Human Trajectory Prediction via Counterfactual Analysis

TL;DR

This paper introduces a counterfactual analysis approach to human trajectory prediction that reduces environment bias effects, improving accuracy across various baseline models and achieving state-of-the-art results.

Contribution

It proposes a novel counterfactual analysis method that isolates trajectory clues from environmental influences, enhancing prediction robustness and generalization.

Findings

Consistent performance improvements across multiple baseline models.

Achieved state-of-the-art results on public pedestrian trajectory benchmarks.

Effective reduction of environment bias in trajectory forecasting.

Abstract

Forecasting human trajectories in complex dynamic environments plays a critical role in autonomous vehicles and intelligent robots. Most existing methods learn to predict future trajectories by behavior clues from history trajectories and interaction clues from environments. However, the inherent bias between training and deployment environments is ignored. Hence, we propose a counterfactual analysis method for human trajectory prediction to investigate the causality between the predicted trajectories and input clues and alleviate the negative effects brought by environment bias. We first build a causal graph for trajectory forecasting with history trajectory, future trajectory, and the environment interactions. Then, we cut off the inference from environment to trajectory by constructing the counterfactual intervention on the trajectory itself. Finally, we compare the factual and counterfactual trajectory clues to alleviate the effects of environment bias and highlight the trajectory clues. Our counterfactual analysis is a plug-and-play module that can be applied to any baseline prediction methods including RNN- and CNN-based ones. We show that our method achieves consistent improvement for different baselines and obtains the state-of-the-art results on public pedestrian trajectory forecasting benchmarks.