Mobile robot trajectory tracking control method based on strategy iteration

A mobile robot and trajectory tracking technology, applied in the field of reinforcement learning, can solve problems such as adverse reactions and system modeling difficulties, and achieve good trajectory tracking and realize the effect of trajectory tracking

Active Publication Date: 2021-06-15
ZHEJIANG UNIV OF TECH
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of the model-based algorithm is that it is difficult to model the system, and it may be counterproductive when the model is inaccurate

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
  • Mobile robot trajectory tracking control method based on strategy iteration
  • Mobile robot trajectory tracking control method based on strategy iteration
  • Mobile robot trajectory tracking control method based on strategy iteration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Embodiments of the present invention are described and stated in detail below in conjunction with the accompanying drawings, but are not limited to the above methods. Within the scope of the knowledge of those skilled in the art, as long as the concept of the present invention is based, various changes and improvements can be made.

[0043] refer to Figure 1 ~ Figure 4 , a trajectory tracking control method for mobile robots based on policy iteration. Different from value-based methods, policy-based reinforcement learning methods directly try to optimize the policy function to achieve tracking. For known mobile robot systems, two neural networks are built first. They are actor neural network and critic neural network respectively. The actor neural network is used to evaluate and improve the system control strategy, and the critic neural network is mainly used to calculate the value function under the current control strategy, and use this value function to evaluate th...

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 a mobile robot trajectory tracking control method based on strategy iteration. The mobile robot trajectory tracking control method is characterized by establishing two neural networks for a known mobile robot system, wherein the neural networks are respectively an actor neural network and a critic neural network, the actor neural network is used for evaluating and improving a system control strategy, the critic neural network is mainly used for calculating a value function under the current control strategy, and the value function is used for evaluating the current strategy. The method comprises the following steps of: 1) establishing a kinematic model of a mobile robot; 2) designing the Actor neural network; 3) designing the Critic neural network; and 4) designing an online algorithm of an Actor/Critic structure. Based on the data-driven control algorithm, the value function is utilized to evaluate the strategy function, the value function and the strategy function are considered in the learning process, and trajectory tracking of the mobile robot can be well achieved.

Description

technical field [0001] The invention belongs to the field of reinforcement learning, and specifically provides a trajectory tracking control method for a mobile robot based on strategy iteration, which is an intelligent control method. Background technique [0002] Today, with the rapid development of modern science and technology, mobile robots are always at the forefront of technology and have been leading the direction of high technology due to their small size, flexibility, simple operation, and flexibility. With the advent of the era of artificial intelligence and computer big data, humans always expect mobile robots to have more powerful autonomous capabilities to replace us in completing more complex and dangerous operational tasks in more neighborhoods. In order to achieve this goal, Its core technology requires mobile robots to have excellent motion planning capabilities, so that robots can work purposefully, accurately and efficiently in unknown environments withou...

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): G05D1/02
CPCG05D1/0253G05D1/0223G05D1/0221G05D1/0276G05D2201/02
Inventor 朱俊威张恒董子源吴珺张文安
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap