Self Model for Embodied Intelligence: Modeling Full-Body Human Musculoskeletal System and Locomotion Control with Hierarchical Low-Dimensional Representation
This work addresses a critical problem in robotics and biomechanics for researchers and developers by enabling more accurate human movement simulation and control, though it is incremental in improving upon existing limited models.
The paper tackles the challenge of modeling and controlling the full human musculoskeletal system, which previously lacked comprehensive models and control algorithms for over 600 muscles, by introducing MS-Human-700 with 90 segments, 206 joints, and 700 muscle-tendon units, achieving state-of-the-art full-body control validated with real human locomotion data.
Modeling and control of the human musculoskeletal system is important for understanding human motor functions, developing embodied intelligence, and optimizing human-robot interaction systems. However, current human musculoskeletal models are restricted to a limited range of body parts and often with a reduced number of muscles. There is also a lack of algorithms capable of controlling over 600 muscles to generate reasonable human movements. To fill this gap, we build a musculoskeletal model (MS-Human-700) with 90 body segments, 206 joints, and 700 muscle-tendon units, allowing simulation of full-body dynamics and interaction with various devices. We develop a new algorithm using low-dimensional representation and hierarchical deep reinforcement learning to achieve state-of-the-art full-body control. We validate the effectiveness of our model and algorithm in simulations with real human locomotion data. The musculoskeletal model, along with its control algorithm, will be made available to the research community to promote a deeper understanding of human motion control and better design of interactive robots. Project page: https://lnsgroup.cc/research/MS-Human-700