Improved method for planning paths of driverless vehicles by aid of rapidly random-exploring trees

A technology for path planning and unmanned vehicles, applied in vehicle position/route/height control, motor vehicles, two-dimensional position/channel control, etc., can solve problems such as inability to follow, follow, and non-smooth paths, and achieve smoothness Direct followable path effects

Active Publication Date: 2018-06-22
TONGJI UNIV
View PDF5 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] But it also has some obvious defects: the randomness of the algorithm will lead to the existence of more redundant nodes, and the generated path is not a smooth path, which cannot be directly followed by an agent with non-holonomic constraints
Real-time motion planning with applications to au

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
  • Improved method for planning paths of driverless vehicles by aid of rapidly random-exploring trees
  • Improved method for planning paths of driverless vehicles by aid of rapidly random-exploring trees
  • Improved method for planning paths of driverless vehicles by aid of rapidly random-exploring trees

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] The present invention provides a two-way pruning optimization RRT path planning algorithm based on non-holonomic constraints of unmanned vehicles, which specifically includes the following steps:

[0040] S1: Use the RRT algorithm to search for a path:

[0041] Such as figure 1 The schematic diagram of the RRT algorithm node expansion is shown. The algorithm takes the starting point as the root node, generates a sampling node uniformly and randomly each time, and selects the point closest to it on the tree. From this point to the direction of the sampling point, follow a fixed step Long expand the next node, and repeat the above process until the target node is added to the tree, and a path from the start point to the end point is found.

[0042] In the obstacle environment, the path generated by using the above RRT planning algorithm is as follows: figure 2 shown. figure 2 , the black bar area is the obstacle space, the white area is the free space, the dot in the...

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

PropertyMeasurementUnit
Angleaaaaaaaaaa
Login to view more

Abstract

The invention relates to an improved method for planning paths of driverless vehicles by the aid of rapidly random-exploring trees. The improved method is characterized by particularly comprising steps of 1), searching and acquiring an initial path from a starting point to an end point by the aid of RRT (rapidly random-exploring tree) algorithms; 2), pruning the initial path by the aid of one-waypruning processes to obtain preliminary pruned paths; 3), further reducing the lengths of the preliminary pruned paths by the aid of bidirectional pruning processes; 4), removing sharp included angleson the paths by the aid of peak clipping processes; 5), carrying out smoothing processing on the paths without clipped peaks to obtain follow paths of the driverless vehicles. Compared with the priorart, the improved method has the advantages that the paths are short, non-holonomic constraints are taken into consideration, and the like.

Description

technical field [0001] The invention relates to the field of path planning for unmanned vehicles, in particular to an improved fast search random tree path planning method for unmanned vehicles. Background technique [0002] Due to the advantages of unmanned vehicles in reducing traffic accidents and casualties, alleviating and reducing traffic congestion, and reducing the energy consumed by users in driving, etc., they have received extensive attention from academia and industry. The implementation of autonomous vehicles involves various fields, including perception, planning, decision-making, and control technologies. To realize autonomous navigation of unmanned vehicles, global path planning is of great significance. Path planning capability is the foundation of unmanned vehicles. Only unmanned vehicles with good path planning capabilities can truly liberate humans and autonomously take humans to their destinations. [0003] Path planning refers to finding a path from a...

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
CPCG05D1/0221G05D2201/02
Inventor 王祝萍李运松张皓陈启军
Owner TONGJI 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