JointMotion: Joint Self-supervision for Joint Motion Prediction

arXiv:2403.05489v1 Announce Type: new
Abstract: We present JointMotion, a self-supervised learning method for joint motion prediction in autonomous driving. Our method includes a scene-level objective connecting motion and environments, and an instance-level objective to refine learned representations. Our evaluations show that these objectives are complementary and outperform recent contrastive and autoencoding methods as pre-training for joint motion prediction. Furthermore, JointMotion adapts to all common types of environment representations used for motion prediction (i.e., agent-centric, scene-centric, and pairwise relative), and enables …

abstract arxiv autonomous autonomous driving cs.cv cs.ro driving environments instance prediction refine self-supervised learning show supervised learning supervision type