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

Spinal Cord Model

Use clinical data to build personalized spinal cord model.

Spinal Cord Model

Use clinical data to build personalized spinal cord model.

Musculoskeletal Model

Based on the existing model, build a full-body human musculoskeletal model.

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.