Three-dimensional path following control based net cage inspection bionic robotic fish

This paper addresses the finite-time three-dimensional path-following control problem for underactuated autonomous airship with error constraints and uncertainties. First, a five degrees-of-freedom path-following error model in the Serret-Frenet coordinate frame is established. By applying the finite-time stability theory, a virtual guidance-based finite-time adaptive neural backstepping path-following control approach is proposed. Barrier Lyapunov functions (BLFs) are introduced to deal with attitude error constraints. Neural networks (NNs) are presented to compensate for the uncertainties. To prevent the “explosion of complexity” in the design of the backstepping method, a finite-time convergent differentiator (FTCD) is introduced to estimate the time derivatives of virtual control signals. Stability analysis showed that all closed-loop signals are uniformly ultimately bounded, the constrained requirements on the airship attitude errors are never violated, and the path-following errors converge to a small neighborhood of the origin in a finite time. At last, simulation studies are provided to demonstrate the effectiveness of the proposed control approach.

Download Full-text

Three-Dimensional Path Following Control of an Underactuated Robotic Dolphin Using Deep Reinforcement Learning

2020 IEEE International Conference on Real-time Computing and Robotics (RCAR) ◽

10.1109/rcar49640.2020.9303309 ◽

2020 ◽

Author(s):

Jincun Liu ◽

Zhenna Liu ◽

Zhengxing Wu ◽

Junzhi Yu

Keyword(s):

Reinforcement Learning ◽

Three Dimensional ◽

Path Following ◽

Path Following Control

Download Full-text

Three-dimensional path following control of underactuated autonomous underwater vehicle based on damping backstepping

International Journal of Advanced Robotic Systems ◽

10.1177/1729881417724179 ◽

2017 ◽

Vol 14 (4) ◽

pp. 172988141772417 ◽

Cited By ~ 12

Author(s):

Xiao Liang ◽

Xingru Qu ◽

Yuanhang Hou ◽

Jundong Zhang

Keyword(s):

Autonomous Underwater Vehicles ◽

Three Dimensional ◽

Path Following ◽

Ocean Current ◽

Singular Problem ◽

Stable Theory ◽

Parameter Uncertainties ◽

External Disturbances ◽

Path Following Control ◽

Following Error

This article addresses the problem of three-dimensional path following control for underactuated autonomous underwater vehicles in the presence of ocean current. Firstly, three-dimensional path following error model was established based on virtual guidance method. The control law is developed by building virtual velocity errors and backstepping method, which can simplify the virtual control input and avoid the singular problem induced by initial state constraints. Considering the curvature and torsion characteristics of the three-dimensional desired path, the approaching angle is introduced to guarantee fast convergence of error. Nonlinear damping term is introduced to offset the effects of dynamic uncertainties and external disturbances. The controller stability was proved by Lyapunov stable theory. Finally, simulations were conducted and the results indicate the effectiveness and robustness to parameter uncertainties and external disturbances of the proposed approach.

Download Full-text

Robust three-dimensional path-following control for an under-actuated stratospheric airship

Advances in Space Research ◽

10.1016/j.asr.2018.09.008 ◽

2019 ◽

Vol 63 (1) ◽

pp. 526-538 ◽

Cited By ~ 2

Author(s):

Lin Cheng ◽

Zongyu Zuo ◽

Jiawei Song ◽

Xiao Liang

Keyword(s):

Three Dimensional ◽

Path Following ◽

Stratospheric Airship ◽

Path Following Control

Download Full-text

Three-Dimensional Path-Following Control of a Robotic Airship with Reinforcement Learning

International Journal of Aerospace Engineering ◽

10.1155/2019/7854173 ◽

2019 ◽

Vol 2019 ◽

pp. 1-12 ◽

Cited By ~ 7

Author(s):

Chunyu Nie ◽

Zewei Zheng ◽

Ming Zhu

Keyword(s):

Reinforcement Learning ◽

Learning Algorithm ◽

Three Dimensional ◽

Path Following ◽

Cerebellar Model Articulation Controller ◽

Intelligent Decision Making ◽

Cmac Neural Network ◽

Path Following Control ◽

Markov Decision ◽

Robotic Airship

This paper proposed an adaptive three-dimensional (3D) path-following control design for a robotic airship based on reinforcement learning. The airship 3D path-following control is decomposed into the altitude control and the planar path-following control, and the Markov decision process (MDP) models of the control problems are established, in which the scale of the state space is reduced by parameter simplification and coordinate transformation. To ensure the control adaptability without dependence on an accurate airship dynamic model, a Q-Learning algorithm is directly adopted for learning the action policy of actuator commands, and the controller is trained online based on actual motion. A cerebellar model articulation controller (CMAC) neural network is employed for experience generalization to accelerate the training process. Simulation results demonstrate that the proposed controllers can achieve comparable performance to the well-tuned proportion integral differential (PID) controllers and have a more intelligent decision-making ability.

Download Full-text