A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDAR
The registration of point clouds in urban environments faces problems such as dynamic vehicles and pedestrians, changeable road environments, and GPS inaccuracies. The state-of-the-art methodologies have usually combined the dynamic object tracking and/or static feature extraction data into a point...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2079-9292/8/1/43 |
| _version_ | 1798003647013978112 |
|---|---|
| author | Rendong Wang Youchun Xu Miguel Angel Sotelo Yulin Ma Thompson Sarkodie-Gyan Zhixiong Li Weihua Li |
| author_facet | Rendong Wang Youchun Xu Miguel Angel Sotelo Yulin Ma Thompson Sarkodie-Gyan Zhixiong Li Weihua Li |
| author_sort | Rendong Wang |
| collection | DOAJ |
| description | The registration of point clouds in urban environments faces problems such as dynamic vehicles and pedestrians, changeable road environments, and GPS inaccuracies. The state-of-the-art methodologies have usually combined the dynamic object tracking and/or static feature extraction data into a point cloud towards the solution of these problems. However, there is the occurrence of minor initial position errors due to these methodologies. In this paper, the authors propose a fast and robust registration method that exhibits no need for the detection of any dynamic and/or static objects. This proposed methodology may be able to adapt to higher initial errors. The initial steps of this methodology involved the optimization of the object segmentation under the application of a series of constraints. Based on this algorithm, a novel multi-layer nested RANSAC algorithmic framework is proposed to iteratively update the registration results. The robustness and efficiency of this algorithm is demonstrated on several high dynamic scenes of both short and long time intervals with varying initial offsets. A LiDAR odometry experiment was performed on the KITTI data set and our extracted urban data-set with a high dynamic urban road, and the average of the horizontal position errors was compared to the distance traveled that resulted in 0.45% and 0.55% respectively. |
| first_indexed | 2024-04-11T12:11:05Z |
| format | Article |
| id | doaj.art-e0ad66e96c634bb8a04cdacc1cdfc436 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-11T12:11:05Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-e0ad66e96c634bb8a04cdacc1cdfc4362022-12-22T04:24:37ZengMDPI AGElectronics2079-92922019-01-01814310.3390/electronics8010043electronics8010043A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDARRendong Wang0Youchun Xu1Miguel Angel Sotelo2Yulin Ma3Thompson Sarkodie-Gyan4Zhixiong Li5Weihua Li6Department of Military Vehicles, Military Transportation University, Tianjin 300161, ChinaDepartment of Military Vehicles, Military Transportation University, Tianjin 300161, ChinaDepartment of Computer Engineering, University of Alcalá, 28801 Alcalá de Henares (Madrid), SpainSuzhou Automotive Research Institute, Tsinghua University, Suzhou 215134, ChinaLaboratory for Industrial Metrology and Automation, College of Engineering, University of Texas, El Paso, TX 79968, USASchool of Mechanical, Materials, Mechatronic and Biomedical Engineering, University of Wollongong, Wollongong, NSW 2522, AustraliaSchool of Mechanical, Materials, Mechatronic and Biomedical Engineering, University of Wollongong, Wollongong, NSW 2522, AustraliaThe registration of point clouds in urban environments faces problems such as dynamic vehicles and pedestrians, changeable road environments, and GPS inaccuracies. The state-of-the-art methodologies have usually combined the dynamic object tracking and/or static feature extraction data into a point cloud towards the solution of these problems. However, there is the occurrence of minor initial position errors due to these methodologies. In this paper, the authors propose a fast and robust registration method that exhibits no need for the detection of any dynamic and/or static objects. This proposed methodology may be able to adapt to higher initial errors. The initial steps of this methodology involved the optimization of the object segmentation under the application of a series of constraints. Based on this algorithm, a novel multi-layer nested RANSAC algorithmic framework is proposed to iteratively update the registration results. The robustness and efficiency of this algorithm is demonstrated on several high dynamic scenes of both short and long time intervals with varying initial offsets. A LiDAR odometry experiment was performed on the KITTI data set and our extracted urban data-set with a high dynamic urban road, and the average of the horizontal position errors was compared to the distance traveled that resulted in 0.45% and 0.55% respectively.http://www.mdpi.com/2079-9292/8/1/43intelligent vehiclesLiDAR odometryrange sensingsimultaneous localization and mapping (SLAM) |
| spellingShingle | Rendong Wang Youchun Xu Miguel Angel Sotelo Yulin Ma Thompson Sarkodie-Gyan Zhixiong Li Weihua Li A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDAR Electronics intelligent vehicles LiDAR odometry range sensing simultaneous localization and mapping (SLAM) |
| title | A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDAR |
| title_full | A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDAR |
| title_fullStr | A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDAR |
| title_full_unstemmed | A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDAR |
| title_short | A Robust Registration Method for Autonomous Driving Pose Estimation in Urban Dynamic Environment Using LiDAR |
| title_sort | robust registration method for autonomous driving pose estimation in urban dynamic environment using lidar |
| topic | intelligent vehicles LiDAR odometry range sensing simultaneous localization and mapping (SLAM) |
| url | http://www.mdpi.com/2079-9292/8/1/43 |
| work_keys_str_mv | AT rendongwang arobustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT youchunxu arobustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT miguelangelsotelo arobustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT yulinma arobustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT thompsonsarkodiegyan arobustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT zhixiongli arobustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT weihuali arobustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT rendongwang robustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT youchunxu robustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT miguelangelsotelo robustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT yulinma robustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT thompsonsarkodiegyan robustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT zhixiongli robustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar AT weihuali robustregistrationmethodforautonomousdrivingposeestimationinurbandynamicenvironmentusinglidar |