Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics
This work addresses the challenge of understanding embodied motor control for neuroscience, though it is incremental as it builds on existing simulation and imitation learning methods.
The researchers tackled the problem of modeling sensorimotor control by developing an imitation learning pipeline to replicate mouse forelimb reaching movements in a biomechanical simulation, finding that adding naturalistic energy and velocity constraints improved predictions of real EMG signals.
The brain has evolved to effectively control the body, and in order to understand the relationship we need to model the sensorimotor transformations underlying embodied control. As part of a coordinated effort, we are developing a general-purpose platform for behavior-driven simulation modeling high fidelity behavioral dynamics, biomechanics, and neural circuit architectures underlying embodied control. We present a pipeline for taking kinematics data from the neuroscience lab and creating a pipeline for recapitulating those natural movements in a biomechanical model. We implement a imitation learning framework to perform a dexterous forelimb reaching task with a musculoskeletal model in a simulated physics environment. The mouse arm model is currently training at faster than 1 million training steps per second due to GPU acceleration with JAX and Mujoco-MJX. We present results that indicate that adding naturalistic constraints on energy and velocity lead to simulated musculoskeletal activity that better predict real EMG signals. This work provides evidence to suggest that energy and control constraints are critical to modeling musculoskeletal motor control.