Attentive Radiate Graph for Pedestrian Trajectory Prediction in Disconnected Manifolds
- 10 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (6) , 7755-7769
Abstract
Pedestrian trajectory prediction grapples with the demanding feat of modeling complex interactions and learning multimodal distribution to navigate different human-centric environments. Despite superior performance in reducing distance-based metrics, recent works tend to predict out-of-distribution trajectories, as the distribution of forthcoming paths comprises a blend of various manifolds that may be disconnected. These unrealistic trajectories can potentially jeopardize the safety of traffic participants and result in significant damage. To meet these challenges, we propose DMPred, a graph-based generator adversarial network that generates realistic multimodal trajectory predictions by better modeling the social interactions of pedestrians across different scenes in disconnected manifolds. The core of DMPred is an attentive radiate graph sequence constructed by considering the localized influence radiating from pedestrian movements, which is followed by a spatiotemporal extractor that stores and reuses potentially forgotten neighboring pedestrian information to allow for better extraction of complex interactions. Additionally, a collection of generators is utilized for forecasting, which incorporates spectral clustering on trajectories during the prior learning process of multiple generators to help reduce model redundancy and enhance flexibility for various prediction scenarios. Through extensive experiments on multiple real-world and simulation datasets, we demonstrate that DMPred obtains highly competitive results with efficacy in predicting realistic multimodal trajectories.Keywords
Funding Information
- National Natural Science Foundation of China (U23A20382, 62201388)
- Shanghai Municipal Science and Technology Major Project (2021SHZDZX0100)
This publication has 48 references indexed in Scilit:
- SocialVAE: Human Trajectory Prediction Using Timewise Latents2022
- Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data2020
- Long-Term Human Motion Prediction with Scene Context2020
- Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction2020
- Group LSTM: Group Trajectory Prediction in Crowded Scenarios2019
- Knowledge Transfer for Scene-Specific Motion Prediction2016
- Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes2016
- Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings2010
- The EM Algorithm and Extensions, 2E2008
- Self-Organization and Associative Memory1988