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

Robot navigation method based on Bayesian optimization multi-information gain exploration strategy

A technology for information gain and robotics, applied in the field of mobile robots

Pending Publication Date: 2022-03-15
BEIJING UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To explore the unknown environment without any map information, the robot can only obtain the range that the current sensor can perceive, so that exploring the environment in the unknown environment is transformed into a decision-making problem in an incomplete state

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 navigation method based on Bayesian optimization multi-information gain exploration strategy
  • Robot navigation method based on Bayesian optimization multi-information gain exploration strategy
  • Robot navigation method based on Bayesian optimization multi-information gain exploration strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] figure 1 For the structure diagram of the model system, refer to figure 1 , Inspired by the research of Bayesian optimization applied in various fields, the present invention provides a robot navigation model based on Bayesian optimization multiple information gain exploration strategy. The robot itself carries sensors such as odometers and RGB-D cameras, and inputs the sensors through the underlying depthimage_to_laserscan package and the Gmapping algorithm to complete robot positioning and build a two-dimensional grid map. At the same time, use the RGB-D information passed in by the robot The color map and depth map of the octree map are constructed, and then the current map information and the current pose of the robot are used as the input of the autonomous exploration algorithm proposed in this paper, the next best candidate point is calculated and the Gaussian model of the environment is updated, and finally carried out on the map A path is planned to reach the g...

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 robot navigation model based on a Bayesian optimization multi-information gain exploration strategy, and belongs to the field of mobile robots and the field of artificial intelligence. The method is realized based on ROS programming, and a simulation robot with a speedometer, an RGB-D camera and other sensors is set. The method comprises the following steps of: firstly, comprehensively measuring and extracting in a mode of fusing leading edge point clustering and a passable area on a candidate point extraction method; on the basis of a candidate point evaluation method, improved Bayesian optimization is used for calculating multiple information gains, map entropy and distance cost are comprehensively considered, then the optimal candidate point is selected, and the robot is prevented from continuously walking along repeated paths in the environment. According to the method, simulation experiment verification is carried out by using gazebo in an ROS operating system, a two-dimensional grid map and an octree map are constructed by using RGB-D information, and a mobile robot can rapidly and effectively explore an unknown environment by using a small number of steps to complete a mapping task with high quality.

Description

technical field [0001] The invention belongs to the field of mobile robots and the field of artificial intelligence, in particular to a mobile robot autonomous exploration and navigation method based on Bayesian optimization of multiple information gain exploration strategies in an unknown environment. Background technique [0002] Today, with the rapid development of the robot field, mobile robots have been widely used in various fields. Among them, the application requirements of fully autonomous mobile robots in indoor scenes are increasing. How to autonomously explore and construct maps in a priori unknown environment is a key issue in the field of robotics research, and the requirements for map construction are different under different task scenarios. For example, rescue robots in disaster-stricken environments have high requirements for the rapidity of map building, and for environments where humans have not yet set foot in but have certain research value, the accurac...

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
IPC IPC(8): G06F16/909G06F16/29G06F17/18G06K9/62
CPCG06F16/909G06F16/29G06F17/18G06F18/23213
Inventor 阮晓钢陈晓朱晓庆
Owner BEIJING UNIV OF TECH
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