Using Machine Learning for move sequence visualization and generation in climbing

2025/03/01 by Thomas Rimbot, Martin Jaggi, Rimbot, Thomas +3
Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Winter Sports Injuries and Performance

paper · pdf · doi:10.48550/arxiv.2503.00458

openalex publication_date 2025/03/01 · openalex created_date 2025/10/12 · openalex updated_date 2026/07/28

Abstract

In this work, we investigate the application of Machine Learning techniques to sport climbing. Expanding upon previous projects, we develop a visualization tool for move sequence evaluation on a given boulder. Then, we look into move sequence prediction from simple holds sequence information using three different Transformer models. While the results are not conclusive, they are a first step in this kind of approach and lay the ground for future work.

Related

• Recurrent Neural Network for MoonBoard Climbing Route Classification and Generation
• The Way Up: A Dataset for Hold Usage Detection in Sport Climbing
• Board-to-Board: Evaluating Moonboard Grade Prediction Generalization
• Automatic sensor-based detection and classification of climbing activities
• Producing a Standard Dataset of Speed Climbing Training Videos Using Deep Learning Techniques