FootBots: A Transformer-based Architecture for Motion Prediction in Soccer

TL;DR

FootBots introduces a transformer-based model that effectively predicts soccer player and ball movements by capturing complex social and temporal dynamics, outperforming existing methods in both real and synthetic datasets.

Contribution

The paper presents FootBots, a novel transformer architecture with set attention for motion prediction and conditioned predictions in soccer, emphasizing social and temporal dynamics.

Findings

Outperforms baseline models in real soccer data

Effective social attention mechanism demonstrated on synthetic data

Excels in conditioned motion prediction tasks

Abstract

Motion prediction in soccer involves capturing complex dynamics from player and ball interactions. We present FootBots, an encoder-decoder transformer-based architecture addressing motion prediction and conditioned motion prediction through equivariance properties. FootBots captures temporal and social dynamics using set attention blocks and multi-attention block decoder. Our evaluation utilizes two datasets: a real soccer dataset and a tailored synthetic one. Insights from the synthetic dataset highlight the effectiveness of FootBots' social attention mechanism and the significance of conditioned motion prediction. Empirical results on real soccer data demonstrate that FootBots outperforms baselines in motion prediction and excels in conditioned tasks, such as predicting the players based on the ball position, predicting the offensive (defensive) team based on the ball and the defensive (offensive) team, and predicting the ball position based on all players. Our evaluation connects quantitative and qualitative findings. https://youtu.be/9kaEkfzG3L8