Intelligent Control Strategy for Robotic Manta via CPG and Deep Reinforcement Learning

被引:1
作者
Su, Shijie [1 ]
Chen, Yushuo [1 ]
Li, Cunjun [2 ]
Ni, Kai [1 ]
Zhang, Jian [1 ]
机构
[1] Jiangsu Univ Sci & Technol, Coll Mech Engn, Zhenjiang 212100, Peoples R China
[2] Zhoushan Inst Calibrat & Testing Qual & Technol Su, Zhoushan 316021, Peoples R China
关键词
swimming mode; deep deterministic policy gradient; swimming task; Markov decision process; FISH; SYSTEMS;
D O I
10.3390/drones8070323
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
The robotic manta has attracted significant interest for its exceptional maneuverability, swimming efficiency, and stealthiness. However, achieving efficient autonomous swimming in complex underwater environments presents a significant challenge. To address this issue, this study integrates Deep Deterministic Policy Gradient (DDPG) with Central Pattern Generators (CPGs) and proposes a CPG-based DDPG control strategy. First, we designed a CPG control strategy that can more precisely mimic the swimming behavior of the manta. Then, we implemented the DDPG algorithm as a high-level controller that adaptively modifies the CPG's control parameters based on the real-time state information of the robotic manta. This adjustment allows for the regulation of swimming modes to fulfill specific tasks. The proposed strategy underwent initial training and testing in a simulated environment before deployment on a robotic manta prototype for field trials. Both further simulation and experimental results validate the effectiveness and practicality of the proposed control strategy.
引用
收藏
页数:19
相关论文
共 36 条
  • [1] From Natural Complexity to Biomimetic Simplification The Realization of Bionic Fish Inspired by the Cownose Ray
    Cai, Yueri
    Bi, Shusheng
    Li, Guoyuan
    Hildre, Hans Petter
    Zhang, Houxiang
    [J]. IEEE ROBOTICS & AUTOMATION MAGAZINE, 2019, 26 (03) : 27 - 38
  • [2] CPG-fuzzy-based control of a cownose-ray-like fish robot
    Cao, Yong
    Lu, Yang
    Cai, Yueri
    Bi, Shusheng
    Pan, Guang
    [J]. INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2019, 46 (06): : 779 - 791
  • [3] Applying central pattern generators to control the robofish with oscillating pectoral fins
    Cao, Yong
    Bi, Shusheng
    Cai, Yueri
    Wang, Yuliang
    [J]. INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2015, 42 (05): : 392 - 405
  • [4] Bioinspired Closed-loop CPG-based Control of a Robot Fish for Obstacle Avoidance and Direction Tracking
    Chen, Jiayong
    Yin, Bo
    Wang, Chengcai
    Xie, Fengran
    Du, Ruxu
    Zhong, Yong
    [J]. JOURNAL OF BIONIC ENGINEERING, 2021, 18 (01) : 171 - 183
  • [5] [陈令坤 Chen Lingkun], 2020, [机械工程学报, Journal of Mechanical Engineering], V56, P182
  • [6] Chen Y.W., 2019, CoRR, V119, P10170
  • [7] Method of artificial intelligence algorithm to improve the automation level of Rietveld refinement
    Feng, Zhenjie
    Hou, Qiang
    Zheng, Yonglei
    Ren, Wei
    Ge, Jun-Yi
    Li, Tao
    Cheng, Cheng
    Lu, Wencong
    Cao, Shixun
    Zhang, Jincang
    Zhang, Tongyi
    [J]. COMPUTATIONAL MATERIALS SCIENCE, 2019, 156 : 310 - 314
  • [8] Course Control of a Manta Robot Based on Amplitude and Phase Differences
    Hao, Yiwei
    Cao, Yong
    Cao, Yonghui
    Huang, Qiaogao
    Pan, Guang
    [J]. JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2022, 10 (02)
  • [9] He J., 2020, P GLOB OC BIL MS US, P1
  • [10] Online PID Tuning Strategy for Hydraulic Servo Control Systems via SAC-Based Deep Reinforcement Learning
    He, Jianhui
    Su, Shijie
    Wang, Hairong
    Chen, Fan
    Yin, BaoJi
    [J]. MACHINES, 2023, 11 (06)