Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Heuristic RRT mechanical arm motion planning method based on target deviation optimization

A motion planning and heuristic technology, applied to manipulators, program-controlled manipulators, manufacturing tools, etc., can solve problems such as time-consuming, feasibility cannot be guaranteed, local minimum, etc., to reduce the search path length, improve quality and efficiency, reduce The effect of the number of inflection points

Active Publication Date: 2020-04-07
NAVAL UNIV OF ENG PLA
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, LaValle introduced probability-based sampling, which improves the search efficiency of the basic RRT algorithm, but at the same time it is easy to fall into the local minimum
Karaman proposed the RRT algorithm with the optimal path, the planning path has high stability and is close to optimal, but it takes a lot of time
The above techniques cannot completely avoid the phenomenon of local optimum or oscillation near obstacles, and the reliability of the algorithm is not strong for the manipulator
At the same time, motion planning is separated from the technology, most of the algorithms stay in two-dimensional space, and the feasibility of practical application in three-dimensional space cannot be guaranteed

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
  • Heuristic RRT mechanical arm motion planning method based on target deviation optimization
  • Heuristic RRT mechanical arm motion planning method based on target deviation optimization
  • Heuristic RRT mechanical arm motion planning method based on target deviation optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The invention will be described in detail below in conjunction with specific embodiments.

[0060] first part

[0061] A heuristic RRT manipulator motion planning method (PBG-RRT) based on target-biased optimization of the present invention, the RRT algorithm is a fast path planning algorithm based on random sampling, which can effectively search high-dimensional spaces, and can effectively It is widely used to avoid the difficulty of 3D modeling. RRT is an algorithm that traverses the whole graph through probability and is easy to search in high-dimensional space. figure 1 is the growth process diagram of RRT.

[0062] The basic principle is: given a starting point q start , put q start store to q nodes In the space, the random sampling point q of the whole map in the space rand , looking for q nodes reach q rand The nearest point in is q near , at q near to q rand advance to q with a certain step size δ in the direction of new , during which collision detec...

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 belongs to the technical field of robot path planning and generation in a three-dimensional space, and particularly relates to a heuristic RRT mechanical arm motion planning method basedon target deviation optimization. The method comprises the following steps: determining a starting point q<start>, and storing the q<start> in q<nodes>; randomly sampling a point q<rand> in a space in a full map, and searching a nearest point in the q<rand> where q<nodes> reach as q<near>; controlling a random point generation direction and distance to allow the random point to move forward to anode q<new> in the direction from q<near> to q<rand> at a step length delta by utilizing a target deviation factor; carrying out collision detection in the forward process, and returning to A2 if collision is detected; if no collision is detected, storing the q<new> in the q<nodes>, and turning to A4; repeating A2 to A3 according to the updated q<nodes> until the obtained latest node q<global> meets the relational expression shown in the description; regarding the latest node q<global> as a target point, and storing the q<new> into the q<nodes>; and reversely searching at q<nodes> according tothe father-son relationship of each node to find a planned path. According to the invention, the length of the searching path can be reduced, and the phenomenon of falling into a local optimal valueor shaking near an obstacle is avoided.

Description

technical field [0001] The invention belongs to the technical field of robot path planning and generation in three-dimensional space, and in particular relates to a heuristic RRT manipulator motion planning method based on target bias optimization. Background technique [0002] Motion planning can be divided into path planning and trajectory planning. Path planning focuses on the generated path, and trajectory planning is to give the path time information. For the manipulator, its end effector is a technical object. In path planning, the main technology is the path point tracking problem. In trajectory planning, it is based on The job task requires to realize the practical application of kinematics inverse solution (position and orientation inverse solution, velocity and acceleration inverse solution), so a systematic motion planning is of great significance for solving practical problems. [0003] The RRT algorithm is a fast path planning algorithm based on random sampling...

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 Applications(China)
IPC IPC(8): B25J9/16
CPCB25J9/1664
Inventor 袁成人刘桂峰张文群郭文勇
Owner NAVAL UNIV OF ENG PLA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com