BIGE is a framework for generative fashions to stick to clinician-defined constraints. To generate sensible movement, our methodology makes use of a biomechanically knowledgeable surrogate mannequin to information the technology course of. Credit score: College of California – San Diego
Researchers on the College of California San Diego have created a mannequin pushed by generative AI that can assist forestall accidents in athletes and likewise support in rehabilitation after an harm. The mannequin may additionally assist athletes prepare higher.
The mannequin, referred to as BIGE (for Biomechanics-informed GenAI for Train Science), was skilled with athlete actions along with details about the biomechanical constraints on the human physique, equivalent to how a lot drive a muscle can develop. The mannequin can generate movies of motions that athletes can mimic to keep away from harm after they prepare. It may well additionally generate motions that athletes can execute to maintain exercising when they’re injured.
It may be used to generate the most effective motions athletes can execute throughout train to keep away from harm and enhance efficiency, or the most effective motions for athletes that want rehabilitation after an harm.
“This approach is going to be the future,” predicts Andrew McCulloch, distinguished professor within the Shu Chien-Gene Lay Division of Bioengineering at UC San Diego and one of many paper’s senior authors.
To the most effective of the researchers’ information, BIGE is the one mannequin that brings collectively generative AI and sensible biomechanics. Most generative AI fashions tasked with producing actions equivalent to squats produce outcomes that aren’t in line with the anatomical and mechanical constraints that restrict actual human actions. In the meantime, strategies that don’t depend on generative AI to generate these actions require a prohibitive quantity of computation.
Comparability of generated samples from baseline fashions and BIGE. The yellow curve represents the motion of the hip joint over all the squat cycle. BIGE generates a extra sensible squat movement in comparison with different fashions. Credit score: College of California San Diego
To coach the mannequin, researchers used information from motion-capture movies of individuals performing squats. They then translated the motions onto 3D-skeletal fashions and used the computed forces to generate extra bodily sensible motions.
Subsequent steps embody utilizing the mannequin for actions past squats and personalizing the fashions for particular people.
“This methodology could be used by anyone,” mentioned Rose Yu, a professor within the UC San Diego Division of Laptop Science and Engineering and one of many paper’s senior authors as properly.
For instance, the mannequin could possibly be used to find out fall dangers within the aged.
The analysis staff just lately offered their work on the Studying for Dynamics & Management Convention on the College of Michigan, in Ann Arbor, Michigan.
Extra data:
BIGE : Biomechanics-informed GenAI for Train Science, rose-stl-lab.github.io/UCSD-Op … Cap-Health-Dataset/
Offered by
College of California – San Diego
Quotation:
Generative AI might help athletes keep away from accidents (2025, October 27)
retrieved 27 October 2025
from https://medicalxpress.com/information/2025-10-generative-ai-athletes-injuries.html
This doc is topic to copyright. Aside from any truthful dealing for the aim of personal research or analysis, no
half could also be reproduced with out the written permission. The content material is supplied for data functions solely.
