, i.e., a task-relevant failure detector. We achieve this by propagating trajectory prediction errors to the planning cost to reason about their impact on the AV. Furthermore, our detector comes equipped with performance measures on the false-positive and the false-negative rate and allows for data-free calibration. In our experiments we compared our detector with various others and found that our detector has the highest area under the receiver operator characteristic curve.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-farid23a, title = {Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles}, author = {Farid, Alec and Veer, Sushant and Ivanovic, Boris and Leung, Karen and Pavone, Marco}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {1959--1969}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/farid23a/farid23a.pdf}, url = {https://proceedings.mlr.press/v205/farid23a.html}, abstract = {In modern autonomy stacks, prediction modules are paramount to planning motions in the presence of other mobile agents. However, failures in prediction modules can mislead the downstream planner into making unsafe decisions. Indeed, the high uncertainty inherent to the task of trajectory forecasting ensures that such mispredictions occur frequently. Motivated by the need to improve safety of autonomous vehicles without compromising on their performance, we develop a probabilistic run-time monitor that detects when a "harmful" prediction failure occurs, i.e., a task-relevant failure detector. We achieve this by propagating trajectory prediction errors to the planning cost to reason about their impact on the AV. Furthermore, our detector comes equipped with performance measures on the false-positive and the false-negative rate and allows for data-free calibration. In our experiments we compared our detector with various others and found that our detector has the highest area under the receiver operator characteristic curve.} }
Endnote
%0 Conference Paper %T Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles %A Alec Farid %A Sushant Veer %A Boris Ivanovic %A Karen Leung %A Marco Pavone %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-farid23a %I PMLR %P 1959--1969 %U https://proceedings.mlr.press/v205/farid23a.html %V 205 %X In modern autonomy stacks, prediction modules are paramount to planning motions in the presence of other mobile agents. However, failures in prediction modules can mislead the downstream planner into making unsafe decisions. Indeed, the high uncertainty inherent to the task of trajectory forecasting ensures that such mispredictions occur frequently. Motivated by the need to improve safety of autonomous vehicles without compromising on their performance, we develop a probabilistic run-time monitor that detects when a "harmful" prediction failure occurs, i.e., a task-relevant failure detector. We achieve this by propagating trajectory prediction errors to the planning cost to reason about their impact on the AV. Furthermore, our detector comes equipped with performance measures on the false-positive and the false-negative rate and allows for data-free calibration. In our experiments we compared our detector with various others and found that our detector has the highest area under the receiver operator characteristic curve.
APA
Farid, A., Veer, S., Ivanovic, B., Leung, K. & Pavone, M.. (2023). Task-Relevant Failure Detection for Trajectory Predictors in Autonomous Vehicles. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:1959-1969 Available from https://proceedings.mlr.press/v205/farid23a.html.

Related Material