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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

A "three-in-one" nose-to-brain delivery strategy: intranasal vancomycin spray achieves simultaneous clearance of pneumococcal colonization, bacteremia, and meningitis.

International journal of pharmaceutics·2026
Same author

Immune-related adverse events with cancer clinical benefits: a systematic review and meta-analysis.

BMC cancer·2026
Same author

CLPTM1L modulates membrane lipid rafts to promote tumor EGFR signaling.

Life metabolism·2026
Same author

Organic Photovoltaic Cells for Reliable Energy Generation in Deep Space Environments.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Dual-responsive ionic liquid based foam-to-gel for precision vaginal delivery of progesterone.

Acta biomaterialia·2026
Same author

LKB1 inactivation elicits an NNMT-mediated methyl sink and confers dependence on PRMT5 in lung cancer.

Cell reports·2026

Related Experiment Video

Updated: Jun 14, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K

RL-CWtrans Net: multimodal swimming coaching driven via robot vision.

Guanlin Wang1

  • 1Faculty of Education, University of Macau, Macau, Macau SAR, China.

Frontiers in Neurorobotics
|August 29, 2024
PubMed
Summary

This study introduces RL-CWtrans Net, a robot vision system for swimming. It uses AI to analyze swimmer movements and provide real-time, personalized coaching for improved technique and performance.

Keywords:
Swin-Transformerartificial neural networksclipfeature extractionmultimodal robotreinforcement learningrobot vision

More Related Videos

Preparation and 3D Tracking of Catalytic Swimming Devices
06:50

Preparation and 3D Tracking of Catalytic Swimming Devices

Published on: July 1, 2016

7.6K
Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy
13:44

Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy

Published on: August 8, 2011

13.8K

Related Experiment Videos

Last Updated: Jun 14, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K
Preparation and 3D Tracking of Catalytic Swimming Devices
06:50

Preparation and 3D Tracking of Catalytic Swimming Devices

Published on: July 1, 2016

7.6K
Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy
13:44

Haptic/Graphic Rehabilitation: Integrating a Robot into a Virtual Environment Library and Applying it to Stroke Therapy

Published on: August 8, 2011

13.8K

Area of Science:

  • Sports Science
  • Robotics
  • Artificial Intelligence

Background:

  • Effective swimming coaching relies on precise analysis of athlete posture and technique.
  • Traditional methods lack real-time feedback capabilities, hindering performance improvement.
  • There is a need for advanced systems to enhance swimming training effectiveness.

Purpose of the Study:

  • To develop a robot vision-driven multimodal swimming training system for real-time guidance.
  • To integrate computer vision and natural language processing for comprehensive athlete analysis.
  • To leverage reinforcement learning for personalized coaching feedback.

Main Methods:

  • Utilized Swin-Transformer for extracting swimmer motion and posture features.
  • Employed CLIP model for understanding natural language swimming instructions.
  • Integrated visual and textual data for enhanced information representation.
  • Applied reinforcement learning to train an intelligent agent for personalized feedback.

Main Results:

  • Demonstrated significant advancements in the accuracy and practicality of the multimodal robot coaching system.
  • The system effectively captures real-time movements and provides immediate, personalized feedback.
  • Experimental results confirm enhanced effectiveness in swimming instruction.

Conclusions:

  • RL-CWtrans Net offers a promising technological solution for real-time swimming coaching.
  • The multimodal approach enhances the precision and personalization of athletic training.
  • This system has the potential to revolutionize swimming performance analysis and improvement.