# Qualitative Prediction of Multi-Agent Spatial Interactions

arXiv: https://arxiv.org/abs/2307.00065 · HTML: https://mlsanity.com/paper/2307.00065/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 30 Jun 2023.

## Builds on (most cited first, 7 of 7)

- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [A Dual-Stage Attention-Based Recurrent Neural Network for Time Series Prediction](https://mlsanity.com/paper/1704.02971/) (2017)
- [Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning](https://mlsanity.com/paper/1809.08835/) (2018)
- [Peeking into the Future: Predicting Future Person Activities and Locations in Videos](https://mlsanity.com/paper/1902.03748/) (2019)
- [Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction](https://mlsanity.com/paper/2008.00777/) (2020)
- [Deep Local Trajectory Replanning and Control for Robot Navigation](https://mlsanity.com/paper/1905.05279/) (2019)
- [REFORM: Recognizing F-formations for Social Robots](https://mlsanity.com/paper/2008.07668/) (2020)

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

- [Experimental Evaluation of ROS-Causal in Real-World Human-Robot Spatial Interaction Scenarios](https://mlsanity.com/paper/2406.04955/) (2024)
- [Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments](https://mlsanity.com/paper/2504.11901/) (2025)

## Abstract (arXiv)

Deploying service robots in our daily life, whether in restaurants, warehouses or hospitals, calls for the need to reason on the interactions happening in dense and dynamic scenes. In this paper, we present and benchmark three new approaches to model and predict multi-agent interactions in dense scenes, including the use of an intuitive qualitative representation. The proposed solutions take into account static and dynamic context to predict individual interactions. They exploit an input- and a temporal-attention mechanism, and are tested on medium and long-term time horizons. The first two approaches integrate different relations from the so-called Qualitative Trajectory Calculus (QTC) within a state-of-the-art deep neural network to create a symbol-driven neural architecture for predicting spatial interactions. The third approach implements a purely data-driven network for motion prediction, the output of which is post-processed to predict QTC spatial interactions. Experimental results on a popular robot dataset of challenging crowded scenarios show that the purely data-driven prediction approach generally outperforms the other two. The three approaches were further evaluated on a different but related human scenarios to assess their generalisation capability.