Unlock instant, AI-driven research and patent intelligence for your innovation.

Path planning method of motor crane robot

A technology for truck cranes and path planning, which is applied to instruments, biological neural network models, data processing applications, etc., and can solve problems such as local minima

Inactive Publication Date: 2010-09-15
何新哲 +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is a local minimum problem in this algorithm
The present invention proposes an improved path planning method based on neural network energy function, which can solve the local minimum value problem of such path planning

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
  • Path planning method of motor crane robot
  • Path planning method of motor crane robot
  • Path planning method of motor crane robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The specific implementation method of the path planning of the improved path planning method based on the neural network energy function of the present invention is divided into the following steps:

[0052] Step 1: Define the path total energy function.

[0053] The collision penalty function of a path is defined as the sum of the collision penalty functions of each path point, and the collision penalty function of a point is obtained through its three-layer forward neural network representation for each obstacle. figure 1A neural network representing the penalty function from a point to an obstacle. The input values ​​of the two nodes of the input layer are the abscissa and ordinate x, y of the path point respectively, and x and y are real numbers, and each node of the middle layer is an inequality restriction condition corresponding to a side of an obstacle, The connection weight coefficients of the input layer and the intermediate layer are equal to the coefficient...

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 relates to a path planning method for automobile crane robots, in particular to an improved autonomous mobile-robot path planning method based on neural network energy function. The method comprises the following steps: a total energy function of a path is defined as the weighted sum of a collision penalty function and an energy function corresponding to the length part of the path;whether a starting point and a target point of the path are on the central axis of a obstacle is detected; if the starting point and the target point are both on the central axis of the obstacle, a path point is selected at random, and the path is planned after the coordinates of the path point are appropriately altered; whether the position of the path point is in the obstacle is detected in a path planning process; the position of the path point is moved by use of different dynamic motion equations according to different positions of the path point positioned inside or outside the obstacle,so as to enable the path point to move towards the direction of reducing the function value of the total energy function; and the shortest obstacle-avoidance path is finally planned.

Description

technical field [0001] The invention relates to the path planning of a car crane robot, in particular to an improved path planning method for an autonomous mobile robot based on a neural network energy function. Background technique [0002] With the development of science and technology, truck crane robots will replace people to work in dangerous environments. Truck crane robots are a kind of autonomous mobile robots. ability to move. The artificial potential field method in the traditional path planning method of autonomous mobile robot path planning, its basic idea is to make the path avoid obstacles by finding the minimum value point of the energy function of the path point, but there is a local minimum value problem and it is not suitable to find the shortest path. "Artificial neural network" is an engineering system that simulates its structure and intelligent behavior based on the understanding of the human brain's organizational structure and operating mechanism. ...

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 Patents(China)
IPC IPC(8): G06Q10/00G06Q50/00G06N3/02G06Q10/04
Inventor 禹建丽张野司广华康明川李先阳程思雅
Owner 何新哲