Nothing Special   »   [go: up one dir, main page]
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 

Saved Queries

Sign in to use this feature.

Search Filter Reset All

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
Add Subjects Reset
Select Subjects

Journals

remove_circle_outline
Add Journals Reset
Select Journals

Article Types

remove_circle_outline
Add Article Types Reset
Select Article Types

Countries / Regions

remove_circle_outline
Add Countries / Regions Reset
Select Countries / Regions
Update Search
share announcement

Search Results (2)

Search Parameters:
Keywords = underwater vehicle-dual-manipulator system

Order results
Result details
Results per page
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
15 pages, 14496 KiB  
Article
Reinforcement-Learning-Based Visual Servoing of Underwater Vehicle Dual-Manipulator System
by Yingxiang Wang and Jian Gao
J. Mar. Sci. Eng. 2024, 12(6), 940; https://doi.org/10.3390/jmse12060940 - 3 Jun 2024
Viewed by 743
Abstract
As a substitute for human arms, underwater vehicle dual-manipulator systems (UVDMSs) have attracted the interest of global researchers. Visual servoing is an important tool for the positioning and tracking control of UVDMSs. In this paper, a reinforcement-learning-based adaptive control strategy for the UVDMS [...] Read more.
As a substitute for human arms, underwater vehicle dual-manipulator systems (UVDMSs) have attracted the interest of global researchers. Visual servoing is an important tool for the positioning and tracking control of UVDMSs. In this paper, a reinforcement-learning-based adaptive control strategy for the UVDMS visual servo, considering the model uncertainties, is proposed. Initially, the kinematic control is designed by developing a hybrid visual servo approach using the information from multi-cameras. The command velocity of the whole system is produced through a task priority method. Then, the reinforcement-learning-based velocity tracking control is developed with a dynamic inversion approach. The hybrid visual servoing uses sensors equipped with UVDMSs while requiring fewer image features. Model uncertainties of the coupled nonlinear system are compensated by the actor–critic neural network for better control performances. Moreover, the stability analysis using the Lyapunov theory proves that the system error is ultimately uniformly bounded (UUB). At last, the simulation shows that the proposed control strategy performs well in the task of dynamical positioning. Full article
(This article belongs to the Section Ocean Engineering)
►▼ Show Figures

Figure 1

Figure 1
<p>Coordinate frames and joint configuration of the UVDMS.</p> Full article ">Figure 2
<p>Actor–critic-based adaptive visual servo control.</p> Full article ">Figure 3
<p>The underwater manipulator’s geometrical parameters.</p> Full article ">Figure 4
<p>Pose of the vehicle in the inertial frame: (<b>a</b>) the position of UUV; (<b>b</b>) the Euler angles of UUV.</p> Full article ">Figure 5
<p>Angles of the manipulators: (<b>a</b>) the left manipulator; (<b>b</b>) the right manipulator.</p> Full article ">Figure 6
<p>Positions of the end effectors in the inertial frame: (<b>a</b>) the left end effector; (<b>b</b>) the right end effector.</p> Full article ">Figure 7
<p>Euler angles and linear velocities of the end effectors: (<b>a</b>) Euler angles of the end effectors; (<b>b</b>) linear velocities of the end effectors.</p> Full article ">Figure 8
<p>Velocities of the vehicle: (<b>a</b>) the vehicle’s linear velocity; (<b>b</b>) the vehicle’s angular velocity.</p> Full article ">Figure 9
<p>Angular velocities of the manipulators: (<b>a</b>) velocities of the left manipulator; (<b>b</b>) velocities of the right manipulator.</p> Full article ">Figure 10
<p>Torques of the manipulators: (<b>a</b>) the left manipulator; (<b>b</b>) the right manipulator.</p> Full article ">Figure 11
<p>Forces input of the vehicle: (<b>a</b>) forces of the vehicle; (<b>b</b>) torques of the vehicle.</p> Full article ">Figure 12
<p>Reinforcement-learning-based compensation signals and the simulation of the UVDMS visual servo in Unity: (<b>a</b>) outputs of the actor neural networks; (<b>b</b>) the screenshot from Unity.</p> Full article ">
17 pages, 14824 KiB  
Article
Model Predictive Collision Avoidance Control for Object Transport of Unmanned Underwater Vehicle-Dual-Manipulator Systems
by Yingxiang Wang and Jian Gao
J. Mar. Sci. Eng. 2024, 12(6), 926; https://doi.org/10.3390/jmse12060926 - 31 May 2024
Viewed by 720
Abstract
Unmanned underwater vehicle-dual-manipulator systems (UVDMSs) have attracted much research due to their humanoid operation capabilities, which have the advantage of cooperative manipulations and transporting underwater objects. Meanwhile, collision avoidance of UVDMSs is more challenging than that of unmanned underwater vehicle-dual manipulator systems (UVMSs). [...] Read more.
Unmanned underwater vehicle-dual-manipulator systems (UVDMSs) have attracted much research due to their humanoid operation capabilities, which have the advantage of cooperative manipulations and transporting underwater objects. Meanwhile, collision avoidance of UVDMSs is more challenging than that of unmanned underwater vehicle-dual manipulator systems (UVMSs). In this work, a model predictive control (MPC) approach is proposed for collision avoidance in objects transporting tasks of UVDMSs. The minimum distances of mutual manipulators and frame obstacles are handled as velocity constraints in the optimization of the UVDMS’s object tracking control. The command velocity generated by the model predictive kinematic controller is tracked by a dynamic inversion control scheme while model uncertainties are compensated by a neural network. Moreover, the tracking errors of the proposed dynamic controller are proved to be convergent by the Lyapunov method. At last, a three-dimensional (3D) UVDMS simulation platform is developed to verify the effectiveness of the proposed control strategy in the tasks of collision avoidance and object transport. Full article
(This article belongs to the Special Issue Track Planning with Automatic Obstacle Recognition and Avoidance for Maritime Vessels)
►▼ Show Figures

Figure 1

Figure 1
<p>Coordinate frames and joint configuration of the UVDMS.</p> Full article ">Figure 2
<p>Definition of the minimum distances to avoid collisions.</p> Full article ">Figure 3
<p>Distance between two non-coplanar links.</p> Full article ">Figure 4
<p>Coordinates and forces of the object.</p> Full article ">Figure 5
<p>Model predictive collision avoidance tracking control scheme.</p> Full article ">Figure 6
<p>Moments of collisions and corresponding results improved by collision avoidance.</p> Full article ">Figure 7
<p>End-effector position of Case 1: (<b>a</b>) Positions of the left end effector; (<b>b</b>) Positions of the right end effector.</p> Full article ">Figure 8
<p>End-effector position of Case 2: (<b>a</b>) Positions of the left end effector; (<b>b</b>) Positions of the right end effector.</p> Full article ">Figure 9
<p>Comparison of the minimum distances of certain links: (<b>a</b>) The fluctuation of the minimum distance from link 5 of the right manipulator to the left manipulator; (<b>b</b>) The fluctuation of the minimum distance from link 3 of the right manipulator to corresponding frames.</p> Full article ">Figure 10
<p>Display of the object trajectory tracking in Unity.</p> Full article ">Figure 11
<p>Object pose: (<b>a</b>) Positions of the object; (<b>b</b>) Euler angles of the object.</p> Full article ">Figure 12
<p>UUV poses: (<b>a</b>) Positions of the vehicle; (<b>b</b>) Euler angles of the vehicle.</p> Full article ">Figure 13
<p>Joint angles: (<b>a</b>) Joints of the left manipulator; (<b>b</b>) Joint of the right manipulator.</p> Full article ">Figure 14
<p>Object and UUV velocities: (<b>a</b>) Velocity of the object; (<b>b</b>) Velocity of the vehicle.</p> Full article ">Figure 15
<p>Joint velocities and manipulators input: (<b>a</b>) Joint angular velocities of both manipulators; (<b>b</b>) Torques of the manipulators.</p> Full article ">Figure 16
<p>UUV torques input and compensation signals from the neural network: (<b>a</b>) Torques of the UUV; (<b>b</b>) NN compensation signals.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying article 1-50 on page 1 of 1.
Back to TopTop