# Polar Collision Grids: Effective Interaction Modelling for Pedestrian Trajectory Prediction in Shared Space Using Collision Checks

arXiv: https://arxiv.org/abs/2308.06654 · HTML: https://mlsanity.com/paper/2308.06654/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 13 Aug 2023.

## Builds on (most cited first, 12 of 12)

- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents](https://mlsanity.com/paper/1704.04394/) (2017)
- [Social Attention: Modeling Attention in Human Crowds](https://mlsanity.com/paper/1710.04689/) (2017)
- [LOKI: Long Term and Key Intentions for Trajectory Prediction](https://mlsanity.com/paper/2108.08236/) (2021)
- [Collaborative Motion Prediction via Neural Motion Message Passing](https://mlsanity.com/paper/2003.06594/) (2020)
- [RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting](https://mlsanity.com/paper/2108.01316/) (2021)
- [Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking](https://mlsanity.com/paper/2102.09117/) (2021)
- [Pedestrian Trajectory Prediction in Pedestrian-Vehicle Mixed Environments: A Systematic Review](https://mlsanity.com/paper/2308.06419/) (2023)
- [SCOUT: Socially-COnsistent and UndersTandable Graph Attention Network for Trajectory Prediction of Vehicles and VRUs](https://mlsanity.com/paper/2102.06361/) (2021)
- [Probabilistic Crowd GAN: Multimodal Pedestrian Trajectory Prediction using a Graph Vehicle-Pedestrian Attention Network](https://mlsanity.com/paper/2006.12906/) (2020)
- [Learning the Pedestrian-Vehicle Interaction for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2202.05334/) (2022)
- [MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic](https://mlsanity.com/paper/2002.05966/) (2020)

## Built on by (most cited first, 2 of 2)

- [Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space](https://mlsanity.com/paper/2405.13969/) (2024)
- [Safety-oriented pedestrian trajectory prediction at urban intersections using time-to-collision and crossing-zone context](https://mlsanity.com/paper/2609.29706/) (2026)

## Abstract (arXiv)

Predicting pedestrians' trajectories is a crucial capability for autonomous vehicles' safe navigation, especially in spaces shared with pedestrians. Pedestrian motion in shared spaces is influenced by both the presence of vehicles and other pedestrians. Therefore, effectively modelling both pedestrian-pedestrian and pedestrian-vehicle interactions can increase the accuracy of the pedestrian trajectory prediction models. Despite the huge literature on ways to encode the effect of interacting agents on a pedestrian's predicted trajectory using deep-learning models, limited effort has been put into the effective selection of interacting agents. In the majority of cases, the interaction features used are mainly based on relative distances while paying less attention to the effect of the velocity and approaching direction in the interaction formulation. In this paper, we propose a heuristic-based process of selecting the interacting agents based on collision risk calculation. Focusing on interactions of potentially colliding agents with a target pedestrian, we propose the use of time-to-collision and the approach direction angle of two agents for encoding the interaction effect. This is done by introducing a novel polar collision grid map. Our results have shown predicted trajectories closer to the ground truth compared to existing methods (used as a baseline) on the HBS dataset.