Contingency Constrained Planning with MPPI within MPPI

Leonard Jung, Alexander Estornell, Michael Everett
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:869-880, 2025.

Abstract

For safety, autonomous systems must be able to consider sudden changes and enact contingency plans appropriately. State-of-the-art methods currently find trajectories that balance between nominal and contingency behavior, or plan for a singular contingency plan; however, this does not guarantee that the resulting plan is safe for all time. To address this research gap, this paper presents Contingency-MPPI, a data-driven optimization-based strategy that embeds contingency planning inside a nominal planner. By learning to approximate the optimal contingency-constrained control sequence with adaptive importance sampling, the proposed method’s sampling efficiency is further improved with initializations from a lightweight path planner and trajectory optimizer. Finally, we present simulated and hardware experiments demonstrating our algorithm generating nominal and contingency plans in real time on a mobile robot.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-jung25a, title = {Contingency Constrained Planning with MPPI within MPPI}, author = {Jung, Leonard and Estornell, Alexander and Everett, Michael}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {869--880}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/jung25a/jung25a.pdf}, url = {https://proceedings.mlr.press/v283/jung25a.html}, abstract = {For safety, autonomous systems must be able to consider sudden changes and enact contingency plans appropriately. State-of-the-art methods currently find trajectories that balance between nominal and contingency behavior, or plan for a singular contingency plan; however, this does not guarantee that the resulting plan is safe for all time. To address this research gap, this paper presents Contingency-MPPI, a data-driven optimization-based strategy that embeds contingency planning inside a nominal planner. By learning to approximate the optimal contingency-constrained control sequence with adaptive importance sampling, the proposed method’s sampling efficiency is further improved with initializations from a lightweight path planner and trajectory optimizer. Finally, we present simulated and hardware experiments demonstrating our algorithm generating nominal and contingency plans in real time on a mobile robot.} }
Endnote
%0 Conference Paper %T Contingency Constrained Planning with MPPI within MPPI %A Leonard Jung %A Alexander Estornell %A Michael Everett %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-jung25a %I PMLR %P 869--880 %U https://proceedings.mlr.press/v283/jung25a.html %V 283 %X For safety, autonomous systems must be able to consider sudden changes and enact contingency plans appropriately. State-of-the-art methods currently find trajectories that balance between nominal and contingency behavior, or plan for a singular contingency plan; however, this does not guarantee that the resulting plan is safe for all time. To address this research gap, this paper presents Contingency-MPPI, a data-driven optimization-based strategy that embeds contingency planning inside a nominal planner. By learning to approximate the optimal contingency-constrained control sequence with adaptive importance sampling, the proposed method’s sampling efficiency is further improved with initializations from a lightweight path planner and trajectory optimizer. Finally, we present simulated and hardware experiments demonstrating our algorithm generating nominal and contingency plans in real time on a mobile robot.
APA
Jung, L., Estornell, A. & Everett, M.. (2025). Contingency Constrained Planning with MPPI within MPPI. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:869-880 Available from https://proceedings.mlr.press/v283/jung25a.html.

Related Material