Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 9, 2026

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice
06:04

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice

Published on: March 4, 2014

22.0K

Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics.

Eric Leonardis1, Akira Nagamori1, Ayesha Thanawalla1

  • 1Salk Institute for Biological Studies, La Jolla, CA 92037.

Arxiv
|December 8, 2025
PubMed
Summary

This study models embodied control by simulating natural movements using physics and imitation learning. Adding naturalistic constraints to simulations improves muscle activity prediction, highlighting their importance in biological movement control.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Intravenous Low-dose Buprenorphine for Acute Pain Management in the Emergency Department: A Case Series.

Clinical practice and cases in emergency medicine·2026
Same author

Adaptive Charge Modulation Enables Focal, Selective Spinal Cord Stimulation.

bioRxiv : the preprint server for biology·2026
Same author

Quantitative MRI Assessment of Myotoxin-Induced Skeletal Muscle Damage of mdx Mice.

Muscle & nerve·2026
Same author

Directed differentiation of functional corticospinal-like neurons from endogenous SOX6+/NG2+ cortical progenitors.

eLife·2026
Same author

MIMIC-MJX: Neuromechanical Emulation of Animal Behavior.

ArXiv·2025
Same author

The antiviral Interferon pathway drives astrocyte aging and motor decline.

bioRxiv : the preprint server for biology·2025

Area of Science:

  • Neuroscience
  • Robotics
  • Computational Biology

Background:

  • Understanding embodied control requires modeling sensorimotor transformations.
  • Developing data-driven simulation platforms for high-fidelity behavioral dynamics, biomechanics, and neural circuits is crucial.

Purpose of the Study:

  • To create a pipeline for simulating natural movements from neuroscience kinematics data.
  • To implement an imitation learning framework for a dexterous forelimb reaching task.

Main Methods:

  • Utilized a musculoskeletal model in the Mujoco physics environment.
  • Employed an imitation learning framework accelerated by JAX and Mujoco-MJX for rapid training.
  • Integrated naturalistic control magnitude constraints into the simulation.

More Related Videos

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.9K
Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

9.1K

Related Experiment Videos

Last Updated: Jan 9, 2026

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice
06:04

Study Motor Skill Learning by Single-pellet Reaching Tasks in Mice

Published on: March 4, 2014

22.0K
Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories
07:52

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

14.9K
Investigating Motor Skill Learning Processes with a Robotic Manipulandum
07:52

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

9.1K

Main Results:

  • Achieved over 1 million training steps per second through GPU acceleration.
  • Simulated muscle activity with naturalistic constraints more accurately predicted real EMG signals.
  • Demonstrated the critical role of control constraints in biological movement modeling.

Conclusions:

  • Control constraints are essential for accurately modeling biological movement.
  • The developed platform and methods advance the simulation of embodied control.
  • This research bridges neuroscience data with physics-based simulations for deeper insights into motor control.