Benchmarking Stroke Forecasting with Stroke-Level Badminton Dataset

TL;DR

This work introduces ShuttleSet22, a stroke-level badminton singles dataset drawn from 2022 high-ranking matches, providing extensive training, validation, and testing data to enable advanced analytics and benchmarking. It also launches Track 2 of the CoachAI Badminton Challenge, with ShuttleNet as the official baseline, to push research on forecasting future turn-based strokes within rallies. The paper documents dataset statistics, problem formulation, evaluation metrics, and challenge results, noting that improvements predominantly occur in shot-type prediction while spatial coordinate gains are more modest. Overall, ShuttleSet22 offers a practical resource to bridge badminton analytics with AI research and outlines directions for integrating multi-faceted predictions in rally forecasting.

Abstract

In recent years, badminton analytics has drawn attention due to the advancement of artificial intelligence and the efficiency of data collection. While there is a line of effective applications to improve and investigate player performance, there are only a few public badminton datasets that can be used by researchers outside the badminton domain. Existing badminton singles datasets focus on specific matchups; however, they cannot provide comprehensive studies on different players and various matchups. In this paper, we provide a badminton singles dataset, ShuttleSet22, which is collected from high-ranking matches in 2022. ShuttleSet22 consists of 30,172 strokes in 2,888 rallies in the training set, 1,400 strokes in 450 rallies in the validation set, and 2,040 strokes in 654 rallies in the testing set, with detailed stroke-level metadata within a rally. To benchmark existing work with ShuttleSet22, we hold a challenge, Track 2: Forecasting Future Turn-Based Strokes in Badminton Rallies, at CoachAI Badminton Challenge @ IJCAI 2023, to encourage researchers to tackle this real-world problem through innovative approaches and to summarize insights between the state-of-the-art baseline and improved techniques, exchanging inspiring ideas. The baseline codes and the dataset are made available at https://github.com/wywyWang/CoachAI-Projects/tree/main/CoachAI-Challenge-IJCAI2023.

Figures (2)

• Figure 1: Illustrated system of Track 2: Forecasting Future Turn-Based Strokes in Badminton Rallies.
• Figure 2: Heatmap of player and opponent locations in ShuttleSet22.