yuanjia yang
← Research Projects

MIMIC-MJX

Neuromechanical emulation of animal behavior — massively parallel imitation learning in MuJoCo-MJX.

JAX MuJoCo pose-estimation imitation-learning biomechanics
GitHub → Live demo → arXiv →

Overview

MIMIC-MJX is a framework for neuromechanical emulation of animal behavior using massively parallel imitation learning in MuJoCo-MJX. It enables GPU-accelerated physics simulation of biomechanically realistic virtual animals that learn to reproduce naturalistic behavior from motion capture data.

The project encompasses two core tools:

Key contributions

Publication

MIMIC-MJX: Neuromechanical Emulation of Animal Behavior C.Y. Zhang*, Y. Yang*, A. Sirbu, et al. — Under Review at Nature Methods

Code