# Stochastic trajectory prediction with social graph network

arXiv: https://arxiv.org/abs/1907.10233 · HTML: https://mlsanity.com/paper/1907.10233/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [Trajectory Prediction with Latent Belief Energy-Based Model](https://mlsanity.com/paper/2104.03086/) (2021)
- [Spectral Temporal Graph Neural Network for Trajectory Prediction](https://mlsanity.com/paper/2106.02930/) (2021)
- [Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers](https://mlsanity.com/paper/2106.12442/) (2021)
- [Physically Feasible Vehicle Trajectory Prediction](https://mlsanity.com/paper/2104.14679/) (2021)
- [Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting](https://mlsanity.com/paper/2101.02385/) (2021)
- [Stochastic Trajectory Prediction under Unstructured Constraints](https://mlsanity.com/paper/2503.14203/) (2025)
- [Predicting Human Trajectories by Learning and Matching Patterns](https://mlsanity.com/paper/2104.10241/) (2021)
- [Leveraging Multi-stream Information Fusion for Trajectory Prediction in Low-illumination Scenarios: A Multi-channel Graph Convolutional Approach](https://mlsanity.com/paper/2211.10226/) (2022)
- [Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers](https://mlsanity.com/paper/2605.14855/) (2026)

## Abstract (arXiv)

Pedestrian trajectory prediction is a challenging task because of the complexity of real-world human social behaviors and uncertainty of the future motion. For the first issue, existing methods adopt fully connected topology for modeling the social behaviors, while ignoring non-symmetric pairwise relationships. To effectively capture social behaviors of relevant pedestrians, we utilize a directed social graph which is dynamically constructed on timely location and speed direction. Based on the social graph, we further propose a network to collect social effects and accumulate with individual representation, in order to generate destination-oriented and social-aware representations. For the second issue, instead of modeling the uncertainty of the entire future as a whole, we utilize a temporal stochastic method for sequentially learning a prior model of uncertainty during social interactions. The prediction on the next step is then generated by sampling on the prior model and progressively decoding with a hierarchical LSTMs. Experimental results on two public datasets show the effectiveness of our method, especially when predicting trajectories in very crowded scenes.