Tsinghua University

Learning & Neural Systems Group
Learning &
Neural Systems Group

Research Topics

We work on neuro-musculo-skeletal modeling and reinforcement learning for human motion control and interactive robotics.


Related areas

AI for Health, Machine Learning, Neural Engineering, Robotics


Neuro-Musculo-Skeletal Modeling

MS-Human-700

A whole-body human musculoskeletal model with 700 muscle-tendon units.

Learning to Move

Optimistic Local Latent Safe Optimization

A Optimistic Local Latent Safe Optimization method for online safe optimization over high-dimensional spaces, which efficiently optimizes the high-dimensional function while enjoying theoretical probabilistic safety guarantee.

Two Stages Hierarchical Training

A hierarchical reinforcement learning algorithm for high-dimensional full-body human musculoskeletal model control.

Interactive Robotics

Preference-based Learning

A personalized gait optimization framework for lower-body exoskeleton.

Human-machine Interaction

Based on the existing model, build a full-body human musculoskeletal model. This model can interact with other machines, such as Exoskeleton, Cruth, and so on.

Wheeled-legged Quadruped

Learning adaptive locomotion for wheeled-legged quadrupeds.