BoxMind: Closed-loop AI strategy optimization for elite boxing validated in the 2024 Olympics
By: Kaiwen Wang, Kaili Zheng, Rongrong Deng, Qingmin Fan, Milin Zhang, Zongrui Li, Xuesi Zhou, Bo Han, Liren Chen, Chenyi Guo, Ji Wu
Published: 2026-01-16
View on arXiv →#cs.AI
Abstract
This paper introduces BoxMind, a closed-loop AI expert system for optimizing boxing strategies. It uses multi-modal data to define atomic punch events and proposes a graph-based predictive model to capture boxer dynamics. Validated in the 2024 Paris Olympics, BoxMind generated strategic recommendations comparable to human experts, contributing to the Chinese National Team's success. It offers a paradigm for transforming unstructured video data into strategic intelligence for competitive sports.