Evaluating Soccer Player Movements Using the Attacker-Defender Model

TL;DR

This paper evaluates and validates the attacker-defender motion model for soccer players using a large dataset, improving parameter optimization and revealing distinct playing styles based on optimized parameters.

Contribution

It enhances parameter optimization methods, validates the model on extensive real match data, and demonstrates its ability to distinguish player styles.

Findings

Model accurately reproduces real dribbling trajectories.

Optimized parameters reveal distinct attacker and defender styles.

Validated on 306 professional soccer matches.

Abstract

The present study investigates the attacker-defender (AD) model proposed by Brink et al. (2023), a motion model that describes the interactions between a ball carrier (attacker) and the nearest defender during ball possession. The model is based on the equations of motion for both players, incorporating resistance, goal-oriented force, and opponent-oriented force. It generates trajectories based on physically interpretable parameters. Although the AD model reproduces real dribbling trajectories well, previous studies have explored only a limited range of parameter values and relied on relatively small datasets. This study aims to (1) enhance parameter optimization by solving the AD model for one player with the opponent's actual trajectory fixed, (2) validate the model's applicability to a large dataset from 306 J1-League matches, and (3) demonstrate distinct playing styles of attackers and defenders based on the full range of optimized parameters.