Multi-sensor fusion positioning method for low-speed parking and driving scene

A driving scene and integrated positioning technology, which is applied in the field of vehicle electronics, can solve the problems that cannot meet the application requirements of typical automatic driving scenes, and the positioning method is single and unusable, so as to improve the positioning accuracy of parking, control the system cost, and improve the The effect of positioning accuracy

Active Publication Date: 2019-06-28
ZHEJIANG LEAPMOTOR TECH CO LTD
View PDF7 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to overcome the problems in the prior art that the existing vehicle-mounted system has a single positioning method and low precision, is only suitable for vehicle-mounted navigation applications, and cannot be used in scenarios such as tunnels and und

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
  • Multi-sensor fusion positioning method for low-speed parking and driving scene
  • Multi-sensor fusion positioning method for low-speed parking and driving scene
  • Multi-sensor fusion positioning method for low-speed parking and driving scene

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0056] Example: such as figure 1 The shown multi-sensor fusion positioning method for low-speed parking driving scenarios includes the following steps:

[0057] (1-1) Semantic map definition:

[0058] The semantic structured data of the parking lot shown in the definition is as figure 2 As shown, it mainly includes parking space information, lane information and positioning road sign information, which can be abstracted from the parking lot design drawing. Among them, parking space information mainly includes but not limited to attributes such as parking space id, length and width, orientation, and lane to which it belongs; lane information mainly includes but not limited to attributes such as lane id, length, curvature, boundary type, front and rear associated lanes, and floor to which it belongs; positioning road signs The information mainly includes but not limited to parking space id, road guidance sign and aerial suspension guide sign, etc.; all kinds of information are store...

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 multi-sensor fusion positioning method for a low-speed parking and driving scene. The method comprises the following steps: 1, semantic map definition, namely defining an offline map data format for parking application scenarios based on positioning algorithm capabilities and interfaces, wherein the offline map data format mainly comprises road data required for global routing and road sign data required for positioning; 2, multi-perceptual fusion odometer, which mainly comprises visual and wheel speedometer or inertial navigation sensor data fusion, and vehicle mileage estimation based on kinematic Kalman filtering; 3, visual road sign detection and matching, which mainly comprises steps of extracting priori landmark information contained in an offline semantic map, and constructing corresponding scene semantic description to match the map semantic information; 4, positioning correction: performing positioning mileage correction according to the visual road sign matching information to form a closed loop correction of the mileage and positioning information. The method provided by the invention has the characteristics that system cost can be controlled, system feasibility is improved and positioning accuracy is high.

Description

technical field [0001] The invention relates to the technical field of vehicle electronics, in particular to a multi-sensing fusion positioning method for low-speed parking driving scenes that can control system cost, improve system feasibility and high positioning accuracy. Background technique [0002] At present, the research and development of autonomous driving technology and systems are mostly based on the two application scenarios of highway and parking. The system composition usually includes sub-modules such as perception, positioning, planning, and decision-making control. Compared with the assisted driving system, positioning is an indispensable component module in the high-level automatic driving system, and it is also the main barrier to distinguish the two. According to the different requirements of autonomous driving applications, the methods and devices used by the positioning module are not exactly the same. The existing vehicle system positioning method is...

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): G01C21/16G01C21/28B60W30/06
Inventor 缪其恒杜卓闫坤王江明许炜
Owner ZHEJIANG LEAPMOTOR TECH CO LTD
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