Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network

TL;DR

Social-WaGDAT is a generative neural network that models interactions among agents using dynamic graphs and attention mechanisms, improving multi-agent trajectory prediction accuracy in crowded scenarios.

Contribution

It introduces a novel interaction-aware trajectory prediction model with relational inductive biases, dynamic graph representation, and a kinematic constraint layer for physical feasibility.

Findings

Outperforms baseline methods on three benchmark datasets.

Effectively models interactions among pedestrians, cyclists, and vehicles.

Enhances prediction accuracy with scene and trajectory context integration.

Abstract

Effective understanding of the environment and accurate trajectory prediction of surrounding dynamic obstacles are indispensable for intelligent mobile systems (like autonomous vehicles and social robots) to achieve safe and high-quality planning when they navigate in highly interactive and crowded scenarios. Due to the existence of frequent interactions and uncertainty in the scene evolution, it is desired for the prediction system to enable relational reasoning on different entities and provide a distribution of future trajectories for each agent. In this paper, we propose a generic generative neural system (called Social-WaGDAT) for multi-agent trajectory prediction, which makes a step forward to explicit interaction modeling by incorporating relational inductive biases with a dynamic graph representation and leverages both trajectory and scene context information. We also employ an efficient kinematic constraint layer applied to vehicle trajectory prediction which not only ensures physical feasibility but also enhances model performance. The proposed system is evaluated on three public benchmark datasets for trajectory prediction, where the agents cover pedestrians, cyclists and on-road vehicles. The experimental results demonstrate that our model achieves better performance than various baseline approaches in terms of prediction accuracy.