MHTraj: A Multi-Domain Hybrid Graph Neural Network With Causal-Spatial Modeling for Multi-Agent Trajectory Prediction
- 25 August 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 13, 1786-1799
Abstract
As a crucial part of social behavior modeling, multi-agent trajectory prediction with dynamic interactions has become one of the core technologies for autonomous systems. One of the main research streams is to leverage relational graph Transformers to learn interactions among agents, as this method demonstrates superior capability in capturing implicit features and modeling complex relationships. However, such researches fall short in efficiently utilizing multi-domain features, consequently being constrained by spatial attention layers that hinder accuracy improvements. To address the above limitations and achieve a more lightweight map-free architecture, this work introduces a Multi-domain Hybrid Graph Transformer (MHTraj) for predicting multi-modal future trajectories. The core insight of the method lies in its well-designed encoder, which enhances inputs via a frequency-domain mixer and employs causal convolution attention to capture global temporal information. Furthermore, a graph Transformer is incorporated to aggregate spatial relationships, thereby yielding the final hybrid features. Extensive experiments on 4 real-world datasets (NBA, ETH/UCY, SDD, nuScenes) show that the proposed method achieves competitive state-of-the-art (SOTA) performances, and meanwhile reducing the parameter count by nearly 50% on the ETH/UCY datasets.Keywords
Funding Information
- National Science and Technology Innovation 2030 (2022ZD0205005)
- National Natural Science Foundation of China (61573057)
This publication has 74 references indexed in Scilit:
- MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction2024
- Efficient Frequency-Domain Image Deraining with Contrastive Regularization2024
- SocialVAE: Human Trajectory Prediction Using Timewise Latents2022
- Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction2022
- Social-Scene-Aware Generative Adversarial Networks for Pedestrian Trajectory Prediction2021
- Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data2020
- SimAug: Learning Robust Representations from Simulation for Trajectory Prediction2020
- DLow: Diversifying Latent Flows for Diverse Human Motion Prediction2020
- It Is Not the Journey But the Destination: Endpoint Conditioned Trajectory Prediction2020
- Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction2020