# Potential Field: Interpretable and Unified Representation for Trajectory Prediction

arXiv: https://arxiv.org/abs/1911.07414 · HTML: https://mlsanity.com/paper/1911.07414/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2019.

## Built on by (most cited first, 4 of 4)

- [Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking](https://mlsanity.com/paper/2102.09117/) (2021)
- [Graph-Based Interaction-Aware Multimodal 2D Vehicle Trajectory Prediction using Diffusion Graph Convolutional Networks](https://mlsanity.com/paper/2309.01981/) (2023)
- [Potential Field as Scene Affordance for Behavior Change-Based Visual Risk Object Identification](https://mlsanity.com/paper/2409.15846/) (2024)
- [Characterizing Structured versus Unstructured Environments based on Pedestrians' and Vehicles' Motion Trajectories](https://mlsanity.com/paper/2502.16847/) (2025)

## Abstract (arXiv)

Predicting an agent's future trajectory is a challenging task given the complicated stimuli (environmental/inertial/social) of motion. Prior works learn individual stimulus from different modules and fuse the representations in an end-to-end manner, which makes it hard to understand what are actually captured and how they are fused. In this work, we borrow the notion of potential field from physics as an interpretable and unified representation to model all stimuli. This allows us to not only supervise the intermediate learning process, but also have a coherent method to fuse the information of different sources. From the generated potential fields, we further estimate future motion direction and speed, which are modeled as Gaussian distributions to account for the multi-modal nature of the problem. The final prediction results are generated by recurrently moving past location based on the estimated motion direction and speed. We show state-of-the-art results on the ETH, UCY, and Stanford Drone datasets.