Neural Interaction Energy for Multi-Agent Trajectory Prediction
Not on the map. Why?
Abstract (arXiv)
Maintaining temporal stability is crucial in multi-agent trajectory prediction. Insufficient regularization to uphold this stability often results in fluctuations in kinematic states, leading to inconsistent predictions and the amplification of errors. In this study, we introduce a framework called Multi-Agent Trajectory prediction via neural interaction Energy (MATE). This framework assesses the interactive motion of agents by employing neural interaction energy, which captures the dynamics of interactions and illustrates their influence on the future trajectories of agents. To bolster temporal stability, we introduce two constraints: inter-agent interaction constraint and intra-agent motion constraint. These constraints work together to ensure temporal stability at both the system and agent levels, effectively mitigating prediction fluctuations inherent in multi-agent systems. Comparative evaluations against previous methods on four diverse datasets highlight the superior prediction accuracy and generalization capabilities of our model.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 26 of its 53 references that are in the map. First posted on arXiv 25 Apr 2024.
Builds on
26 of 53 references.
References · 26
- 2017Graph Attention Networkscited by 8,923
- 2018Neural Ordinary Differential Equationscited by 3,779
- 2020Learning to Simulate Complex Physics with Graph Networkscited by 880
- 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
- 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
- 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 325
- 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
- 2018Machine Theory of Mindcited by 226
- 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
- 2017Social Attention: Modeling Attention in Human Crowdscited by 186
- 2019Symplectic ODE-Net: Learning Hamiltonian Dynamics with Controlcited by 184
- 2020Transformer Networks for Trajectory Forecastingcited by 181
14 more
- 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 175
- 2023Leapfrog Diffusion Model for Stochastic Trajectory Predictioncited by 132
- 2019Multi-Agent Tensor Fusion for Contextual Trajectory Predictioncited by 131
- 2022On Adversarial Robustness of Trajectory Prediction for Autonomous Vehiclescited by 90
- 2022Human Trajectory Prediction via Neural Social Physicscited by 66
- 2021LOKI: Long Term and Key Intentions for Trajectory Predictioncited by 57
- 2018Generating Multi-Agent Trajectories using Programmatic Weak Supervisioncited by 46
- 2024DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrievalcited by 26
- 2018Scene-LSTM: A Model for Human Trajectory Predictioncited by 25
- 2021PHASE: PHysically-grounded Abstract Social Events for Machine Social Perceptioncited by 22
- 2018Relational Forward Models for Multi-Agent Learningcited by 21
- 2020Multi-Modal Trajectory Prediction of NBA Playerscited by 19
- 2020Multi-agent Trajectory Prediction with Fuzzy Query Attentioncited by 16
- 2019Factorised Neural Relational Inference for Multi-Interaction Systemscited by 15
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.