ForceFormer: Exploring Social Force and Transformer for Pedestrian Trajectory Prediction

TL;DR

ForceFormer is a novel social force and Transformer-based model that improves pedestrian trajectory prediction by effectively incorporating goal and social interaction information, reducing collisions in dense scenes.

Contribution

The paper introduces ForceFormer, integrating social forces into a Transformer model, to better utilize goal information and social interactions for pedestrian trajectory prediction.

Findings

Achieves comparable accuracy to state-of-the-art models.

Reduces collision rates in dense pedestrian scenarios.

Effectively models social interactions and goal guidance.

Abstract

Predicting trajectories of pedestrians based on goal information in highly interactive scenes is a crucial step toward Intelligent Transportation Systems and Autonomous Driving. The challenges of this task come from two key sources: (1) complex social interactions in high pedestrian density scenarios and (2) limited utilization of goal information to effectively associate with past motion information. To address these difficulties, we integrate social forces into a Transformer-based stochastic generative model backbone and propose a new goal-based trajectory predictor called ForceFormer. Differentiating from most prior works that simply use the destination position as an input feature, we leverage the driving force from the destination to efficiently simulate the guidance of a target on a pedestrian. Additionally, repulsive forces are used as another input feature to describe the avoidance action among neighboring pedestrians. Extensive experiments show that our proposed method achieves on-par performance measured by distance errors with the state-of-the-art models but evidently decreases collisions, especially in dense pedestrian scenarios on widely used pedestrian datasets.