PRISM: Predictive Representation of Interaction Style and Motion for Social Robot Navigation

2026-09-16

AI Summary

为解决机器人导航中忽视个体互动差异的问题，提出PRISM框架，通过观察人类互动推断互动特征，并应用于导航策略，降低碰撞率。

Abstract

Humans often observe others before interacting and adjust their behavior accordingly. Robot navigation in crowds, however, often represents pedestrians mainly by observed geometric states, leaving individual differences in interaction tendencies implicit. We propose PRISM (Predictive Representation of Interaction Style and Motion), a framework that infers interaction traits from passive observations of human-human interactions. PRISM encodes human trajectories into a continuous ordinal latent space with a transformer encoder trained by Rank-N-Contrast loss, and pairs each inferred trait with a temporal-stability score supplied to the navigation policy. In randomized crowd simulations, PRISM reduces collision rates over the geometry-only baseline and yields small improvements in navigation-time and path-length metrics. These results suggest the utility of passive latent-trait inference for social navigation in dynamic crowds.

Problem

• Robot Navigation
• Human Interaction
• Crowd Dynamics
• Latent Trait Inference

Innovation

• PRISM
• latent trait inference
• transformer encoder
• Rank-N-Contrast loss
• social navigation