Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Grey wolf optimization algorithm-based RBPF-SLAM improvement method

A technology of RBPF-SLAM, optimization algorithm, applied in the direction of calculation, calculation model, electromagnetic wave re-radiation, etc., can solve the problem that the distribution of the particle set cannot well represent the posterior probability density, deviation, particle degradation, etc.

Inactive Publication Date: 2019-08-06
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the iterative process of this algorithm, there will be problems of particle degradation and particle dissipation, resulting in the distribution of the particle set not being able to represent the true posterior probability density well, resulting in poor positioning and mapping accuracy or even completely deviated from it.

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
  • Grey wolf optimization algorithm-based RBPF-SLAM improvement method
  • Grey wolf optimization algorithm-based RBPF-SLAM improvement method
  • Grey wolf optimization algorithm-based RBPF-SLAM improvement method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Such as figure 1 As shown, an indoor positioning method based on laser SLAM includes the following steps:

[0046] The first step is sampling. Particles based on the previous moment and the odometer data obtained at this moment to generate a preliminary estimated state at time t This step consists of transitioning from the state distribution p(x t |u t ,x t-1 ) sampling, the sampled particles are evenly distributed with a particle weight of 1 / N, where N is the number of particles.

[0047] In the second step, according to the data obtained from the lidar sensor and the independent map of each particle at the last moment Execute the mountain-climbing scanning matching algorithm to perform preliminary optimization on the particle pose in the previous step. The mountain-climbing scanning matching algorithm starts from the current pose, and fine-tunes the pose on the surrounding grids as its comparison point. If the matching degree of the current pose is the highes...

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 grey wolf optimization algorithm-based RBPF-SLAM improvement method. The method is used for further optimizing the distribution prediction of a proposal distribution function and improving the positioning and modeling precision of an algorithm. A grey wolf algorithm model is simple and has high optimization performance; with a unique search capability and an explorationdevelopment balancing mode, the algorithm has a better global search capability and lower space complexity compared with algorithms such as a PSO. According to the algorithm, the local exploration andglobal development capability of the grey wolf optimization algorithm are utilized to improve the estimation performance of an RBPF, so that particles with low weight can rush to an optimal value, and the estimated value of the particles can be further optimized in the running process. In the improved algorithm, particle degradation is relieved to a certain extent, and the number of particles required by accurate positioning and modeling is effectively reduced.

Description

technical field [0001] The present invention relates to the scientific research on the positioning and map construction of mobile robots. The gray wolf optimization algorithm is used to further optimize the particle pose in the RBPF-SLAM algorithm, thereby further optimizing the distribution of particle sets and improving the accuracy of positioning and mapping. Background technique [0002] The degree of intelligence of a mobile robot is mainly reflected in its ability to navigate autonomously in its environment. As the core of the autonomous navigation system, instant localization and mapping (SLAM) technology is considered to be an important factor for the realization of intelligence and autonomy of mobile robots. premise. The SLAM technology of mobile robots is the key prerequisite for robots to realize intelligence and autonomous navigation. It is a hot research issue in the field of robots. and industrialization play an extremely important role. [0003] LiDAR has th...

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): G01S17/89G06N3/00
CPCG01S17/89G01S17/006G06N3/006
Inventor 宫大为李安旭代小林何志恒何嘉诚
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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
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