{"id":11936,"date":"2026-07-23T10:20:21","date_gmt":"2026-07-23T10:20:21","guid":{"rendered":"https:\/\/cyber-valley.de\/?post_type=news&p=11936"},"modified":"2026-08-11T11:48:26","modified_gmt":"2026-08-11T11:48:26","slug":"replicating-the-complexity-of-human-movement","status":"publish","type":"news","link":"https:\/\/cyber-valley.de\/de\/news\/replicating-the-complexity-of-human-movement\/","title":{"rendered":"Replicating the complexity of human movement"},"content":{"rendered":"\n

Daniel H\u00e4ufle, Georg Martius, and Pierre Schumacher have completed their project \u201cLearning efficient control of non-linear muscle-driven systems: Morphological computation as guiding principle\u201d. The project was funded by the Cyber\u00a0Valley Research Fund and was carried out between 2021 and 2024 at the University of T\u00fcbingen. Its aim was to test whether morphological computation can improve how computer models of the human body learn to replicate its movements.<\/p>\n\n\n\n

Morphological computation (MC) is the process by which the body moves and interacts with the world without relying on the brain to calculate the exact forces that need to be applied by each muscle and joint. For example, the brain only needs to give the simple instruction \u201cclose your hand\u201d, while low-level reflex arcs, in-built neural architectures, and muscle properties automatically coordinate the exact forces, timing, and adjustments needed to successfully perform the movement.<\/p>\n\n\n\n

The researchers first developed a new learning approach that allows computer models of the human body with many muscles to learn complex movements more effectively. They found that having many muscles makes learning harder, but by guiding the learning process more carefully, they were able to produce stable, human-like movements such as walking, even across uneven terrain. Building on this, they showed that adding simple, muscle-like properties makes movements more robust and natural, both in simulation and on real robots. Remarkably, a walking pattern learned in simulation worked on a real robot without extra training.<\/p>\n\n\n\n

The project demonstrated that morphological computation can advance computer models of the human body. The research represents the first step towards bringing the full diversity of human movement to artificial systems and robotics. With potentially broad applications across various industries, such as healthcare, rehabilitation, prosthetics, and advanced manufacturing, it aligns with Cyber\u00a0Valley\u2019s mission to translate cutting-edge research into real-world applications for a better future.<\/p>\n\n\n\n

This project produced the following peer-reviewed publications: <\/h4>\n\n\n\n