MS-Human-700

Whole-body Human MusculoSkeletal Modeling and Control

Paper Model Code Video

Project Overview

The MS-Human-700 project encompasses a comprehensive series of research initiatives focused on advancing human musculoskeletal modeling and control. By integrating high-fidelity physiological simulations with cutting-edge reinforcement learning and control theory, this project addresses fundamental challenges in embodied intelligence, biomechatronics, and human-robot interaction.

Our research is structured around several key pillars, providing a holistic framework for digital human simulation:

  • Musculoskeletal Modeling: MS-Human-700 establishes the foundation with a full-body model featuring 90 segments, 206 joints, and 700 muscles.
  • Efficient Learning: DynSyn leverages dynamical synergies to enable efficient policy learning in high-dimensional, overactuated systems.
  • Model-Based Control: MPC2 implements hierarchical model predictive control for robust, zero-shot motion planning and execution.
  • Contact Modeling: SoftFoot integrates deformable contact dynamics to enhance the physiological realism of locomotion interactions.
  • Scalable Exploration: QFlex utilizes value-guided flow to solve exploration challenges in high-dimensional continuous control spaces.
  • Embodied VLM Learning: MoVLR explores vision-language model guidance for intuitive musculoskeletal control and reward specification.

Model Architecture

The MS-Human-700 model represents a whole-body human musculoskeletal system, featuring:

  • 90 body segments
  • 206 joints
  • 700 muscle-tendon units
  • Anatomically plausible parameters
  • MuJoCo integration

The model enables simulation of full-body dynamics and interaction with various devices, making it suitable for research in embodied intelligence, robotics, and biomechanics.

MS-Human-700 Model Visualization

Demonstration

Video Presentation

DynSyn Control Results

The MS-Human-700 model controlled by the DynSyn algorithm demonstrates remarkable capabilities in both locomotion and manipulation tasks.

Locomotion Control

MS-Human-700 Locomotion Control with DynSyn

Manipulation Control

MS-Human-700 Manipulation Control with DynSyn

MPC2 Control Results

The MS-Human-700 model controlled by the MPC2 algorithm demonstrates strong generalization to model changes and perturbations.

Soccer Motion Control

Adaptation Control to Model Changes

Adaptation to Sudden Perturbation

QFlex Control Results

The MS-Human-700 model controlled by the QFlex algorithm demonstrates scalable exploration and agile whole-body control in high-dimensional settings.

Whole-body Running

MS-Human-700 running control with QFlex

Ballet Motion Control

MS-Human-700 ballet control with QFlex

High-Fidelity Motion Tracking

Leveraging MuJoCo Warp for massively parallel GPU simulation enables rapid and efficient training of control policies for high-precision motion tracking across diverse and dynamic trajectories.

The demos below illustrate tracking capabilities in two render modes:
Overlap (model and reference trajectory rendered together) and Separate (offset rendering for detailed motion comparison).

Running - Overlap

Running - Overlap

Running - Separate

Running - Separate

Walking - Overlap

Walking - Overlap

Walking - Separate

Walking - Separate

Research Papers

Self Model for Embodied Intelligence: Modeling Full-Body Human Musculoskeletal System and Locomotion Control with Hierarchical Low-Dimensional Representation

IEEE International Conference on Robotics and Automation (ICRA) 2024

This fundamental work introduces the MS-Human-700 model, a high-fidelity musculoskeletal system featuring 90 body segments, 206 joints, and 700 muscle-tendon units. It proposes a novel hierarchical deep reinforcement learning framework that leverages low-dimensional representations to achieve robust full-body control.

Key Contributions:

  • Full-body human musculoskeletal model with 700+ muscles for simulation.
  • A hierarchical control algorithm designed to manage high-dimensional muscle coordination.
  • Validation with real-world human locomotion data.
Project Page Code arXiv

DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems

International Conference on Machine Learning (ICML) 2024

Addressing the complexity of high-dimensional, overactuated systems, DynSyn introduces dynamical synergistic representations. Drawing inspiration from biological muscle synergies, this research demonstrates how to extract synergistic structures from dynamics to enable efficient learning and task-specific adaptation.

Key Contributions:

  • Novel dynamical synergistic representation for sample-efficient learning.
  • Enhanced robustness and interpretability of synergistic control policies.
  • Demonstrated generalizability across a diverse range of motor tasks.
Project Page Code arXiv

Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning

International Conference on Learning Representations (ICLR) 2025

MPC2 presents a hierarchical model-based learning algorithm enabling zero-shot, near-real-time control for complex high-dimensional systems. Just like biological motor control, it integrates sampling-based model predictive control with mechanism-aware proportional control to ensure robust actuator coordination.

Key Contributions:

  • Hierarchical model-based framework optimized for high-dimensional control.
  • Zero-shot generalization and near-real-time performance capabilities.
  • Morphology-aware proportional controller for stable and robust coordination.
  • Automated optimization reducing the dependency on manual reward engineering.
Project Page Code (Coming Soon) arXiv

Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow

International Conference on Learning Representations (ICLR) 2026

QFlex proposes a value-guided probability flow to sustain effective directed exploration in high-dimensional continuous control. It enhances scalability while preserving flexibility in native action spaces, demonstrating superior performance on complex musculoskeletal control tasks.

Key Contributions:

  • Value-guided flow exploration mechanism for high-dimensional continuous control.
  • Theoretically grounded directed exploration ensuring valid policy improvement.
  • Flow matching-based actor-critic implementation.
  • Extensive validation on over-actuated musculoskeletal benchmarks and full-body control.
Project Page Code (Coming Soon) arXiv

Embodied Learning of Reward for Musculoskeletal Control with Vision Language Models

Learning for Dynamics & Control Conference (L4DC) 2026

MoVLR investigates the intersection of embodied intelligence and large vision-language models for musculoskeletal control. By utilizing the semantic understanding capabilities of VLMs, this work enables the learning of reward functions directly from visual observations, facilitating more intuitive and generalized control policy learning.

Key Contributions:

  • Framework for deriving reward signals from Vision Language Models for complex control tasks.
  • Enhanced generalization across different embodiments and task specifications.
  • Demonstration of effective policy learning using VLM-guided rewards in high-dimensional spaces.
Project Page Code (Coming Soon) arXiv
×

Citation