BIGE : Biomechanics-informed GenAI for Exercise Science

Shubh Maheshwari, Anwesh Mohanty, Yadi Cao, Swithin Razu, Andrew McCulloch, Rose Yu
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:1243-1256, 2025.

Abstract

Proper movements enhance mobility, coordination, and muscle activation, which are crucial for performance, injury prevention, and overall fitness. However, traditional simulation tools rely on strong modeling assumptions, are difficult to set up and computationally expensive. On the other hand, generative AI approaches provide efficient alternatives to motion generation. But they often lack physiological relevance and do not incorporate biomechanical constraints, limiting their practical applications in sports and exercise science. To address these limitations, we propose a novel framework, BIGE, that combines bio-mechanically meaningful scoring metrics with generative modeling. BIGE integrates a differentiable surrogate model for muscle activation to reverse optimize the latent space of the generative model, enabling the retrieval of physiologically valid motions through targeted search. Through extensive experiments on squat exercise data, our framework demonstrates superior performance in generating diverse, physically plausible motions while maintaining high fidelity to clinician-defined objectives compared to existing approaches.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-maheshwari25a, title = {BIGE : Biomechanics-informed GenAI for Exercise Science}, author = {Maheshwari, Shubh and Mohanty, Anwesh and Cao, Yadi and Razu, Swithin and McCulloch, Andrew and Yu, Rose}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {1243--1256}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/maheshwari25a/maheshwari25a.pdf}, url = {https://proceedings.mlr.press/v283/maheshwari25a.html}, abstract = {Proper movements enhance mobility, coordination, and muscle activation, which are crucial for performance, injury prevention, and overall fitness. However, traditional simulation tools rely on strong modeling assumptions, are difficult to set up and computationally expensive. On the other hand, generative AI approaches provide efficient alternatives to motion generation. But they often lack physiological relevance and do not incorporate biomechanical constraints, limiting their practical applications in sports and exercise science. To address these limitations, we propose a novel framework, BIGE, that combines bio-mechanically meaningful scoring metrics with generative modeling. BIGE integrates a differentiable surrogate model for muscle activation to reverse optimize the latent space of the generative model, enabling the retrieval of physiologically valid motions through targeted search. Through extensive experiments on squat exercise data, our framework demonstrates superior performance in generating diverse, physically plausible motions while maintaining high fidelity to clinician-defined objectives compared to existing approaches.} }
Endnote
%0 Conference Paper %T BIGE : Biomechanics-informed GenAI for Exercise Science %A Shubh Maheshwari %A Anwesh Mohanty %A Yadi Cao %A Swithin Razu %A Andrew McCulloch %A Rose Yu %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-maheshwari25a %I PMLR %P 1243--1256 %U https://proceedings.mlr.press/v283/maheshwari25a.html %V 283 %X Proper movements enhance mobility, coordination, and muscle activation, which are crucial for performance, injury prevention, and overall fitness. However, traditional simulation tools rely on strong modeling assumptions, are difficult to set up and computationally expensive. On the other hand, generative AI approaches provide efficient alternatives to motion generation. But they often lack physiological relevance and do not incorporate biomechanical constraints, limiting their practical applications in sports and exercise science. To address these limitations, we propose a novel framework, BIGE, that combines bio-mechanically meaningful scoring metrics with generative modeling. BIGE integrates a differentiable surrogate model for muscle activation to reverse optimize the latent space of the generative model, enabling the retrieval of physiologically valid motions through targeted search. Through extensive experiments on squat exercise data, our framework demonstrates superior performance in generating diverse, physically plausible motions while maintaining high fidelity to clinician-defined objectives compared to existing approaches.
APA
Maheshwari, S., Mohanty, A., Cao, Y., Razu, S., McCulloch, A. & Yu, R.. (2025). BIGE : Biomechanics-informed GenAI for Exercise Science. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:1243-1256 Available from https://proceedings.mlr.press/v283/maheshwari25a.html.

Related Material