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

A planning method and device for robot collision avoidance path

A robot and path technology, applied in the direction of navigation calculation tools, etc., can solve problems such as dependence on sampling parameters and discrete collision detection distance parameters

Active Publication Date: 2017-02-08
SHENZHEN INSTITUTE OF INFORMATION TECHNOLOGY +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The embodiment of the present invention provides a planning method and device for a robot collision avoidance path, aiming at solving complex problems such as high-dimensional spaces and complex obstacle environments in the prior art, which rely heavily on selected sampling parameters and discrete collision detection The problem with the distance parameter

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
  • A planning method and device for robot collision avoidance path
  • A planning method and device for robot collision avoidance path
  • A planning method and device for robot collision avoidance path

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] figure 1 The implementation process of the method for planning a robot collision avoidance path provided by the first embodiment of the present invention is shown, and the details are as follows:

[0066] In step S101, according to the initial configuration q of the robot s and the target configuration q g Calculate the initial value r of the collision detection distance parameter col .

[0067] In the embodiment of the present invention, the initial configuration q of the robot is initialized first. s and the target configuration q g , and then according to the initial configuration q s and the target configuration q g Calculate the initial value r of the collision detection distance col , where the calculated r col Satisfy:

[0068] r col =||q g -q s ||.

[0069] In step S102, according to the initial configuration q s , target configuration q g A bidirectional fast dense search tree is constructed, and the bidirectional fast dense search tree includes ...

Embodiment 2

[0136] Figure 8 A specific structural block diagram of the apparatus for planning a collision avoidance path of a robot provided by Embodiment 2 of the present invention is shown. For convenience of description, only parts related to the embodiment of the present invention are shown. The device 8 includes: a collision detection distance initialization unit 41 , a search tree construction unit 42 , a collision detection distance setting unit 43 , a planned path generation unit 44 , a collision detection unit 45 , a collision detection distance update unit 46 and a planned path update unit 47 .

[0137] Among them, the collision detection distance initialization unit 41 is used for according to the initial configuration q of the robot s and the target configuration q g Calculate the initial value r of the collision detection distance parameter col ;

[0138] The search tree construction unit 42 is used for according to the initial configuration q s , target configuration q ...

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 is suitable for the field of robot collision prevention and control, and provides a planning method and device of a robot collision prevention path. The method comprises the following steps: firstly, calculating according to an initial configuration qs and a target configuration qg of a robot so as to obtain an initial value rcol of a collision detection distance parameter; then constructing a bidirectional rapid intensive search tree according to qs and qg, and setting the value of a collision detection distance parameter of the bidirectional rapid intensive search tree to be rcol; then generating a robot planning path according to qs and qg; carrying out collision detection on the robot at discrete sampling configuration points respectively on the robot planning path, and updating the value rcol to be half of rcol if the robot collides with a barrier at one discrete configuration point; and generating a novel robot planning path according to the updated rcol until the robot does not collide with the barrier at all discrete configuration points on the new robot planning path. According to the invention, if the robot collides with the barrier, the collision detection distance parameter rcol can be adaptively reduced by half, so that the robot can successfully pass through a narrow channel or a barrier intensive space.

Description

technical field [0001] The invention belongs to the field of robot collision avoidance and manipulation, and in particular relates to a planning method and device for a robot collision avoidance path. Background technique [0002] At present, the sampling-based planning technology has been widely used in the fields of collision avoidance and manipulation of high-degree-of-freedom intelligent robots, and has become a research hotspot of widespread concern at home and abroad. The significant advantage of this method is that it only needs to approximate the construction of the free configuration space based on random sampling, thus avoiding the need to completely and accurately construct all effective C-space models using methods such as skeletal grids and grid decomposition, in order to find the results brought by accurate analysis. The PSPACE problem avoids the NP problem of exponentially increasing storage space and computational complexity caused by high degrees of freedom....

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): G01C21/20
CPCG01C21/20
Inventor 李华忠梁永生但唐仁唐飞
Owner SHENZHEN INSTITUTE OF INFORMATION TECHNOLOGY
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