Description: Contrastive Learning of Socially-aware Motion Representations
reinforcement learning (140) representation learning (19) imitation learning (14) data augmentation (9) multi agent (6) contrastive learning (2) social nce (1) motion forecasting (1)
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds. Despite promising progress, existing representations learned with neural networks still struggle to generalize in closed-loop predictions (e.g., output colliding trajectories). This issue largely arises from the non-i.i.d. nature of sequential prediction in conjunction with ill-distributed training data. Intuitively, if the training data o
In this work, we aim to address this issue by explicitly modeling negative examples through self-supervision: (i) we introduce a social contrastive loss that regularizes the extracted motion representation by discerning the ground-truth positive events from synthetic negative ones; (ii) we construct informative negative samples based on our prior knowledge of rare but dangerous circumstances. Our method substantially reduces the collision rates of recent trajectory forecasting, behavioral cloning and reinfo
Our key idea is to explicitly model negative examples based on our prior knowledge. Intuitively, one effective way to explain the social norms behind positive examples is to portray the opposite negative examples like collisions. Our method can be viewed as a form of negative data augmentation through self-supervision, as opposed to laboriously collecting additional state-action pairs from dangerous scenarios.