Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-sensor fusion positioning method for automatic driving scene

A multi-sensor fusion, automatic driving technology, applied in the direction of road network navigator, etc., can solve the problems of high price, low robustness, low positioning accuracy, etc., to achieve the effect of ensuring positioning accuracy, accurate output, and convenient use

Active Publication Date: 2019-12-31
AUTOCORE INTELLIGENT TECH NANJING CO LTD
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the conventional Kalman filter algorithm requires expensive high-precision RTK (real-time dynamic measurement technology) and IMU, and its positioning accuracy is low in viaducts, tunnels and other places where GPS signals are unstable; the existing particle filter algorithm needs deep learning The module detects road signs, matches them with the road features in the prior map, and updates the model parameters; the SLAM algorithm is less robust on the expressway where the vehicle is running fast, and it requires a high-performance computing platform
Therefore, there is no economical and accurate positioning method suitable for vehicle automatic driving in the prior art

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 automatic driving scene
  • Multi-sensor fusion positioning method for automatic driving scene
  • Multi-sensor fusion positioning method for automatic driving scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] A multi-sensor fusion positioning method disclosed in this embodiment for an automatic driving scene specifically includes the following steps:

[0043] Step 1, the GPS, IMU, Camera and vehicle ODOM installed on the car respectively collect real-time information of the car, among which, the GPS is set on the roof and is located at the center of vehicle rotation, the IMU is installed at the center of vehicle rotation, and the Camera is installed in the vehicle axis on the front windshield. The GPS mainly collects the latitude and longitude information of the vehicle’s location. In this embodiment, the GPS of the RAC-P1 model is used; the IMU collects the heading information of the vehicle, and the heading information includes the heading angle of the vehicle and the angular velocity of the heading angle. In this embodiment, the MTI-30 is used The IMU of model; Camera collects lane detection information, wherein the detection information of lane comprises the concrete lan...

Embodiment 2

[0075] In this embodiment, the meanings of the characters in the formulas have been mentioned in the summary of the invention and Embodiment 1, so details are not repeated here. Such as figure 1 As shown, a multi-sensor fusion positioning method for an automatic driving scene disclosed in this embodiment specifically includes the following steps:

[0076] Step 1, the GPS, IMU, Camera and vehicle ODOM installed on the car respectively collect real-time information of the car, among which, the GPS is set on the roof and is located at the center of vehicle rotation, the IMU is installed at the center of vehicle rotation, and the Camera is installed in the vehicle axis on the front windshield. The GPS mainly collects the latitude and longitude information of the vehicle’s location. In this embodiment, the GPS of the RAC-P1 model is used; the IMU collects the heading information of the vehicle, and the heading information includes the heading angle of the vehicle and the angular ...

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 present invention discloses a multi-sensor fusion positioning method for an automatic driving scene, which uses a low-cost sensor combined with a vector map to implement lane-level positioning through an improved particle filtering algorithm. The method provided by the present invention has obvious price advantages, and by using the method provided by the present invention, the popularizationof an autonomous driving technology can be facilitated, the positioning accuracy can be ensured, the use is more convenient, high-frequency positioning information with an adjustable frequency can beoutput, and reference data can be provided for environmental perception and body control.

Description

technical field [0001] The invention belongs to the field of automatic driving, and in particular relates to a multi-sensor fusion positioning method for automatic driving scenes. Background technique [0002] High-precision positioning is an important research topic in the field of autonomous driving. At present, high-precision integrated navigation, multi-line laser radar, camera and other sensors are commonly used in combination with high-precision maps to achieve lane-level positioning. Kalman filter, particle filter, SLAM (instant positioning and map construction) and other fusion positioning algorithms. Among them, the conventional Kalman filter algorithm requires expensive high-precision RTK (real-time dynamic measurement technology) and IMU, and its positioning accuracy is low in viaducts, tunnels and other places where GPS signals are unstable; the existing particle filter algorithm needs deep learning The module detects road signs, matches them with the road featu...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G01C21/28
CPCG01C21/28
Inventor 李赵刘心刚袁瑞廷张旸陈诚刘洁
Owner AUTOCORE INTELLIGENT TECH NANJING CO LTD