An online self-learning multi-joint motion planning method based on neural network
A technology of motion planning and neural network, applied in the direction of neural learning method, biological neural network model, neural architecture, etc., can solve problems such as cumbersome solution process, high difficulty, delay, etc., and achieve high calculation efficiency, low calculation difficulty and short implementation time delayed effect
Active Publication Date: 2021-07-13
BEIJING RES INST OF PRECISE MECHATRONICS CONTROLS
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the solution of the working space of the manipulator in the three-dimensional space involves a variety of sampling numerical methods, multi-joint synchronous trajectory planning control, and its complex nonlinear relationship with time, the solution process is cumbersome, difficult and inefficient, and has delays. characteristics, it is difficult to realize the self-learning real-time motion planning of the robotic arm
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
[0036] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:
[0037] The neural network method can ignore the specific physical parameters of the process or system, and realize the complex nonlinear mapping between input and output through the learning of training samples, and has good generalization ability. It has the best global approximation performance, and the training method is fast. Easy to implement, there is no local optimum problem. The neural network is used to establish the functional relationship between the trajectory-related information such as joint positions and angles and the trajectory-related information at the previous N moments, so that the trajectory-related information can be predicted.
[0038] Specifically, such as figure 1 As shown, the online self-learning multi-joint motion planning method of the present invention is realized through the following steps:
[0039] (1) Collect...
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 an online self-learning multi-joint motion planning method based on a neural network, which utilizes the global best approximation performance of the neural network to realize real-time self-learning and control of nonlinear complex paths. Since multi-joints perform trajectory planning control synchronously, which has a complex nonlinear relationship with time, the present invention realizes online self-learning of multi-joints by establishing a neural network model of the time-correlated sequence of each joint position, which is used for real-time monitoring of intelligent manipulators. Control greatly reduces the difficulty of numerical solution, improves computing efficiency, and has real-time self-learning ability.
Description
technical field [0001] The invention relates to an online self-learning multi-joint motion planning method based on a neural network, which is used for online self-learning to realize the motion planning and control of a multi-joint manipulator, belongs to the field of trajectory planning and control of intelligent robots, and is especially suitable for realizing manipulator arm alignment. Discovery of new trajectory paths, real-time self-learning and control. Background technique [0002] With the development of technology, intelligent robots have been widely concerned and applied. They include highly integrated equipment with multiple disciplines such as mechanical structure, drive, and control. The mechanical arm of an intelligent robot generally includes multiple drive joints, and its trajectory control determines the Precision, service and application of robotic arms. The motion trajectory control of the manipulator is mostly used in three-dimensional space. At present...
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): B25J9/16G06N3/04G06N3/08
CPCB25J9/1664G06N3/08G06N3/045
Inventor 郭雅静朱晓荣赵青陈靓郭喜彬
Owner BEIJING RES INST OF PRECISE MECHATRONICS CONTROLS