Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Aug 1, 2025

Designing and Implementing Nervous System Simulations on LEGO Robots

Designing and Implementing Nervous System Simulations on LEGO Robots

Published on: May 25, 2013

A Survey on Reinforcement Learning Methods in Bionic Underwater Robots.

Ru Tong^1,2, Yukai Feng^1,2, Jian Wang^1,2

¹State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.

Biomimetics (Basel, Switzerland)

|April 24, 2023

Summary

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

Flexible artificial lateral line based on luminous flux for underwater velocity vector estimation.

National science review·2026

Same author

Evaluation of nucleic acid-based matrix-assisted laser desorption/ionization time-of-flight mass spectrometry for rapid identification of <i>Mycobacterium tuberculosis</i> and drug resistance in patients with retreatment tuberculosis.

Frontiers in microbiology·2026

Same author

Retrospective non-target screening reveals the occurrence and environmental risk of pharmaceutical transformation products in the Pearl River Basin.

Environment international·2026

Same author

Cell crowding initiates tumor invasion by triggering a nanoscale topography transition of plasma membranes.

Acta biomaterialia·2026

Same author

"Double-hit" precipitates fulminant cardiac dysfunction in a child with homozygous CAP2 variant: a case report.

Frontiers in cardiovascular medicine·2026

Same author

Non-Parametric Kinematic Optimization of Flapping Foil Propulsion Using a Discrete Adjoint Method.

Biomimetics (Basel, Switzerland)·2026

This summary is machine-generated.

Reinforcement learning enhances bionic underwater robot capabilities for complex tasks. This survey details current methods, challenges, and future directions for intelligent underwater robotics.

Area of Science:

Robotics
Artificial Intelligence
Marine Engineering

Background:

Bionic robots offer unique advantages for underwater exploration and operations.
Advancements in motion control and intelligent decision-making are expanding their capabilities.
Reinforcement learning (RL) is increasingly applied to bionic underwater robots.

Purpose of the Study:

To provide a comprehensive survey of reinforcement learning applications in bionic underwater robots.
To classify RL methods and discuss their suitability for control and decision-making tasks.
To identify challenges and future research directions in this domain.

Main Methods:

Classification of existing reinforcement learning algorithms for bionic underwater robots.
Review of RL algorithms from the perspective of control and decision-making tasks.

Keywords:

bionic underwater robot intelligent control reinforcement learning robotic fish

More Related Videos

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

A Robotic Platform to Study the Foreflipper of the California Sea Lion

A Robotic Platform to Study the Foreflipper of the California Sea Lion

Published on: January 10, 2017

Related Experiment Videos

Last Updated: Aug 1, 2025

Designing and Implementing Nervous System Simulations on LEGO Robots

Designing and Implementing Nervous System Simulations on LEGO Robots

Published on: May 25, 2013

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

A Robotic Platform to Study the Foreflipper of the California Sea Lion

A Robotic Platform to Study the Foreflipper of the California Sea Lion

Published on: January 10, 2017

Exploration of training and deployment solutions, considering environmental and robot-specific challenges.

Main Results:

RL shows significant promise for enhancing the autonomy and performance of bionic underwater robots.
Key challenges include complex underwater environments and the underactuated nature of many bionic robots.
Existing RL methods are reviewed across various task types and deployment strategies.

Conclusions:

Reinforcement learning is a rapidly growing field for bionic underwater robot development.
Addressing challenges in training and deployment is crucial for practical applications.
This survey offers a foundation and insights for future research in RL for intelligent underwater robotics.