Robot control method and device based on interaction degree of components
A control method and technology of a control device, applied in the field of intelligent robots, can solve the problems of lack of interpretability of motion strategies, high complexity of robot control, and poor control stability of robots, so as to reduce complexity, simplify complexity, and improve stability. Effect
Active Publication Date: 2020-12-01
SUN YAT SEN UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the existing DRL algorithm is used to control the robot in reality. In the face of high-latitude control problems, it directly searches in the high-latitude state and behavior space, and the complexity of robot control is high; in addition, because the existing DRL algorithm is a kind of End-to-end behavior, that is, directly search the entire state-behavior space and output the final learned motion strategy, so the final motion strategy lacks interpretability, resulting in poor stability of robot control
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
[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0046] Such as figure 1 As shown, an embodiment of the present invention provides a robot control method based on the degree of component interaction, including:
[0047] Step S101: obtain the overall status information of the robot to be controlled;
[0048] Step S102: Input the overall state information of the robot to be controlled into the constructed action prediction model, so that the action prediction model can generate the overall state information of the...
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 discloses a robot control method based on an interaction degree of components. The method comprises the steps of obtaining overall state information of a to-be-controlled robot; inputting the overall state information of the to-be-controlled robot into an action prediction model, enabling the action prediction model to carry out structural decomposition on the overall state information to obtain state information of each component, and then calculating the interaction degree between one component and the remaining components according to the state information of the components; determining enhanced state information of each component according to the interaction degree between one component and the remaining components; predicting predicted action information of each component according to the enhanced state information of each component, and then generating overall predicted action information of the to-be-controlled robot according to the predicted action information ofall the components; and finally, controlling the to-be-controlled robot to move according to the overall predicted action information of the to-be-controlled robot. By implementing the robot controlmethod based on the interaction degree of the components, the complexity of robot control can be reduced, and the stability of robot control is improved.
Description
technical field [0001] The invention relates to the technical field of intelligent robots, in particular to a method and device for controlling a robot based on the interaction degree of components. Background technique [0002] Deep reinforcement learning (DRL) can guarantee various robot behavior control in challenging tasks such as locomotion and manipulation. However, the existing DRL algorithm is used to control the robot in reality. In the face of high-latitude control problems, it directly searches in the high-latitude state and behavior space, and the complexity of robot control is high; in addition, because the existing DRL algorithm is a kind of End-to-end behavior, that is, directly search the entire state-behavior space and output the final learned motion policy, so the final motion policy lacks interpretability, resulting in poor stability of robot control. Contents of the invention [0003] Embodiments of the present invention provide a robot control method ...
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 Patent Type & Authority Applications(China)
IPC IPC(8): B25J11/00B25J9/16
CPCB25J9/1602B25J9/1664B25J9/1679B25J11/0005
Inventor 余超董银昭葛宏伟陈炳才孙亮
Owner SUN YAT SEN UNIV