Social NCE: Contrastive Learning of Socially-aware Motion Representations

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• vita-epfl/social-nce — marked official in Papers with Code; named in the paper
• YuejiangLIU/social-nce-trajectron-plus-plus
• qiyan98/social-nce-stgcnn
• vita-epfl/social-nce-crowdnav

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 only comes from human behaviors in safe spaces, i.e., from "positive" examples, it is difficult for learning algorithms to capture the notion of "negative" examples like collisions. 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 reinforcement learning algorithms, outperforming state-of-the-art methods on several benchmarks. Our code is available at https://github.com/vita-epfl/social-nce.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2012.11717")
get_code_for_paper("2012.11717")
have("2012.11717")

Connect an agent — have() is free.