SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving

Prarthana Bhattacharyya, Chengjie Huang, Krzysztof Czarnecki
Proceedings of The 6th Conference on Robot Learning, PMLR 205:1793-1805, 2023.

Abstract

Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation learning. However its potential in motion forecasting for autonomous driving has rarely been explored. In this study, we report the first systematic exploration and assessment of incorporating self-supervision into motion forecasting. We first propose to investigate four novel self-supervised learning tasks for motion forecasting with theoretical rationale and quantitative and qualitative comparisons on the challenging large-scale Argoverse dataset. Secondly, we point out that our auxiliary SSL-based learning setup not only outperforms forecasting methods which use transformers, complicated fusion mechanisms and sophisticated online dense goal candidate optimization algorithms in terms of performance accuracy, but also has low inference time and architectural complexity. Lastly, we conduct several experiments to understand why SSL improves motion forecasting.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-bhattacharyya23a, title = {SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving}, author = {Bhattacharyya, Prarthana and Huang, Chengjie and Czarnecki, Krzysztof}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {1793--1805}, 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/bhattacharyya23a/bhattacharyya23a.pdf}, url = {https://proceedings.mlr.press/v205/bhattacharyya23a.html}, abstract = {Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation learning. However its potential in motion forecasting for autonomous driving has rarely been explored. In this study, we report the first systematic exploration and assessment of incorporating self-supervision into motion forecasting. We first propose to investigate four novel self-supervised learning tasks for motion forecasting with theoretical rationale and quantitative and qualitative comparisons on the challenging large-scale Argoverse dataset. Secondly, we point out that our auxiliary SSL-based learning setup not only outperforms forecasting methods which use transformers, complicated fusion mechanisms and sophisticated online dense goal candidate optimization algorithms in terms of performance accuracy, but also has low inference time and architectural complexity. Lastly, we conduct several experiments to understand why SSL improves motion forecasting.} }
Endnote
%0 Conference Paper %T SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving %A Prarthana Bhattacharyya %A Chengjie Huang %A Krzysztof Czarnecki %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-bhattacharyya23a %I PMLR %P 1793--1805 %U https://proceedings.mlr.press/v205/bhattacharyya23a.html %V 205 %X Self-supervised learning (SSL) is an emerging technique that has been successfully employed to train convolutional neural networks (CNNs) and graph neural networks (GNNs) for more transferable, generalizable, and robust representation learning. However its potential in motion forecasting for autonomous driving has rarely been explored. In this study, we report the first systematic exploration and assessment of incorporating self-supervision into motion forecasting. We first propose to investigate four novel self-supervised learning tasks for motion forecasting with theoretical rationale and quantitative and qualitative comparisons on the challenging large-scale Argoverse dataset. Secondly, we point out that our auxiliary SSL-based learning setup not only outperforms forecasting methods which use transformers, complicated fusion mechanisms and sophisticated online dense goal candidate optimization algorithms in terms of performance accuracy, but also has low inference time and architectural complexity. Lastly, we conduct several experiments to understand why SSL improves motion forecasting.
APA
Bhattacharyya, P., Huang, C. & Czarnecki, K.. (2023). SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:1793-1805 Available from https://proceedings.mlr.press/v205/bhattacharyya23a.html.

Related Material