Socialality Anchors: Towards Group-bounded Trajectory Prediction

2026-09-29

AI Summary

This study addresses the challenge of trajectory prediction, where existing group modeling approaches rely on fixed thresholds while neglecting individual differences and spatiotemporal dynamics. To overcome these limitations, this work proposes Sociality, a framework inspired by human social perception. Methodologically, it introduces a novel dual-scalar controlled grouping kernel that integrates historical observations with future previews to learn personalized grouping rules. By combining an extended grouping window with a group-aware interaction model, the framework achieves stable, context-aware, and interpretable group inference. Experimental results demonstrate that the proposed method significantly improves prediction performance on standard benchmarks, while qualitative analyses further validate the interpretability and stability of the learned anchors.

Abstract

Trajectory prediction is a key component for understanding human behavior patterns in dynamic scenes. Researchers have devoted substantial efforts to modeling social interactions, especially group-wise interactions, since group membership often reflects shared intention, coordinated motion, and stable mutual adaptation, thus providing a persistent and semantically meaningful social prior for forecasting. However, existing group modeling methods may rely on a fixed threshold and infer groups mainly from agents' relative positions within the observation window, overlooking the fact that grouping rules should be agent-specific, temporally coherent, and context-adaptive across diverse personalities, culturalities, and evolving interaction contexts. Inspired by human social perception that alternates between interpersonal distance in boundary-sensitive situations and relative speed consistency in dynamic interactions, we propose Socialality, a human-inspired trajectory prediction framework with interpretable Socialality anchors and an extended grouping window for stable, context-aware grouping inference. Concretely, Socialality introduces a duo-scalar-controlled grouping kernel Socialality that jointly leverages historical observations and short-term future trajectory previews to learn agent-specific grouping rules, and employs a group-wise perception mechanism to model in-group and out-of-group interactions in an intuitive and explainable manner. Furthermore, we conduct extensive experiments on standard benchmarks to demonstrate the performance gains of Socialality, and provide qualitative analyses and statistical studies of anchor distributions to verify the interpretability and stability of the proposed Socialality anchors.

Problem

• Trajectory Prediction
• Group Modeling
• Social Interactions
• Context-adaptive Grouping

Innovation

• Trajectory Prediction
• Sociality Anchors
• Group-bounded Interaction
• Agent-specific Grouping
• Interpretable Modeling