LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty

Mohamad Hosein Danesh, Panpan Cai, David Hsu
Proceedings of The 6th Conference on Robot Learning, PMLR 205:199-211, 2023.

Abstract

Uncertainty in human behaviors poses a significant challenge to autonomous driving in crowded urban environments. The partially observable Markov decision process (POMDP) offers a principled general framework for decision making under uncertainty and achieves real-time performance for complex tasks by leveraging Monte Carlo sampling. However, sampling may miss rare, but critical events, leading to potential safety concerns. To tackle this challenge, we propose a new algorithm, LEarning Attention over Driving bEhavioRs (LEADER), which learns to attend to critical human behaviors during planning. LEADER learns a neural network generator to provide attention over human behaviors; it integrates the attention into a belief-space planner through importance sampling, which biases planning towards critical events. To train the attention generator, we form a minimax game between the generator and the planner. By solving this minimax game, LEADER learns to perform risk-aware planning without explicit human effort on data labeling.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-danesh23a, title = {LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty}, author = {Danesh, Mohamad Hosein and Cai, Panpan and Hsu, David}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {199--211}, 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/danesh23a/danesh23a.pdf}, url = {https://proceedings.mlr.press/v205/danesh23a.html}, abstract = {Uncertainty in human behaviors poses a significant challenge to autonomous driving in crowded urban environments. The partially observable Markov decision process (POMDP) offers a principled general framework for decision making under uncertainty and achieves real-time performance for complex tasks by leveraging Monte Carlo sampling. However, sampling may miss rare, but critical events, leading to potential safety concerns. To tackle this challenge, we propose a new algorithm, LEarning Attention over Driving bEhavioRs (LEADER), which learns to attend to critical human behaviors during planning. LEADER learns a neural network generator to provide attention over human behaviors; it integrates the attention into a belief-space planner through importance sampling, which biases planning towards critical events. To train the attention generator, we form a minimax game between the generator and the planner. By solving this minimax game, LEADER learns to perform risk-aware planning without explicit human effort on data labeling.} }
Endnote
%0 Conference Paper %T LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty %A Mohamad Hosein Danesh %A Panpan Cai %A David Hsu %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-danesh23a %I PMLR %P 199--211 %U https://proceedings.mlr.press/v205/danesh23a.html %V 205 %X Uncertainty in human behaviors poses a significant challenge to autonomous driving in crowded urban environments. The partially observable Markov decision process (POMDP) offers a principled general framework for decision making under uncertainty and achieves real-time performance for complex tasks by leveraging Monte Carlo sampling. However, sampling may miss rare, but critical events, leading to potential safety concerns. To tackle this challenge, we propose a new algorithm, LEarning Attention over Driving bEhavioRs (LEADER), which learns to attend to critical human behaviors during planning. LEADER learns a neural network generator to provide attention over human behaviors; it integrates the attention into a belief-space planner through importance sampling, which biases planning towards critical events. To train the attention generator, we form a minimax game between the generator and the planner. By solving this minimax game, LEADER learns to perform risk-aware planning without explicit human effort on data labeling.
APA
Danesh, M.H., Cai, P. & Hsu, D.. (2023). LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:199-211 Available from https://proceedings.mlr.press/v205/danesh23a.html.

Related Material