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

Published: 10 Sept 2022, Last Modified: 17 Sept 2023CoRL 2022 PosterReaders: Everyone
Student First Author: yes
Keywords: Motion Forecasting, Autonomous Driving, Self-Supervised Learning
TL;DR: We report the first systematic exploration of self-supervision with motion forecasting for autonomous driving.
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.
Supplementary Material: zip
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2206.14116/code)
Website: https://arxiv.org/abs/2206.14116
Code: https://github.com/AutoVision-cloud/SSL-Lanes
14 Replies

Loading