EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Reinforcement Learning-Enabled Control and Design of Rigid-Link Robotic Fish: A Comprehensive Review

Nhat Dinh, Darion Vosbein, Yuehua Wang, Qingsong Cui

Sensors · 2026

DOI: 10.3390/s26030996 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, 2026. Verfasst von Nhat Dinh und 3 weiteren Autor:innen. Beteiligte Einrichtung: Smart Devices and Intelligent Systems Laboratory, New Mexico Institute of Mining and Technology, Socorro, NM 87801, USA. Hauptthemen laut MEDLINE: Fishes, Robotics. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 92 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: New Mexico Institute of Mining and Technology (Startup Fund), National Science Foundation, National Institute of Food and Agriculture.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rising demand for maritime surveys of infrastructure, energy resources, and environmental conditions, autonomous robotic fish have emerged as a promising solution with their biomimetic propulsion, agile motion, efficiency, and capacity for underwater inspection, monitoring, data collection, and exploration tasks in complex aquatic environments. Inspired by fish spines, rigid-link fish robots (RLFRs), a category of robotic fish, are widely utilized in robotics research and applications. Their rigid, actuated joints enable them to reproduce the undulatory locomotion and high maneuverability of biological fishes, while the modular nature of rigid links between joints makes them cost-effective and easy to assemble. This review examines and presents recent approaches and advancements in the field of structural design, as well as Reinforcement learning (RL)-enabled controls with sensors and actuators. Existing designs are classified by joint configuration, with key structural, material, fabrication, and propulsion considerations summarized. The review highlights the use of Q-learning, Deep Q-Network (DQN), and Deep Deterministic Policy Gradient (DDPG) algorithms for RLFR controllers, showing their impact on adaptability, motion control, and learning in dynamic hydrodynamic conditions. Technical challenges—including unstructured environments and complex fluid–body interactions—are discussed, along with future directions. This review aims to clarify current progress and identify technological gaps for advancing rigid-link robotic fish.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

FishesRoboticsReinforcement Machine LearningAnimalsAutonomous RobotsBiomimeticsAlgorithmsEquipment Design

Stichwörter der Autor:innen

Q-learningdeep Q-networkdeep deterministic policy gradientreinforcement learningrigid link fish robots

Autor:innen und Institutionen

  • Smart Devices and Intelligent Systems Laboratory, New Mexico Institute of Mining and Technology, Socorro, NM 87801, USA.
  • Department of Computer Science, East Texas A&M University, Commerce, TX 75428, USA.

Förderung

  • New Mexico Institute of Mining and Technology (Startup Fund)
  • National Science Foundation
  • National Institute of Food and Agriculture
  • New Mexico Institute of Mining and Technology Startup Fund, National Science

Zitieren

APA

Dinh, N., Vosbein, D., Wang, Y., & Cui, Q. (2026). Reinforcement Learning-Enabled Control and Design of Rigid-Link Robotic Fish: A Comprehensive Review. Sensors. https://doi.org/10.3390/s26030996

Vancouver

Dinh N, Vosbein D, Wang Y, Cui Q. Reinforcement Learning-Enabled Control and Design of Rigid-Link Robotic Fish: A Comprehensive Review. Sensors. 2026. doi:10.3390/s26030996

BibTeX
@article{Dinh2026,
  author = {Dinh, Nhat and Vosbein, Darion and Wang, Yuehua and Cui, Qingsong},
  title = {Reinforcement Learning-Enabled Control and Design of Rigid-Link Robotic Fish: A Comprehensive Review},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26030996}
}
Kostenlos starten →