Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
This work addresses trajectory prediction for autonomous vehicles and social robots in crowded scenarios, representing an incremental improvement through explicit interaction modeling and kinematic constraints.
The paper tackled the problem of predicting future trajectories for multiple agents in interactive, crowded environments by proposing Social-WaGDAT, a generative neural system that models interactions using dynamic graphs and incorporates scene context, achieving better prediction accuracy than baselines on three public datasets.
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.