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 for 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 test the state-of-the-art stroke forecasting approach, ShuttleNet, with the corresponding stroke forecasting task, i.e., predict the future strokes based on the given strokes of each rally. We also hold a challenge, Track 2: Forecasting Future Turn-Based Strokes in Badminton Rallies, at CoachAI Badminton Challenge 2023 to boost researchers to tackle this problem. The baseline codes and the dataset will be made available on https://github.com/wywyWang/CoachAI-Projects/tree/main/CoachAI-Challenge-IJCAI2023.

翻译：近年来，随着人工智能技术的发展与数据采集效率的提升，羽毛球运动分析引起了广泛关注。虽然已有诸多有效应用用于提升和研究球员表现，但可供非羽毛球领域研究人员使用的公开羽毛球数据集仍然稀少。现有的羽毛球单打数据集集中于特定对阵组合，无法支持对不同球员及多样化对阵的全面研究。本文提出了一个羽毛球单打数据集ShuttleSet22，其数据来源于2022年顶级赛事。该数据集包含训练集（30,172次击球，2,888个回合）、验证集（1,400次击球，450个回合）和测试集（2,040次击球，654个回合），并提供了详细的逐拍级回合元数据。为在ShuttleSet22上建立现有工作的基准，我们采用最新的击球预测方法ShuttleNet，执行对应的击球预测任务（即根据每个回合的已知击球序列预测后续击球）。此外，我们在2023年CoachAI羽毛球挑战赛中设立了第二赛道"羽毛球回合中逐拍交替击球预测"，旨在激励研究者攻克该问题。基准代码与数据集将在https://github.com/wywyWang/CoachAI-Projects/tree/main/CoachAI-Challenge-IJCAI2023 开源提供。