Team Intro to AI team8 at CoachAI Badminton Challenge 2023: Advanced ShuttleNet for Shot Predictions

TL;DR

This paper presents an improved version of ShuttleNet for badminton shot prediction, leveraging past strokes, which led to winning the CoachAI Badminton Challenge at IJCAI 2023.

Contribution

The paper introduces an enhanced ShuttleNet model that outperforms the baseline in predicting badminton shots, demonstrating state-of-the-art results in a competitive setting.

Findings

Achieved first place in the CoachAI Badminton Challenge 2023.

Significantly improved shot prediction accuracy over baseline.

Made code publicly available for reproducibility.

Abstract

In this paper, our objective is to improve the performance of the existing framework ShuttleNet in predicting badminton shot types and locations by leveraging past strokes. We participated in the CoachAI Badminton Challenge at IJCAI 2023 and achieved significantly better results compared to the baseline. Ultimately, our team achieved the first position in the competition and we made our code available.