Board-to-Board: Evaluating Moonboard Grade Prediction Generalization
This provides climbers with a tool to track progress and assess routes with reduced bias, though it is incremental as it builds on existing grade prediction work.
The paper tackled the problem of predicting bouldering route grades on Moonboard datasets, achieving state-of-the-art performance with 0.87 MAE and 1.12 RMSE using methods that avoid decomposing routes into moves to reduce bias.
Bouldering is a sport where athletes aim to climb up an obstacle using a set of defined holds called a route. Typically routes are assigned a grade to inform climbers of its difficulty and allow them to more easily track their progression. However, the variation in individual climbers technical and physical attributes and many nuances of an individual route make grading a difficult and often biased task. In this work, we apply classical and deep-learning modelling techniques to the 2016, 2017 and 2019 Moonboard datasets, achieving state of the art grade prediction performance with 0.87 MAE and 1.12 RMSE. We achieve this performance on a feature-set that does not require decomposing routes into individual moves, which is a method common in literature and introduces bias. We also demonstrate the generalization capability of this model between editions and introduce a novel vision-based method of grade prediction. While the generalization performance of these techniques is below human level performance currently, we propose these methods as a basis for future work. Such a tool could be implemented in pre-existing mobile applications and would allow climbers to better track their progress and assess new routes with reduced bias.