A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban Driving
Real-time and high-precision localization information is vital for many modules of unmanned vehicles. At present, a high-cost RTK (Real Time Kinematic) and IMU (Integrated Measurement Unit) integrated navigation system is often used, but its accuracy cannot meet the requirements and even fails in ma...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/11/11/1348 |
id |
doaj-766348a7b391414293ec379a2afabe88 |
---|---|
record_format |
Article |
spelling |
doaj-766348a7b391414293ec379a2afabe882020-11-25T02:10:39ZengMDPI AGRemote Sensing2072-42922019-06-011111134810.3390/rs11111348rs11111348A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban DrivingHang Liu0Qin Ye1Hairui Wang2Liang Chen3Jian Yang4College of Surveying and Geo-Informatics, Tongji University, Shanghai 200092, ChinaCollege of Surveying and Geo-Informatics, Tongji University, Shanghai 200092, ChinaBeijing Momenta Technology Company Limited, Beijing 100190, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaSchool of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, ChinaReal-time and high-precision localization information is vital for many modules of unmanned vehicles. At present, a high-cost RTK (Real Time Kinematic) and IMU (Integrated Measurement Unit) integrated navigation system is often used, but its accuracy cannot meet the requirements and even fails in many scenes. In order to reduce the costs and improve the localization accuracy and stability, we propose a precise and robust segmentation-based Lidar (Light Detection and Ranging) localization system aided with MEMS (Micro-Electro-Mechanical System) IMU and designed for high level autonomous driving. Firstly, we extracted features from the online frame using a series of proposed efficient low-level semantic segmentation-based multiple types feature extraction algorithms, including ground, road-curb, edge, and surface. Next, we matched the adjacent frames in Lidar odometry module and matched the current frame with the dynamically loaded pre-build feature point cloud map in Lidar localization module based on the extracted features to precisely estimate the 6DoF (Degree of Freedom) pose, through the proposed priori information considered category matching algorithm and multi-group-step L-M (Levenberg-Marquardt) optimization algorithm. Finally, the lidar localization results were fused with MEMS IMU data through a state-error Kalman filter to produce smoother and more accurate localization information at a high frequency of 200Hz. The proposed localization system can achieve 3~5 cm in position and 0.05~0.1° in orientation RMS (Root Mean Square) accuracy and outperform previous state-of-the-art systems. The robustness and adaptability have been verified with localization testing data more than 1000 Km in various challenging scenes, including congested urban roads, narrow tunnels, textureless highways, and rain-like harsh weather.https://www.mdpi.com/2072-4292/11/11/1348Lidar localization systemunmanned vehiclesegmentation-based feature extractioncategory matchingmulti-group-step L-M optimizationmap management |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hang Liu Qin Ye Hairui Wang Liang Chen Jian Yang |
spellingShingle |
Hang Liu Qin Ye Hairui Wang Liang Chen Jian Yang A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban Driving Remote Sensing Lidar localization system unmanned vehicle segmentation-based feature extraction category matching multi-group-step L-M optimization map management |
author_facet |
Hang Liu Qin Ye Hairui Wang Liang Chen Jian Yang |
author_sort |
Hang Liu |
title |
A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban Driving |
title_short |
A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban Driving |
title_full |
A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban Driving |
title_fullStr |
A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban Driving |
title_full_unstemmed |
A Precise and Robust Segmentation-Based Lidar Localization System for Automated Urban Driving |
title_sort |
precise and robust segmentation-based lidar localization system for automated urban driving |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-06-01 |
description |
Real-time and high-precision localization information is vital for many modules of unmanned vehicles. At present, a high-cost RTK (Real Time Kinematic) and IMU (Integrated Measurement Unit) integrated navigation system is often used, but its accuracy cannot meet the requirements and even fails in many scenes. In order to reduce the costs and improve the localization accuracy and stability, we propose a precise and robust segmentation-based Lidar (Light Detection and Ranging) localization system aided with MEMS (Micro-Electro-Mechanical System) IMU and designed for high level autonomous driving. Firstly, we extracted features from the online frame using a series of proposed efficient low-level semantic segmentation-based multiple types feature extraction algorithms, including ground, road-curb, edge, and surface. Next, we matched the adjacent frames in Lidar odometry module and matched the current frame with the dynamically loaded pre-build feature point cloud map in Lidar localization module based on the extracted features to precisely estimate the 6DoF (Degree of Freedom) pose, through the proposed priori information considered category matching algorithm and multi-group-step L-M (Levenberg-Marquardt) optimization algorithm. Finally, the lidar localization results were fused with MEMS IMU data through a state-error Kalman filter to produce smoother and more accurate localization information at a high frequency of 200Hz. The proposed localization system can achieve 3~5 cm in position and 0.05~0.1° in orientation RMS (Root Mean Square) accuracy and outperform previous state-of-the-art systems. The robustness and adaptability have been verified with localization testing data more than 1000 Km in various challenging scenes, including congested urban roads, narrow tunnels, textureless highways, and rain-like harsh weather. |
topic |
Lidar localization system unmanned vehicle segmentation-based feature extraction category matching multi-group-step L-M optimization map management |
url |
https://www.mdpi.com/2072-4292/11/11/1348 |
work_keys_str_mv |
AT hangliu apreciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT qinye apreciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT hairuiwang apreciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT liangchen apreciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT jianyang apreciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT hangliu preciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT qinye preciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT hairuiwang preciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT liangchen preciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving AT jianyang preciseandrobustsegmentationbasedlidarlocalizationsystemforautomatedurbandriving |
_version_ |
1724918392705515520 |