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

Real-time path planning method based on improved Kstar algorithm and deep learning

A technology of real-time path planning and deep learning, which is applied in the fields of computer science and intelligent transportation systems, can solve the problems of high computational complexity of dynamic real-time planning algorithms, inability to cope with real-time traffic environment, and aggravate traffic pressure, etc., to achieve enhanced detection and tracking ability, reduce the number of planning, and reduce the effect of noise interference

Active Publication Date: 2021-05-04
HANGZHOU DIANZI UNIV
View PDF8 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Real-time optimal route planning is an important component of the intelligent transportation field, which can effectively relieve traffic pressure and reduce traffic congestion. However, the existing simple dynamic real-time planning has been unable to cope with the complex real-time traffic environment, and the complex dynamic real-time planning algorithm is computationally complex. At the same time, the existing real-time path planning system usually calculates the same path repeatedly and needs to re-plan the path after the path estimate exceeds the threshold, which will take more time
Most of the existing road evaluation formulas simply measure the time it takes to pass the road or the length of the road. There is a section of the road that is relatively congested but still guides users to this section, which will increase the pressure on traffic

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
  • Real-time path planning method based on improved Kstar algorithm and deep learning
  • Real-time path planning method based on improved Kstar algorithm and deep learning
  • Real-time path planning method based on improved Kstar algorithm and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] A real-time path planning method based on the improved Kstar algorithm and deep learning provided by the present invention will be further described below in conjunction with the accompanying drawings.

[0060] see Figure 1-2 , shown as a flow chart of the method, the specific steps are as follows:

[0061] Step (1): Set the update cycle, generally set to five minutes;

[0062] Step (2): obtain the target position according to the user's navigation request, and obtain the user's current position according to the GPS satellite;

[0063] Step (3): Load the map between the current location and the target location and the relevant historical information of the included roads, use the improved Kstar algorithm to obtain k candidate paths, divide the nodes on the map into layers, and divide them into provinces, cities, etc. Hierarchical network. In step (3), the following steps are further included:

[0064] Step (3.1): Determine and mark the starting point s and the targ...

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 real-time path planning method based on an improved Kstar algorithm and deep learning. According to the real-time path planning method, a k-shortest paths problem is combined into real-time path planning, k excellent to-be-selected paths are quickly and efficiently found out by improving the Kstar algorithm, a more reasonable road evaluation formula is put forward, the time for passing through the road and the congestion index of the road are comprehensively considered, and the traffic pressure is relieved while the optimal path is found out. The improved Kstar algorithm is used for regionalizing a road map, the speed of heuristic search is greatly increased, efficient data structures such as heaps and path structure diagrams are constructed, unnecessary memory waste is optimized, a plurality of to-be-selected paths are quickly obtained under the condition that the time complexity of the method is close to that of a conventional optimal path algorithm, and the number of unnecessary navigation route planning times is effectively reduced.

Description

technical field [0001] The invention relates to the technical fields of computer science and intelligent transportation systems, in particular to a real-time path planning method based on improved Kstar algorithm and deep learning. Background technique [0002] With the development of cities and the popularity of vehicles, road congestion has become an important and difficult point in traffic route planning. The waste of time and space and economic costs caused by congestion are constantly increasing. Reasonable real-time optimal route planning has become an urgent need for the development of intelligent transportation. need. [0003] Real-time optimal route planning is an important component of the intelligent transportation field, which can effectively relieve traffic pressure and reduce traffic congestion. However, the existing simple dynamic real-time planning has been unable to cope with the complex real-time traffic environment, and the complex dynamic real-time planni...

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): G05D1/02
CPCG05D1/0276
Inventor 袁友伟周威炜葛云阳鄢腊梅
Owner HANGZHOU DIANZI UNIV
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