Development of Kinematic Model of the Knee in Omniverse

11.03.2025, Abschlussarbeiten, Bachelor- und Masterarbeiten

The Human-Centered Computing and Extended Reality Lab of the Professorship for Machine Intelligence in Orthopedics seeks applicants for Bachelor/Master Thesis for the Summer Semester 2025.

Abstract

This project aims to develop a scalable digital twin of the human knee for robotic training purposes in Omniverse. The resulting model will be used to train actuation methods for wearable robotics and interactive robotics.

Project Description

The objective of this student thesis is to develop a kinematic model of the human knee that can serve as a digital twin for robotic training purposes. To fit all possible patients, the model must be adaptable to certain conditions and scalable without losing its kinematic accuracy. The model needs to be created in Isaac Sim (part of Omniverse). In the end, the digital twin needs to be able to act as a robotic agent which can be controlled in Isaac Sim.
In case of this project is handed out as a master thesis, the project’s scale will increase appropriately.
Key research areas include:

• Creation of accurate digital twins of human joints
• Development within simulations environments for robotic learning

Technical Prerequisites

• Experience with simulation tools like Mujoco and ideally Omniverse/Isaac Sim
• Experience with Python and C/C++
• Experience with game engines helpful
• Experience or a willingness to learn about the kinematics of human joints

Please send your transcript of records, CV and motivation to: Victor Schaack (vic.schaack@tum.de) with CC to hex-thesis.ortho@mh.tum.de

Literatur
Ahmed, N., Afyouni, I., Dabool, H., & Al Aghbari, Z. (2024). A systemic survey of the Omniverse platform and its applications in data generation, simulation and metaverse. Frontiers in Computer Science, 6. https://doi.org/10.3389/fcomp.2024.1423129
Quinn, A. R. J., Saxby, D. J., Yang, F., de Sousa, A. C. C., & Pizzolato, C. (2023). A digital twin framework for robust control of robotic-biological systems. In Journal of Biomechanics (Vol. 152, p. 111557). Elsevier BV. https://doi.org/10.1016/j.jbiomech.2023.111557
Smith, P. N., Refshauge, K. M., & Scarvell, J. M. (2003). Development of the concepts of knee kinematics11No commercial party having a direct financial interest in the results of the research supporting this article has or will confer a benefit upon the author(s) or upon any organization with which the author(s) is/are associated. In Archives of Physical Medicine and Rehabilitation (Vol. 84, Issue 12, pp. 1895–1902). Elsevier BV. https://doi.org/10.1016/s0003-9993(03)00281-8
Schache, A. G., Baker, R., & Lamoreux, L. W. (2006). Defining the knee joint flexion–extension axis for purposes of quantitative gait analysis: An evaluation of methods. In Gait & Posture (Vol. 24, Issue 1, pp. 100–109). Elsevier BV. https://doi.org/10.1016/j.gaitpost.2005.08.002
(Byrnes, S. K., Holder, J., Stief, F., Wearing, S., Böhm, H., Dussa, C. U., & Horstmann, T. (2022). Frontal plane knee moment in clinical gait analysis: A systematic review on the effect of kinematic gait changes. In Gait & Posture (Vol. 98, pp. 39–48). Elsevier BV. https://doi.org/10.1016/j.gaitpost.2022.07.258)

Possible Resources:
https://developer.nvidia.com/isaac/sim
https://developer.nvidia.com/isaac/lab
https://docs.isaacsim.omniverse.nvidia.com/latest/index.html
https://developer.nvidia.com/blog/building-a-synthetic-motion-generation-pipeline-for-humanoid-robot-learning/
https://docs.omniverse.nvidia.com/isaacsim/latest/features/warehouse_logistics/ext_omni_anim_people.html

Kontakt: hex-thesis.ortho@mh.tum.de, vic.schaack@tum.de