Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrations

TL;DR

The paper introduces Resonance, a novel model inspired by vibration systems, to predict social-aware pedestrian trajectories by decomposing movements into independent vibrations for better explainability and accuracy.

Contribution

It proposes a new resonance-based approach that models social interactions as co-vibrations, enabling explainable and decoupled trajectory forecasting.

Findings

Effective in capturing social behaviors

Improves trajectory prediction accuracy

Enhances interpretability of social interactions

Abstract

Learning to forecast trajectories of intelligent agents has caught much more attention recently. However, it remains a challenge to accurately account for agents' intentions and social behaviors when forecasting, and in particular, to simulate the unique randomness within each of those components in an explainable and decoupled way. Inspired by vibration systems and their resonance properties, we propose the Resonance (short for Re) model to encode and forecast pedestrian trajectories in the form of ``co-vibrations''. It decomposes trajectory modifications and randomnesses into multiple vibration portions to simulate agents' reactions to each single cause, and forecasts trajectories as the superposition of these independent vibrations separately. Also, benefiting from such vibrations and their spectral properties, representations of social interactions can be learned by emulating the resonance phenomena, further enhancing its explainability. Experiments on multiple datasets have verified its usefulness both quantitatively and qualitatively.