# StarNet: Pedestrian Trajectory Prediction using Deep Neural Network in Star Topology

arXiv: https://arxiv.org/abs/1906.01797 · HTML: https://mlsanity.com/paper/1906.01797/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2019.

## Built on by (most cited first, 17 of 17)

- [Motion Transformer with Global Intention Localization and Local Movement Refinement](https://mlsanity.com/paper/2209.13508/) (2022)
- [MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying](https://mlsanity.com/paper/2306.17770/) (2023)
- [Adaptive Trajectory Prediction via Transferable GNN](https://mlsanity.com/paper/2203.05046/) (2022)
- [Interpretable Social Anchors for Human Trajectory Forecasting in Crowds](https://mlsanity.com/paper/2105.03136/) (2021)
- [STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes](https://mlsanity.com/paper/2204.01026/) (2022)
- [Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches](https://mlsanity.com/paper/2111.06740/) (2021)
- [S2TNet: Spatio-Temporal Transformer Networks for Trajectory Prediction in Autonomous Driving](https://mlsanity.com/paper/2206.10902/) (2022)
- [Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction](https://mlsanity.com/paper/2108.00238/) (2021)
- [SCOUT: Socially-COnsistent and UndersTandable Graph Attention Network for Trajectory Prediction of Vehicles and VRUs](https://mlsanity.com/paper/2102.06361/) (2021)
- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://mlsanity.com/paper/2503.03262/) (2025)
- [Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting](https://mlsanity.com/paper/2209.12243/) (2022)
- [Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning](https://mlsanity.com/paper/2211.00848/) (2022)
- [EPG-MGCN: Ego-Planning Guided Multi-Graph Convolutional Network for Heterogeneous Agent Trajectory Prediction](https://mlsanity.com/paper/2303.17027/) (2023)
- [Attention-aware Social Graph Transformer Networks for Stochastic Trajectory Prediction](https://mlsanity.com/paper/2312.15881/) (2023)
- [Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting](https://mlsanity.com/paper/2101.02385/) (2021)
- [STF: Spatial Temporal Fusion for Trajectory Prediction](https://mlsanity.com/paper/2311.18149/) (2023)
- [Phase Space Reconstruction Network for Lane Intrusion Action Recognition](https://mlsanity.com/paper/2102.11149/) (2021)

## Abstract (arXiv)

Pedestrian trajectory prediction is crucial for many important applications. This problem is a great challenge because of complicated interactions among pedestrians. Previous methods model only the pairwise interactions between pedestrians, which not only oversimplifies the interactions among pedestrians but also is computationally inefficient. In this paper, we propose a novel model StarNet to deal with these issues. StarNet has a star topology which includes a unique hub network and multiple host networks. The hub network takes observed trajectories of all pedestrians to produce a comprehensive description of the interpersonal interactions. Then the host networks, each of which corresponds to one pedestrian, consult the description and predict future trajectories. The star topology gives StarNet two advantages over conventional models. First, StarNet is able to consider the collective influence among all pedestrians in the hub network, making more accurate predictions. Second, StarNet is computationally efficient since the number of host network is linear to the number of pedestrians. Experiments on multiple public datasets demonstrate that StarNet outperforms multiple state-of-the-arts by a large margin in terms of both accuracy and efficiency.