How Is the Stroke? Inferring Shot Influence in Badminton Matches via Long Short-term Dependencies

Abstract

Identifying significant shots in a rally is important for evaluating players’ performance in badminton matches. While there are several studies that have quantified player performance in other sports, analyzing badminton data has remained untouched. In this article, we introduce a badminton language to fully describe the process of the shot, and propose a deep learning model composed of a novel short-term extractor and a long-term encoder for capturing a shot-by-shot sequence in a badminton rally by framing the problem as predicting a rally result. Our model incorporates an attention mechanism to enable the transparency between the action sequence and the rally result, which is essential for badminton experts to gain interpretable predictions. Experimental evaluation based on a real-world dataset demonstrates that our proposed model outperforms the strong baselines. We also conducted case studies to show the ability to enhance players’ decision-making confidence and to provide advanced insights for coaching, which benefits the badminton analysis community and bridges the gap between the field of badminton and computer science.

ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis

“…4) The shot type of the hitting stroke, where the shot type is selected from one of the 18 types: net shot, return net, smash, wrist smash, lob, defensive return lob, clear, drive, driven flight, back-court drive, drop, passive drop, push, rush, defensive return drive, crosscourt net shot, short service, and long service. The detailed explanations of each type are introduced in [42].…”

“…In this section, we present 3 application scenarios related to the performance on ShuttleSet, including measuring the win probability of each stroke in a rally (shot influence [41,42], Section 5.1), forecasting the future strokes (stroke forecasting [43], Section 5.2) and the movements of both players (movement forecasting [3], Section 5.3) given the previous strokes. Following their evaluation settings for data separation and evaluation metrics, the shot influence task formulates the task as predicting the final outcome of a rally and adopts the latest 10 matches as the test set and the remaining for the train set to evaluate model effectiveness for inferring the win probability of each stroke in the unseen matches.…”

“…Wang et al [41,42] introduces the shot influence task by framing as predicting which player wins the rally by giving the stroke-level information (e.g., shot type, player location, if returning around the head), which can be used to measure the quality of each shot in a rally for enhancing players' decision-making confidence. Generally, the state-of-the-art model is ShuttleScorer [42], which consists of a shot encoder for encoding stroke-level information with various timestamps, a pattern extractor for considering short-term patterns alternatively, and a rally encoder with a Transformer encoder [39]. We also implemented a bi-directional gated recurrent unit (Bi-GRU) [5], Prototype Sequence Network (ProSeNet) [28], DeepMoji [11], Ordered neurons LSTM (ON-LSTM) [35], Transformer [39], Reformer [26], and TokenLearner [32] as the baselines for comparison.…”

“…In this paper, we present the ShuttleSet dataset annotated by domain experts with the efficient and precise S 2 -labeling tool [17] using the BLSR format [42]. Based on the labeling tool, ShuttleSet provides stroke-by-stroke human annotation ground truth records for 44 matches from 2018 to 2021 with 27 high-ranking players (16 men's singles and 11 women's singles), which consist of 104 sets, 3,685 rallies, and 36,492 strokes.…”

The CoachAI Badminton Environment: Bridging the Gap between a Reinforcement Learning Environment and Real-World Badminton Games

“…The rising interest in sports analytics has triggered a surge in research (Kao et al 2022;Wang et al 2022b), with a focus on leveraging reinforcement learning to enhance player strategies (Won, Gopinath, and Hodgins 2021;Chen et al 2023). Simulation environments with automatic opponents are critical to swiftly evaluate the designed algorithms; however, previous efforts mainly centered on physics-based interactions or simple rule-based opponents, e.g., Brockman et al (2016); Kurach et al (2020).…”