Publication
Learning Human Gait with Muscle Control and Metabolic Cost Integration
Nadine Drewing; Firas Al-Hafez; Guoping Zhao; Jan Peters; André Seyfarth; Rolf Findeisen; Maziar Ahmad Sharbafi
In: American Control Conference, ACC 2026, New Orleans, LA, USA, May 26-29, 2026. American Control Conference (ACC), Pages 3565-3570, IEEE, 2026.
Abstract
Human locomotion involves complex coordination
of over-actuated muscle systems and joints, making simulation
and control design highly challenging. While recent reinforce-
ment and imitation learning methods can replicate human-like
kinematics, they often fail to produce physiologically realistic
force patterns, largely due to the limited availability and
consideration of reference force plate or electromyography
(EMG) data. This paper presents a hybrid imitation learning
framework that integrates muscle-driven simulations with rein-
forcement learning to address over-actuation and to account for
the fact that the available data reflects closed-loop actions in-
volving muscle control. A key contribution is the incorporation
of metabolic cost into the reward function, shaping energetically
efficient and physiologically plausible controllers. Simulation
results demonstrate that the learned policies generate muscle
activations and ground reaction forces that align more closely
with OpenSim references and experimental data than standard
imitation learning. The method provides a scalable tool for
developing and validating closed-loop control strategies for
assistive systems such as exoskeletons and prostheses, while
highlighting broader implications for learning-based control of
over-actuated biomechanical systems.