A control method and simulation system for the center of gravity of a biped robot based on reinforcement learning
A biped robot, center of gravity control technology, applied in the direction of program control of manipulators, manipulators, motor vehicles, etc., can solve the problems of inability to adapt to the changing road environment in real time, poor center of gravity effect of biped robots, etc., to simplify the training process and The effect of fitting difficulty, smooth movement, and zero-delay response judgment
Active Publication Date: 2022-03-01
武汉远图信息科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In view of this, the present invention proposes a method and system for controlling the center of gravity of a biped robot based on reinforcement learning, which is used to solve the problem that the center of gravity of a biped robot is not effective and cannot adapt to the changing road environment in real time
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
[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the implementation manners in the present invention, all other implementation manners obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.
[0052] In the embodiment of the present invention, use Solidworks The software builds the three-dimensional component model of the biped robot, using Coppelia Sim The software realizes the simulation of the model, and the deep learning platform is selected Tensorflow , the reinforcement learning framework is selected PARL , in the constructed biped robot components, the side length of the large cube is set to unit 20 cm , weight set to unit...
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 method, system, device and storage medium for controlling the center of gravity of a biped robot based on reinforcement learning. The method includes: a step of building three-dimensional components of the robot, constructing a three-dimensional model of the robot based on basic cube components, and setting the freedom of each part degree; the step of building the gravity system of the robot is to calibrate the parameters of the basic cube components and the center of gravity of the robot in the initial state to build the gravity system of the robot; the step of building the inertia system of the robot is to build the moment of inertia model based on each joint of the leg; The center of gravity of the footed robot and the center of gravity control strategy of steady-state walking are carried out to calibrate and set the relevant parameters of the center of gravity control; the robot simulation step is based on the reinforcement learning framework to realize the center of gravity and steady-state walking control simulation of the biped robot. The invention can realize high-efficiency and real-time center-of-gravity control of the robot, and can adapt to changeable road surface environments.
Description
technical field [0001] The invention belongs to the fields of robots and artificial intelligence, and in particular relates to a method for controlling the center of gravity of a biped robot based on reinforcement learning and a simulation system. Background technique [0002] In recent years, with the improvement of machinery manufacturing technology and artificial intelligence technology, the demand and application fields of robots have been greatly expanded. Various industrial robots, sweeping robots, service robots, etc. have been successfully applied in various industries. In the field of service robots, bipedal high-simulation robots have always been the most difficult and most important research direction. One very important reason is that biped robots need efficient and real-time center of gravity control during dynamic operation to ensure rapid and stable of the mobile. [0003] However, due to the comprehensive influence of the current mechanical manufacturing lev...
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 Patents(China)
IPC IPC(8): B25J9/16B25J17/02B62D57/032
CPCB25J9/1656B25J17/0258B62D57/032
Inventor 张帆
Owner 武汉远图信息科技有限公司