SocialCircle+: Learning the Angle-based Conditioned Interaction Representation for Pedestrian Trajectory Prediction

TL;DR

This paper introduces SocialCircle+, an angle-based conditioned social interaction representation for pedestrian trajectory prediction, inspired by echolocation, which improves prediction accuracy and explainability by modeling social and physical conditions.

Contribution

The work presents a novel angle-based interaction representation that captures social and environmental conditions, enhancing trajectory prediction and interpretability.

Findings

Outperforms existing methods across multiple prediction benchmarks.

Demonstrates effective modeling of causal relationships among interactive variables.

Shows improved adaptability with different prediction backbones.

Abstract

Trajectory prediction is a crucial aspect of understanding human behaviors. Researchers have made efforts to represent socially interactive behaviors among pedestrians and utilize various networks to enhance prediction capability. Unfortunately, they still face challenges not only in fully explaining and measuring how these interactive behaviors work to modify trajectories but also in modeling pedestrians' preferences to plan or participate in social interactions in response to the changeable physical environments as extra conditions. This manuscript mainly focuses on the above explainability and conditionality requirements for trajectory prediction networks. Inspired by marine animals perceiving other companions and the environment underwater by echolocation, this work constructs an angle-based conditioned social interaction representation SocialCircle+ to represent the socially interactive context and its corresponding conditions. It employs a social branch and a conditional branch to describe how pedestrians are positioned in prediction scenes socially and physically in angle-based-cyclic-sequence forms. Then, adaptive fusion is applied to fuse the above conditional clues onto the social ones to learn the final interaction representation. Experiments demonstrate the superiority of SocialCircle+ with different trajectory prediction backbones. Moreover, counterfactual interventions have been made to simultaneously verify the modeling capacity of causalities among interactive variables and the conditioning capability.