Map-Adaptive Goal-Based Trajectory Prediction

Lingyao Zhang, Po-Hsun Su, Jerrick Hoang, Galen Clark Haynes, Micol Marchetti-Bowick
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:1371-1383, 2021.

Abstract

We present a new method for multi-modal, long-term vehicle trajectory prediction. Our approach relies on using lane centerlines captured in rich maps of the environment to generate a set of proposed goal paths for each vehicle. Using these paths – which are generated at run time and therefore dynamically adapt to the scene – as spatial anchors, we predict a set of goal-based trajectories along with a categorical distribution over the goals. This approach allows us to directly model the goal-directed behavior of traffic actors, which unlocks the potential for more accurate long-term prediction. Our experimental results on both a large-scale internal driving dataset and on the public nuScenes dataset show that our model outperforms state-of-the-art approaches for vehicle trajectory prediction over a 6-second horizon. We also empirically demonstrate that our model is better able to generalize to road scenes from a completely new city than existing methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v155-zhang21a, title = {Map-Adaptive Goal-Based Trajectory Prediction}, author = {Zhang, Lingyao and Su, Po-Hsun and Hoang, Jerrick and Haynes, Galen Clark and Marchetti-Bowick, Micol}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {1371--1383}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/zhang21a/zhang21a.pdf}, url = {https://proceedings.mlr.press/v155/zhang21a.html}, abstract = {We present a new method for multi-modal, long-term vehicle trajectory prediction. Our approach relies on using lane centerlines captured in rich maps of the environment to generate a set of proposed goal paths for each vehicle. Using these paths – which are generated at run time and therefore dynamically adapt to the scene – as spatial anchors, we predict a set of goal-based trajectories along with a categorical distribution over the goals. This approach allows us to directly model the goal-directed behavior of traffic actors, which unlocks the potential for more accurate long-term prediction. Our experimental results on both a large-scale internal driving dataset and on the public nuScenes dataset show that our model outperforms state-of-the-art approaches for vehicle trajectory prediction over a 6-second horizon. We also empirically demonstrate that our model is better able to generalize to road scenes from a completely new city than existing methods.} }
Endnote
%0 Conference Paper %T Map-Adaptive Goal-Based Trajectory Prediction %A Lingyao Zhang %A Po-Hsun Su %A Jerrick Hoang %A Galen Clark Haynes %A Micol Marchetti-Bowick %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-zhang21a %I PMLR %P 1371--1383 %U https://proceedings.mlr.press/v155/zhang21a.html %V 155 %X We present a new method for multi-modal, long-term vehicle trajectory prediction. Our approach relies on using lane centerlines captured in rich maps of the environment to generate a set of proposed goal paths for each vehicle. Using these paths – which are generated at run time and therefore dynamically adapt to the scene – as spatial anchors, we predict a set of goal-based trajectories along with a categorical distribution over the goals. This approach allows us to directly model the goal-directed behavior of traffic actors, which unlocks the potential for more accurate long-term prediction. Our experimental results on both a large-scale internal driving dataset and on the public nuScenes dataset show that our model outperforms state-of-the-art approaches for vehicle trajectory prediction over a 6-second horizon. We also empirically demonstrate that our model is better able to generalize to road scenes from a completely new city than existing methods.
APA
Zhang, L., Su, P., Hoang, J., Haynes, G.C. & Marchetti-Bowick, M.. (2021). Map-Adaptive Goal-Based Trajectory Prediction. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:1371-1383 Available from https://proceedings.mlr.press/v155/zhang21a.html.

Related Material