Bipedal Walking of Underwater Soft Robot Based on Data-Driven Model Inspired by Octopus

Wu, Qiuxuan; Wu, Yan; Yang, Xiaochen; Zhang, Botao; Wang, Jian; Chepinskiy, Sergey A.; Zhilenkov, Anton

doi:10.3389/frobt.2022.815435

Cited by 6 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 100 ], an effective solution for the attitude control of the jellyfish-like robot relies on both a 3D barycenter adjustment mechanism and a Q-learning-based attitude control method, whose reward is related to the target and the current attitude; however, freely adjusting the three-axis attitude has not yet been achieved. Unlike the previous two studies focusing on the overall attitude of bionic robots, the study in [ 101 ] focuses on the posture of each soft arm of an octopus-inspired soft robot. Based on a set posture error thresholds, precise attitude control of the soft arm is achieved through the DQN method, and the bipedal walking of the octopus-inspired soft robot is realized by coordinating the two precise attitude-controlled soft arms.…”

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

“…Biological soft tissues in nature have great environmental adaptability and high bearing capacity, such as octopus' arms [9,10], elephant trunk [11], and human ngers [12,13]. The ability to change its own stiffness to increase the grasping force according to different grasping targets is called variable stiffness.…”

Section: Introductionmentioning

confidence: 99%

Design, Fabrication and Analysis of Soft Robotic Grippers based on Passive Layer Jamming

Yin

Huang

et al. 2023

Preprint

View full text Add to dashboard Cite

Soft fingers with variable stiffness based on jamming principle have the characteristics of simple structure, convenient control, and rapid response, but is usually requires vacuum pressure to squeeze the particles or layered materials to produce stiffness changes. A novel passive variable stiffness soft finger based on the passive layer jamming principle was presented in this paper. The inflation chamber of the soft finger was bent and squeezes the outer wall of the jamming chamber. The squeezing force causes the jamming layer unit inside the jamming chamber to squeeze each other to generate friction, which causes stiffness changed. Besides, aiming at the previous manufacturing methods of double-chamber soft fingers, this work also proposes an “integrated molding” casting process based on the lost-wax casting method, which can realize the manufacturing of soft fingers through on casting without splice. The experimental results shown that the soft finger with passive layer jamming also has excellent grasping performance under the condition of reducing additional equipment (vacuum system).

show abstract

“…SMAs were also used to actuate a soft robot by employing Q-learning to develop a control policy for end effector locomotion 29 . Additionally, an octopus-inspired soft robot used deep q learning (DQN) to control the posture of the soft arms of the robot 30 . One approach used a deep deterministic policy gradient (DDPG) algorithm to learn a control policy for soft continuum arms 31 .…”

Section: Introductionmentioning

confidence: 99%

Design and control of soft biomimetic pangasius fish robot using fin ray effect and reinforcement learning

Youssef

Soliman

Saleh

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Soft robots provide a pathway to accurately mimic biological creatures and be integrated into their environment with minimal invasion or disruption to their ecosystem. These robots made from soft deforming materials possess structural properties and behaviors similar to the bodies and organs of living creatures. However, they are difficult to develop in terms of integrated actuation and sensing, accurate modeling, and precise control. This article presents a soft-rigid hybrid robotic fish inspired by the Pangasius fish. The robot employs a flexible fin ray tail structure driven by a servo motor, to act as the soft body of the robot and provide the undulatory motion to the caudal fin of the fish. To address the modeling and control challenges, reinforcement learning (RL) is proposed as a model-free control strategy for the robot fish to swim and reach a specified target goal. By training and investigating the RL through experiments on real hardware, we illustrate the capability of the fish to learn and achieve the required task.

show abstract

Bipedal Walking of Underwater Soft Robot Based on Data-Driven Model Inspired by Octopus

Cited by 6 publications

References 23 publications

A Survey on Reinforcement Learning Methods in Bionic Underwater Robots

A Survey on Reinforcement Learning Methods in Bionic Underwater Robots

Design, Fabrication and Analysis of Soft Robotic Grippers based on Passive Layer Jamming

Design and control of soft biomimetic pangasius fish robot using fin ray effect and reinforcement learning

Contact Info

Product

Resources

About