Parting with Misconceptions about Learning-based Vehicle Motion Planning

Daniel Dauner, Marcel Hallgarten, Andreas Geiger, Kashyap Chitta
Proceedings of The 7th Conference on Robot Learning, PMLR 229:1268-1281, 2023.

Abstract

The release of nuPlan marks a new era in vehicle motion planning research, offering the first large-scale real-world dataset and evaluation schemes requiring both precise short-term planning and long-horizon ego-forecasting. Existing systems struggle to simultaneously meet both requirements. Indeed, we find that these tasks are fundamentally misaligned and should be addressed independently. We further assess the current state of closed-loop planning in the field, revealing the limitations of learning-based methods in complex real-world scenarios and the value of simple rule-based priors such as centerline selection through lane graph search algorithms. More surprisingly, for the open-loop sub-task, we observe that the best results are achieved when using only this centerline as scene context (i.e., ignoring all information regarding the map and other agents). Combining these insights, we propose an extremely simple and efficient planner which outperforms an extensive set of competitors, winning the nuPlan planning challenge 2023.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-dauner23a, title = {Parting with Misconceptions about Learning-based Vehicle Motion Planning}, author = {Dauner, Daniel and Hallgarten, Marcel and Geiger, Andreas and Chitta, Kashyap}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {1268--1281}, 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/dauner23a/dauner23a.pdf}, url = {https://proceedings.mlr.press/v229/dauner23a.html}, abstract = {The release of nuPlan marks a new era in vehicle motion planning research, offering the first large-scale real-world dataset and evaluation schemes requiring both precise short-term planning and long-horizon ego-forecasting. Existing systems struggle to simultaneously meet both requirements. Indeed, we find that these tasks are fundamentally misaligned and should be addressed independently. We further assess the current state of closed-loop planning in the field, revealing the limitations of learning-based methods in complex real-world scenarios and the value of simple rule-based priors such as centerline selection through lane graph search algorithms. More surprisingly, for the open-loop sub-task, we observe that the best results are achieved when using only this centerline as scene context (i.e., ignoring all information regarding the map and other agents). Combining these insights, we propose an extremely simple and efficient planner which outperforms an extensive set of competitors, winning the nuPlan planning challenge 2023.} }
Endnote
%0 Conference Paper %T Parting with Misconceptions about Learning-based Vehicle Motion Planning %A Daniel Dauner %A Marcel Hallgarten %A Andreas Geiger %A Kashyap Chitta %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-dauner23a %I PMLR %P 1268--1281 %U https://proceedings.mlr.press/v229/dauner23a.html %V 229 %X The release of nuPlan marks a new era in vehicle motion planning research, offering the first large-scale real-world dataset and evaluation schemes requiring both precise short-term planning and long-horizon ego-forecasting. Existing systems struggle to simultaneously meet both requirements. Indeed, we find that these tasks are fundamentally misaligned and should be addressed independently. We further assess the current state of closed-loop planning in the field, revealing the limitations of learning-based methods in complex real-world scenarios and the value of simple rule-based priors such as centerline selection through lane graph search algorithms. More surprisingly, for the open-loop sub-task, we observe that the best results are achieved when using only this centerline as scene context (i.e., ignoring all information regarding the map and other agents). Combining these insights, we propose an extremely simple and efficient planner which outperforms an extensive set of competitors, winning the nuPlan planning challenge 2023.
APA
Dauner, D., Hallgarten, M., Geiger, A. & Chitta, K.. (2023). Parting with Misconceptions about Learning-based Vehicle Motion Planning. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:1268-1281 Available from https://proceedings.mlr.press/v229/dauner23a.html.

Related Material