EvolveGraph: Multi-Agent Trajectory Prediction with Dynamic Relational Reasoning

Abstract

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.

arXiv commentNeurIPS 2020. Website: https://jiachenli94.github.io/publications/Evolvegraph/

References in corpus (7)

• Social Force Model for Pedestrian Dynamics
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
• Generic Tracking and Probabilistic Prediction Framework and Its Application in Autonomous Driving
• Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network
• Neural Relational Inference with Fast Modular Meta-learning
• Potential Field: Interpretable and Unified Representation for Trajectory Prediction

Cited by in corpus (9)

• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• A Review of Tracking, Prediction and Decision Making Methods for Autonomous Driving
• SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks
• Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning
• Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction
• nuScenes Knowledge Graph -- A comprehensive semantic representation of traffic scenes for trajectory prediction
• Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
• Generalizability Analysis of Graph-based Trajectory Predictor with Vectorized Representation
• About latent roles in forecasting players in team sports