Online Optimization of Normalized CPGs for a Multi-Joint Robotic Fish

Ru, Tong; Wu, Zhengxing; Wang, Jian; Tan, Min; Yu, Junzhi

doi:10.23919/ccc52363.2021.9550257

Cited by 5 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, from Table 2 , action control based on the CPG model has an advantage in terms of quantity. To expand the application value of CPG in reinforcement learning, improved CPG algorithms have also been proposed to meet control requirements and reduce the risk of abrupt changes in parameters, such as normalized CPG [ 125 ], modified CPG network in bidirectional perturbation [ 124 ], and modified CPG with reduced input parameters [ 98 ]. These novel CPG models are more suitable for reinforcement learning environments, providing a solid foundation for subsequent RL-based bionic motion optimization methods, and are of high reference value.…”

Section: Rl-based Methods In Task Spaces Of Bionic Underwater Robotsmentioning

confidence: 99%

A Survey on Reinforcement Learning Methods in Bionic Underwater Robots

Feng

Wang

et al. 2023

Biomimetics

Self Cite

View full text Add to dashboard Cite

Bionic robots possess inherent advantages for underwater operations, and research on motion control and intelligent decision making has expanded their application scope. In recent years, the application of reinforcement learning algorithms in the field of bionic underwater robots has gained considerable attention, and continues to grow. In this paper, we present a comprehensive survey of the accomplishments of reinforcement learning algorithms in the field of bionic underwater robots. Firstly, we classify existing reinforcement learning methods and introduce control tasks and decision making tasks based on the composition of bionic underwater robots. We further discuss the advantages and challenges of reinforcement learning for bionic robots in underwater environments. Secondly, we review the establishment of existing reinforcement learning algorithms for bionic underwater robots from different task perspectives. Thirdly, we explore the existing training and deployment solutions of reinforcement learning algorithms for bionic underwater robots, focusing on the challenges posed by complex underwater environments and underactuated bionic robots. Finally, the limitations and future development directions of reinforcement learning in the field of bionic underwater robots are discussed. This survey provides a foundation for exploring reinforcement learning control and decision making methods for bionic underwater robots, and provides insights for future research.

show abstract

Section: Rl-based Methods In Task Spaces Of Bionic Underwater Robotsmentioning

confidence: 99%

A Survey on Reinforcement Learning Methods in Bionic Underwater Robots

Feng

Wang

et al. 2023

Biomimetics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although it lacks enough theoretical basis, CPG control has been widely used in bionic engineering [227][228][229][230][231].…”

Section: Motion Controlmentioning

confidence: 99%

Research Development on Fish Swimming

Jiang

2022

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

Fishes have learned how to achieve outstanding swimming performance through the evolution of hundreds of millions of years, which can provide bio-inspiration for robotic fish design. The premise of designing an excellent robotic fish include fully understanding of fish locomotion mechanism and grasp of the advanced control strategy in robot domain. In this paper, the research development on fish swimming is presented, aiming to offer a reference for the later research. First, the research methods including experimental methods and simulation methods are detailed. Then the current research directions including fish locomotion mechanism, structure and function research and bionic robotic fish are outlined. Fish locomotion mechanism is discussed from three views: macroscopic view to find a unified principle, microscopic view to include muscle activity and intermediate view to study the behaviors of single fish and fish school. Structure and function research is mainly concentrated from three aspects: fin research, lateral line system and body stiffness. Bionic robotic fish research focuses on actuation, materials and motion control. The paper concludes with the future trend that curvature control, machine learning and multiple robotic fish system will play a more important role in this field. Overall, the intensive and comprehensive research on fish swimming will decrease the gap between robotic fish and real fish and contribute to the broad application prospect of robotic fish.

show abstract

“…Wang et al [24] used particle swarm optimization to optimize the CPG parameters of a robotic fish with swinging tail fins, thereby achieving a higher swimming speed. Tong et al [25] proposed a method to optimize CPG parameters online. By establishing the dynamic model of the robot fish, N-CPGs were optimized using the deep Q network (DQN) to improve the swimming speed of the robot fish.…”

Section: Introductionmentioning

confidence: 99%

Realization and Online Optimization for Gliding and Flapping Propulsion of a Manta Ray Robot

Cao,

et al. 2023

JMSE

View full text Add to dashboard Cite

Currently, the bionic robotic fish is primarily devoted to the bionic appearance of fish and rarely involves the bionic swimming posture. However, biological studies have proved that fish have extraordinary swimming ability, so it is necessary to imitate the swimming posture of fish. This paper introduces a manta ray robot driven by three fin rays, with its pectoral fins being structurally simulated using silicone rubber. According to the manta ray’s integrated gliding and flapping propulsion characteristics, we established a central-pattern-generator-based (CPG-based) biomimetic-motion-control method to realize the manta ray robot’s integrated gliding and flapping propulsion control. We designed an evaluation method of motion–posture similarity for the manta ray robot and optimized the control parameters to enhance the resemblance to the manta ray robot. The experimental results show that the online similarity-optimization method based on particle swarm optimization enhances the resemblance to 86.93%, and its swimming stability is also improved to some extent, which verifies the effectiveness of the optimization method. This study provides a new idea for optimizing motion control of the manta ray robot and realizing environmental affinity.

show abstract

Online Optimization of Normalized CPGs for a Multi-Joint Robotic Fish

Cited by 5 publications

References 13 publications

A Survey on Reinforcement Learning Methods in Bionic Underwater Robots

A Survey on Reinforcement Learning Methods in Bionic Underwater Robots

Research Development on Fish Swimming

Realization and Online Optimization for Gliding and Flapping Propulsion of a Manta Ray Robot

Contact Info

Product

Resources

About