EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning
This addresses trajectory prediction for interactive agents in applications like decision-making, though it is incremental as it builds on existing graph-based methods with dynamic and multi-modal enhancements.
The paper tackles the problem of predicting multi-agent trajectories by introducing EvolveGraph, a framework that uses dynamic relational reasoning and latent interaction graphs to handle evolving interactions and provide multi-modal predictions, achieving state-of-the-art accuracy on synthetic and real-world benchmarks.
Multi-agent interacting systems are prevalent in the world, from pure physical systems to complicated social dynamic systems. In many applications, effective understanding of the situation and accurate trajectory prediction of interactive agents play a significant role in downstream tasks, such as decision making and planning. In this paper, we propose a generic trajectory forecasting framework (named EvolveGraph) with explicit relational structure recognition and prediction via latent interaction graphs among multiple heterogeneous, interactive agents. Considering the uncertainty of future behaviors, the model is designed to provide multi-modal prediction hypotheses. Since the underlying interactions may evolve even with abrupt changes, and different modalities of evolution may lead to different outcomes, we address the necessity of dynamic relational reasoning and adaptively evolving the interaction graphs. We also introduce a double-stage training pipeline which not only improves training efficiency and accelerates convergence, but also enhances model performance. The proposed framework is evaluated on both synthetic physics simulations and multiple real-world benchmark datasets in various areas. The experimental results illustrate that our approach achieves state-of-the-art performance in terms of prediction accuracy.