Training Dynamic Motion Primitives using Deep Reinforcement Learning to Control a Robotic Tadpole

Hameed, Imran; Xu, Chao; Navarro-Alarcon, David; Jing, Xingjian

doi:10.1109/iros47612.2022.9981112

Cited by 2 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the FBW model, RL method SAC provided an effective approach for obtaining subcarangiform body wave parameters for a five-jointed fish-like robot, and both the cost of transport and velocity performance were optimized [ 90 ], in which the parameters of two optimized groups were compared, verifying that the optimal efficiency and optimal speed cannot be achieved simultaneously. Based on the DMP model and trust region policy optimization (TRPO) method, the robotic tadpole achieved an effective propulsion gait, with expected thrust and stable heading attitude as high rewards [ 91 ], which generated a target point strategy for the DMP model through navigation learning, allowing the robot to swim along a number of randomly generated paths. No matter which kind of bionic motion model, an appropriate reinforcement learning algorithm design can achieve gait optimization for bionic underwater robots.…”

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

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%