Host: The Japanese Society for Artificial Intelligence
Name : The 39th Annual Conference of the Japanese Society for Artificial Intelligence
Number : 39
Location : [in Japanese]
Date : May 27, 2025 - May 30, 2025
Sport climbing, which gained attention with the Tokyo Olympics, is a discipline that requires complex decision-making and movement patterns. The continuity and transitions of a climber's movements are influenced by route design and individual skills, but methods to systematically analyze these aspects have not been well established. In this study, we propose a new framework called the "Climbing Transition Network (CTN)" that represents the climber's trajectory as a directed network, aiming to visualize movement patterns and evaluate the complexity of routes. Analysis of 24 performance data from speed climbing in the 2018 World Cup revealed that climbers' movement patterns were highly varied, with significant variation in the number of smearing and lunging actions, as well as the number of holds used. Additionally, the number of holds caught with the hands, rather than the feet, showed a stronger correlation with climbing time.