Robot group cooperative active sensing method based on self-organized mapping

A technology of self-organizing mapping and robotics, applied in the direction of two-dimensional position/channel control, etc., to achieve the effect of expanding the research field, simplifying the complexity, and reducing the computational complexity

Active Publication Date: 2019-05-24
TSINGHUA UNIV
View PDF12 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although it is also used in path planning, it is aimed at single-target 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
  • Robot group cooperative active sensing method based on self-organized mapping
  • Robot group cooperative active sensing method based on self-organized mapping
  • Robot group cooperative active sensing method based on self-organized mapping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0020] A self-organizing map-based robot group cooperative active perception method proposed by the present invention, figure 1 It is an integral part of each robot in the robot group involved in the present invention, and each robot has the same configuration, and is equipped with a bottom drive board, an industrial computer, a wireless module, a depth camera and a laser radar respectively. Among them, the robot perceives the surrounding environment through the depth camera, the laser radar is used for auxiliary detection, and the depth camera and the laser radar are collected synchronously. Handling and controlling the robot, the bottom driver board controls the work of the bottom motor to provide the robot with the power to move forward. In the robot of this embodiment, the turtlebot3 mobile robot is used as the main body, with three omnidirectional...

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 discloses a multi-robot cooperative active sensing method based on self-organized mapping. The method includes the steps: performing first-round detection according to a calculated trackand a multi-traveling salesman problem model by a robot group to form a closed-loop path; selecting a robot with the lowest ratio of traveling budget time of reaching a target observation point to actual consumed time as a winning robot, performing iterative calculation on the path point of the winning robot by a self-organized mapping network algorithm to obtain a closed-loop path comprising thetarget observation point, and detecting a current target point according to the closed-loop path through a depth camera and a laser radar by the winning robot; traversing all target points and finishing detection. A robot group cooperative active sensing problem in a scene with a large amount of information is transformed into a multi-traveling salesman mathematical model for multi-objective pathplanning, and complexity of problems is greatly simplified. The robot path point is iteratively processed by the self-organized mapping neural network algorithm, and calculation complexity is low.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and is an application combining a machine learning algorithm and a robot environment target detection technology, and in particular relates to a robot group cooperative active perception method based on self-organizing mapping. Background technique [0002] At present, the target perception technology of agents in the environment is mainly passive environment detection, target recognition and tracking, real-time positioning and map construction, etc., and the number of agents involved is mostly a single one. On the other hand, the research field of robot swarms is more focused on the formation of robot swarms, the communication mechanism between robots, and the task allocation between multiple robots, etc., and there are few achievements in the aspect of multi-robot collaborative task completion. With the rapid development of artificial intelligence technology, intelligent algorithms repres...

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): G05D1/02
Inventor 刘华平王华鲜华容赵怀林孙富春吴莹莹
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap