Single-line laser radar obstacle detection method for fully automatic unmanned rail vehicle

A single-line laser radar and rail vehicle technology, applied in the field of remote control and monitoring, can solve the problems of large size, low efficiency, and difficult to use, and achieve the effect of miniaturization

Pending Publication Date: 2019-06-25
成都宇俊盛科技有限公司
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complexity of the criss-crossing tracks and irregular track obstacles, such as landslides and landslides, which seriously hinder the unmanned driving of rail vehicles, it is necessary

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
  • Single-line laser radar obstacle detection method for fully automatic unmanned rail vehicle
  • Single-line laser radar obstacle detection method for fully automatic unmanned rail vehicle
  • Single-line laser radar obstacle detection method for fully automatic unmanned rail vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Example 1: see figure 1 , figure 2 , A single-line lidar obstacle detection method for fully automatic unmanned rail vehicles, the method steps are as follows,

[0036] a. The lidar and the controller are connected through Ethernet, and the UDP protocol is used to send data frames to the controller; the UDP protocol is used to send data frames to the controller at a frequency of 100 Hz, and each frame of data contains 2000 groups of data, one every 0.18° Group, each group of data contains three data of reflection point distance, angle and reflection signal intensity;

[0037] b. The controller performs dense repetitive data filtering and shaping processing on each frame of data;

[0038] The characteristic of lidar scanning is that the closer the points are, the denser the points, which leads to a process of dense to sparse points on a straight line from near to far. If dense repetitive data filtering is not performed, the dense points will be sparse, which will lead to close...

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 single-line laser radar obstacle detection method for a fully automatic unmanned rail vehicle. The method comprises steps of a, transmitting, by a laser radar, a data frame to a controller; b, processing each frame of data; c, performing image segmentation; d, converting the data into Cartesian coordinates; e, performing calibration and standardization; f, determining thecorresponding angle of the driving direction of the laser radar; g, intercepting data within a valid angle range; h, performing a Hough transform and obtaining a scan curve of track walls or guardrails on both sides of the rails; i, performing a sliding mean filtering process on two linear parameters; j, determining whether there is an obstacle and feeding a result back to the controller. Compared with the prior art, the single-line laser radar obstacle detection method of the invention is an important part of a vehicle driving safety guarantee system, can ensure that the unmanned rail vehicle can accurately detect obstacles that may collide with the rail vehicle during the driving process, and takes effective measures to avoid collision accidents.

Description

Technical field [0001] The invention relates to the field of remote control and monitoring, in particular to a single-line laser radar obstacle detection method for fully automatic unmanned rail vehicles. Background technique [0002] Existing railway, subway and other track defects are detected by manual walking or large-scale manned automatic maintenance vehicles. The efficiency of manual walking monitoring is low, and it is prone to misdetection; at present, there is no long-distance (tens or even hundreds of kilometers) unmanned driving detection system in the railway rail transit system. Unmanned driving can reduce the safety level of the inspection vehicle, and its efficiency in performing operations is much higher than that of manual inspection. However, due to the complexity of the criss-crossing of tracks, and irregular track obstacles, such as rockfalls and collapses on the mountain, cause serious obstacles to the unmanned driving of railcars, so human detection is req...

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
Inventor 刘俊
Owner 成都宇俊盛科技有限公司
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