Using Machine Learning for move sequence visualization and generation in climbing
This work addresses the specific problem of move sequence analysis in sport climbing for climbers and coaches, but it is incremental as it builds on previous projects and lacks conclusive outcomes.
The paper tackled the problem of analyzing and generating climbing move sequences by developing a visualization tool for evaluation and using Transformer models for prediction from holds sequences, but the results were inconclusive and preliminary.
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.