Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors

Sushant Veer, Apoorva Sharma, Marco Pavone
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2807-2820, 2023.

Abstract

Trajectory prediction modules are key enablers for safe and efficient planning of autonomous vehicles (AVs), particularly in highly interactive traffic scenarios. Recently, learning-based trajectory predictors have experienced considerable success in providing state-of-the-art performance due to their ability to learn multimodal behaviors of other agents from data. In this paper, we present an algorithm called multi-predictor fusion (MPF) that augments the performance of learning-based predictors by imbuing them with motion planners that are tasked with satisfying logic-based rules. MPF probabilistically combines learning- and rule-based predictors by mixing trajectories from both standalone predictors in accordance with a belief distribution that reflects the online performance of each predictor. In our results, we show that MPF outperforms the two standalone predictors on various metrics and delivers the most consistent performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-veer23a, title = {Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors}, author = {Veer, Sushant and Sharma, Apoorva and Pavone, Marco}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2807--2820}, 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/veer23a/veer23a.pdf}, url = {https://proceedings.mlr.press/v229/veer23a.html}, abstract = {Trajectory prediction modules are key enablers for safe and efficient planning of autonomous vehicles (AVs), particularly in highly interactive traffic scenarios. Recently, learning-based trajectory predictors have experienced considerable success in providing state-of-the-art performance due to their ability to learn multimodal behaviors of other agents from data. In this paper, we present an algorithm called multi-predictor fusion (MPF) that augments the performance of learning-based predictors by imbuing them with motion planners that are tasked with satisfying logic-based rules. MPF probabilistically combines learning- and rule-based predictors by mixing trajectories from both standalone predictors in accordance with a belief distribution that reflects the online performance of each predictor. In our results, we show that MPF outperforms the two standalone predictors on various metrics and delivers the most consistent performance.} }
Endnote
%0 Conference Paper %T Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors %A Sushant Veer %A Apoorva Sharma %A Marco Pavone %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-veer23a %I PMLR %P 2807--2820 %U https://proceedings.mlr.press/v229/veer23a.html %V 229 %X Trajectory prediction modules are key enablers for safe and efficient planning of autonomous vehicles (AVs), particularly in highly interactive traffic scenarios. Recently, learning-based trajectory predictors have experienced considerable success in providing state-of-the-art performance due to their ability to learn multimodal behaviors of other agents from data. In this paper, we present an algorithm called multi-predictor fusion (MPF) that augments the performance of learning-based predictors by imbuing them with motion planners that are tasked with satisfying logic-based rules. MPF probabilistically combines learning- and rule-based predictors by mixing trajectories from both standalone predictors in accordance with a belief distribution that reflects the online performance of each predictor. In our results, we show that MPF outperforms the two standalone predictors on various metrics and delivers the most consistent performance.
APA
Veer, S., Sharma, A. & Pavone, M.. (2023). Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2807-2820 Available from https://proceedings.mlr.press/v229/veer23a.html.

Related Material