Learning based predictive tracking control method and device for wheeled mobile robot
A mobile robot, tracking control technology, applied in the direction of adaptive control, combustion engine, general control system, etc., can solve the problem that the control effect depends on the accurate model of the wheeled mobile robot, and the movement of the wheeled mobile robot cannot be well controlled, etc. The effect of safety and comfort
Active Publication Date: 2021-10-19
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF9 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] In order to solve the above-mentioned technical problems, the present invention proposes a learning-based predictive tracking control method and device for a wheeled mobile robot. The movement of the wheeled mobile robot is well controlled, and the control effect is more dependent on the technical problem of the accurate model of the wheeled mobile 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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0047] combine first figure 1 The flow of the learning-based predictive tracking control method of a wheeled mobile robot according to an embodiment of the present invention is described. Such as figure 1 As shown, the method includes the following steps:
[0048] Step S01: Carry out offline design, the offline design includes determining the sampling interval δ, the control execution time T e , learning error rate upper limit Determine the terminal domain Ω of the terminal controller ε Construct the basic model of the wheeled mobile robot, the basic model is a system including the pilot robot and the wheeled mobile robot, used to obtain the theoretical state value of the wheeled mobile robot; construct a learning model, the learning model Inputting the difference between the actual state value of the wheeled mobile robot and the theoretical state value is used to obtain a model deviation prediction value, and the model deviation prediction value is used to characterize t...
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
Login to View More Abstract
The invention provides a learning based predictive tracking control method and device for a wheeled mobile robot, and the method comprises the steps: obtaining a difference value between an actual state of the wheeled mobile robot and a theoretical state value of the wheeled mobile robot at the current moment, taking the difference value as the input of a learning model, outputting a model deviation prediction value, and calculating a learning error rate; if the learning error rate is greater than the learning error rate upper limit, updating a first learning model of the wheeled mobile robot on the basis of the model deviation predicted value; determining a predictive tracking control optimization problem model of the wheeled mobile robot based on the predictive tracking control target and constraint conditions of the wheeled mobile robot; and controlling a first learning model of the wheeled mobile robot by using a control strategy. According to the scheme, the control accuracy, the use safety and the use comfort of the wheeled mobile robot in actual use are guaranteed.
Description
technical field [0001] The invention relates to the field of robot trajectory tracking control, in particular to a learning-based predictive tracking control method and device for a wheeled mobile robot. Background technique [0002] As an important part of the field of robotics, wheeled mobile robots have been widely concerned by researchers. A complete wheeled mobile robot system generally consists of an environment perception system, a control system, and a behavior execution system. It integrates multiple disciplines such as sensors, electronics, information processing, automatic control, and artificial intelligence. At the same time, with its high integration and mobility, compared with other types of robots, wheeled mobile robots can carry out flexible operations in various complex environments. Especially with the continuous improvement of robot intelligence, wheeled mobile machines have gradually penetrated into all walks of life in modern society. It is not only ...
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
Login to View More IPC IPC(8): G05B13/04
CPCG05B13/042Y02T10/40
Inventor 戴荔陆雨琛黄腾杨欢孙中奇夏元清翟弟华
Owner BEIJING INSTITUTE OF TECHNOLOGYGY