Supercharge Your Innovation With Domain-Expert AI Agents!

Underwater robot motion control method based on Actor-Critic algorithm

A technology of robot movement and underwater robot, applied in the direction of non-electric variable control, control/adjustment system, height or depth control, etc., can solve the problems of low precision of underwater robot speed and attitude control, real-time adjustment parameters, etc.

Active Publication Date: 2021-03-09
HARBIN ENG UNIV
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the existing underwater robot is difficult to adjust the parameters in real time during the movement process, and when the controller is disturbed, the control accuracy of the speed and attitude of the underwater robot is low, and a method based on Actor-Critic algorithm is proposed The motion control method of underwater robot

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Underwater robot motion control method based on Actor-Critic algorithm
  • Underwater robot motion control method based on Actor-Critic algorithm
  • Underwater robot motion control method based on Actor-Critic algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0017] Specific implementation mode one: the present implementation mode is a kind of underwater robot motion control method based on Actor-Critic algorithm, and specific process is:

[0018] Step 1. Initialize parameters;

[0019] Step 2. Design the speed control system and the heading control system of the underwater robot respectively based on the backstepping method, and then determine the control law of the speed control system and the control law of the heading control system according to the designed speed control system and heading control system;

[0020] Step 3. Set the Actor-Critic neural network. The Actor-Critic neural network includes four RBF neural networks, which are Actor current network, Actor target network, Critic current network and Critic target network;

[0021] Step 4. Determine the input and output of the Actor's current network; determine the input and output of the Critic's current network;

[0022] Step 5. Determine the input and output of the Act...

specific Embodiment approach 2

[0027] Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is: the initialization parameters in the step one; specifically:

[0028] Initialize the neural network parameters θ and w as random numbers of [-1,1], and set the neural network update weights α, discount rate γ, ε; initialize the original controller parameters ku0, Kr10 and Kr20; initialize the AUV model parameter quality m , a dimensionless hydrodynamic parameter x u|u| , N r , N r|r| , the moment of inertia I of the underwater robot around the z-axis of the motion coordinate system z .

[0029] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0030] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is that in the step two, the speed control system and the heading control system of the underwater robot are respectively designed based on the backstepping method, and then according to the designed speed control system And the heading control system determines the control law of the speed control system and the control law of the heading control system; the specific process is:

[0031] In order to use the parameter adaptive backstepping controller based on the Actor-Critic algorithm to realize the trajectory tracking control of the AUV, the goal of the present invention is to design the controller u so that the speed v and attitude of the AUV system in the presence of ocean current interference The quantity η is still able to track the expected value v d , η d and make the tracking error e v =v-v d 、e η =η-η d There are predetermined dynamic performance and stead...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an underwater robot motion control method based on an Actor-Critic algorithm, and relates to an underwater robot motion control method. The invention aims to solve the problemsthat parameters of an existing underwater robot are difficult to adjust in real time in the moving process, and the control precision of a controller on the speed and posture of the underwater robotis low when the underwater robot is disturbed. The process comprises the following steps: 1, initializing parameters; 2, determining control laws of a speed control system and a heading control system; 3, setting a neural network; 4, determining the input and output of the current network; 5, determining input and output of a target network; 6, updating a current network weight parameter of the Actor; 7, updating the current network weight parameter of the Critic; 8, repeatedly executing the step 4 to the step 7 for n times, and copying the updated current network weight parameter to the target network for the nth time; 9, repeatedly executing the step 8 to obtain a control law parameter value. The method is applied to the field of underwater robot motion control.

Description

technical field [0001] The invention relates to an underwater robot motion control method based on Actor-Critic algorithm. Background technique [0002] Autonomous Underwater Vehicle (AUV), as an important technical means to explore the ocean, has revolutionary applications in many disciplines such as marine environmental science, biology, archaeology, geography, etc. As a result, it has received widespread attention from all walks of life. The complex dynamic characteristics of AUV and the changing ocean environment pose great challenges to its motion control. Therefore, research on AUV motion control methods has important practical significance. When traveling in the ocean, AUVs are disturbed by factors such as ocean current disturbances and model uncertainties. Most of the tasks performed by AUVs require good accuracy, that is, the accuracy of the controller is extremely high. Some traditional control methods rely on dynamic equations for derivation, and select appropri...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G05D1/06
CPCG05D1/0692
Inventor 孙延超杜雨桐王卓吴淼秦洪德韩光洁
Owner HARBIN ENG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com