Prof. Dr. Anne Koelewijn

Chair of Machine Learning and Data Analytics Lab

It is my goal to improve movement for people, e.g. those with a disability or athlete. To do so, I aim to better understand human motion, and design better devices, such as prostheses, exoskeletons, and running shoes, as well as prevent injuries, such as knee osteoarthritis. I focus on wearable technologies and the combination of physics-based models with machine learning methods.

Research projects

Personalized musculoskeletal models and gait simulations: using imaging techniques such as diffusion tensor imaging (DTI), as well as using machine learning methods, we aim to personalize musculoskeletal models and gait simulations, such that we can per

  • Personalization of muscoskeletal models through AI (PoMMAI)

    (Third Party Funds Single)

    Term: 1. January 2021 - 31. December 2021
    Funding source: Fraunhofer-Gesellschaft
    Human movement is a complex process that depends on many factors such as body constitution, health condition, but also external factors. Joint angles, joint moments and muscle forces are variables quantifying the movement to give valuable insights about these factors. Simulation of musculoskeletal models can be used to perform detailed movement analysis to obtain these variables. The application of simulation is two-fold: Reconstruction of measured motion and prediction of new motion. Motion reconstruction can give valuable insights for example for sports analysis in marathon runners or medical gait assessment of Parkinson’s patients. Simulation can predict changes in human motion in response to environmental changes. This is beneficial to, for instance, support virtual product design of footwear or below-knee prostheses.

    However, for accurate and detailed simulations, the personalization of musculoskeletal models is crucial. Precise scaling of segment and muscle parameters can be achieved using magnetic resonance imaging (MRI) which requires time and cost consuming measurements additionally to the movement acquisition and expert knowledge. State-of-the-art methods relying only on movement recordings scale segment parameters and muscle attachment points. But they do not scale muscle parameters like maximum isometric forces.

    We will combine optimal control simulation with the application of advanced machine learning methods to personalize segment as well as muscle parameters based on marker and ground reaction force. The goal is to make personalized simulations feasible in healthcare, sports science, and industrial practice. To this end, we aim at developing an approach with three key improvements: First, it can be applied without additional and time-consuming measurements using expensive modalities; Secondly, it can be used without expert knowledge but operates automatically; Thirdly, it is feasible with limited computational re-sources, i.e., computational power and time.

  • Biomechanical Assessment and Simulation

    (Third Party Funds Single)

    Term: 1. August 2019 - 1. August 2022
    Funding source: Industrie

    The goal of this project is to develop data-based and knowledge-based methods for accurate analysis and simulation of human motion, focused on gait. Movement simulations are created by solving trajectory optimization problems, using an objective related to energy, a musculoskeletal model to model the body and muscle dynamics, and constraints to define the movement task. We use data-based approaches to improve musculoskeletal models and simulation accuracy. With our research, we aim to better understand human motion, and thereby improve design of wearables, such as prostheses, exoskeletons, and running shoes.


  • Koelewijn, A., & Selinger, J.C. (2022). Predictive Gait Simulations of Human Energy Optimization. In Juan C. Moreno, Jawad Masood, Urs Schneider, Christophe Maufroy, Jose L. Pons (Eds.), Wearable Robotics: Challenges and Trends. (pp. 377-381). Cham: Springer Science and Business Media Deutschland GmbH.



Related Research Fields