Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics

TL;DR

This paper introduces a high-speed, GPU-accelerated imitation learning framework for simulating mouse forelimb reaching dynamics, demonstrating the importance of energy and velocity constraints for realistic musculoskeletal motor control modeling.

Contribution

It presents a scalable, parallel imitation learning pipeline for biomechanical modeling of mouse limb movements, integrating naturalistic constraints to improve biological accuracy.

Findings

Faster than 1 million training steps per second due to GPU acceleration.

Adding energy and velocity constraints improves EMG signal prediction.

The framework advances understanding of embodied motor control mechanisms.

Abstract

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.