A story in the Monitor (you can read it here) talks about a UNH grad-school project to use AI to standardize the difficulty rating for rock-climbing routes.
Shaad Mahmud, an associate professor of electrical and computer engineering at UNH, started working nearly two years ago with O’Mara using emerging deep-learning model technologies to eliminate bias from rock climbing grading and the results have yielded breakthroughs for the sport. This field was largely unexplored before they started, and this research is unique as it fuses software and hardware for its assessments of difficulty.
“All the models that we have started work on either image processing or somebody manually doing it, the route method, whatever methods we have, all of them have this kind of traditional image-based or natural language processing based method. But we are building sensors that integrate the rock line, like the pinch and the jug, the sensors would be fused on it, and the machine learning will be able to make decisions based on the data that’s coming out of it,” he said.
Return to the Concord Monitor