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

IMU pre-integration-based laser radar online calibration method for automatic driving system

A lidar and autonomous driving technology, applied in radio wave measurement systems, instruments, etc., can solve problems such as the need for special equipment, limited flexibility, increased cost, etc., to achieve a wide range of applications, low cost, and improved safety.

Active Publication Date: 2020-06-09
TSINGHUA UNIV
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has the following defects: 1) It needs to realize the layout of specific scenes, and the use area is limited; 2) It needs special equipment, which increases additional costs; 3) It needs to collect data under special working conditions, and the flexibility is limited; 4) Only It can be performed offline, but cannot correct the external parameter error of the lidar in real time online
But related work is still blank

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
  • IMU pre-integration-based laser radar online calibration method for automatic driving system
  • IMU pre-integration-based laser radar online calibration method for automatic driving system
  • IMU pre-integration-based laser radar online calibration method for automatic driving system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in further detail below in conjunction with the embodiments given in the accompanying drawings.

[0043] Such as figure 1 As shown, the autopilot-related hardware involved in the present invention includes a laser radar, an IMU (Inertial Measurement Unit, inertial measurement unit) and a computing unit. Among them, lidar is used for obstacle detection in the automatic driving system. It will feed back the detected point cloud information to the automatic driving system in real time. The obstacle detection algorithm of automatic driving analyzes the type and position of obstacles based on the point cloud information. The IMU device usually consists of two parts: an accelerometer and an angular velocity meter, which measure the vehicle's three-axis (x, y, and z axes, respectively pointing to the vehicle's forward direction, the left side of the vehicle, and the sky) acceleration and three-axis angular velocity (respectively around x...

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 an IMU pre-integration-based laser radar external parameter estimation method for an automatic driving system. The method is based on an original vehicle-mounted sensor of an automatic driving system. The invention provides an end-to-end laser radar external parameter online calibration method. Complex mathematical model derivation and optimization are avoided, point clouddata and vehicle state trajectory data of the laser radar are processed by using the data analysis capability of the deep convolutional neural network, an external parameter error of the laser radar is estimated online in real time, so real-time correction of external parameters of the laser radar is realized, accuracy and stability of the environmental perception function of the automatic drivingsystem are improved, and driving safety of the automatic driving system is ensured.

Description

technical field [0001] The invention relates to a laser radar external parameter estimation method for an automatic driving system, in particular to an online calibration method for a laser radar of an automatic driving system based on IMU pre-integration. Background technique [0002] The automatic driving system can liberate the hands of the driver and bring passengers a new experience of safety, efficiency and comfort. It is a new growth point in the automotive and transportation industries and has attracted attention from all over the world. Major automakers in the world, such as Daimler Group, Volkswagen Group, and General Motors, have launched mass production plans for autonomous driving systems. Internet companies such as Google, Uber, and Baidu have also successively established their own autonomous driving divisions. Launched an autonomous driving research and development platform and a shared travel plan. [0003] In order to accurately perceive environmental info...

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): G01S7/497
CPCG01S7/497
Inventor 秦晓辉王晓伟边有钢徐彪谢国涛胡满江杨泽宇胡展溢周华健钟志华
Owner TSINGHUA UNIV