Bioinspired robotics takes advantage of biological systems in nature for morphology, action and perception to build advanced robots of compelling performance and wide application. This paper focuses on the design, modeling and control of a bioinspired robotic fish. The design utilizes a recently-developed artificial muscle named super coiled polymer for actuation and a soft material (silicone rubber) for building the robot body. The paper proposes a learning based speed control design approach for bioinspired robotic fish using model-free reinforcement learning. Based on a mathematically tractable dynamic model derived by approximating the robotic fish with a three-link robot, speed control simulation is conducted to demonstrate and validate the control design method. Exampled with a three-link reduced-order dynamic system, the proposed learning based control design approach is applicable to many and various complicated bioinspired robotic systems.
Skip Nav Destination
ASME 2018 Dynamic Systems and Control Conference
September 30–October 3, 2018
Atlanta, Georgia, USA
Conference Sponsors:
- Dynamic Systems and Control Division
ISBN:
978-0-7918-5189-0
PROCEEDINGS PAPER
Learning Based Speed Control of Soft Robotic Fish
Sunil Kumar Rajendran,
Sunil Kumar Rajendran
George Mason University, Fairfax, VA
Search for other works by this author on:
Feitian Zhang
Feitian Zhang
George Mason University, Fairfax, VA
Search for other works by this author on:
Sunil Kumar Rajendran
George Mason University, Fairfax, VA
Feitian Zhang
George Mason University, Fairfax, VA
Paper No:
DSCC2018-8977, V001T04A005; 7 pages
Published Online:
November 12, 2018
Citation
Rajendran, SK, & Zhang, F. "Learning Based Speed Control of Soft Robotic Fish." Proceedings of the ASME 2018 Dynamic Systems and Control Conference. Volume 1: Advances in Control Design Methods; Advances in Nonlinear Control; Advances in Robotics; Assistive and Rehabilitation Robotics; Automotive Dynamics and Emerging Powertrain Technologies; Automotive Systems; Bio Engineering Applications; Bio-Mechatronics and Physical Human Robot Interaction; Biomedical and Neural Systems; Biomedical and Neural Systems Modeling, Diagnostics, and Healthcare. Atlanta, Georgia, USA. September 30–October 3, 2018. V001T04A005. ASME. https://doi.org/10.1115/DSCC2018-8977
Download citation file:
67
Views
0
Citations
Related Proceedings Papers
Related Articles
Musculoskeletal System for Bio-Inspired Robotic Systems
Mechanical Engineering (March,2016)
Model Following Adaptive Sliding Mode Tracking Control Based on a Disturbance Observer for the Mechanical Systems
J. Dyn. Sys., Meas., Control (May,2018)
Experimental Verification of Kinematics and Kinetics in a Biomimetic Bipedal Robot
J. Mechanisms Robotics (February,2023)
Related Chapters
Time-Varying Coefficient Aided MM Scheme
Robot Manipulator Redundancy Resolution
Breathing and Living Walls
Advanced Energy Efficient Building Envelope Systems
The ServoTeach Module
Precision Programming of Roving Robots: Project-Based Fundamentals of Wheeled, Legged and Hybrid Mobile Robots