A Normal Distribution Transform-Based Radar Odometry Designed For Scanning and Automotive Radars

被引：37
作者：
Kung, Pou-Chun [1 ]
Wang, Chieh-Chih [2 ,3 ]
Lin, Wen-Chieh [4 ]
机构：
[1] Natl Chiao Tung Univ, Grad Degree Program Robot, Hsinchu, Taiwan
[2] Natl Chiao Tung Univ, Dept Elect & Comp Engn, Hsinchu, Taiwan
[3] Ind Technol Res Inst, Mech & Mechatron Syst Res Labs, Hsinchu, Taiwan
[4] Natl Chiao Tung Univ, Dept Comp Sci, Hsinchu, Taiwan
来源：
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) | 2021年
关键词：
Radar; Odometry; Scan Matching; Autonomous Driving; MOTION ESTIMATION;
D O I：
10.1109/ICRA48506.2021.9561413
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Existing radar sensors can be classified into automotive and scanning radars. While most radar odometry (RO) methods are only designed for a specific type of radar, our RO method adapts to both scanning and automotive radars. Our RO is simple yet effective, where the pipeline consists of thresholding, probabilistic submap building, and an Normal Distribution Transform-based (NDT-based) radar scan matching. The proposed RO has been tested on two public radar datasets: the Oxford Radar RobotCar dataset and the nuScenes dataset, which provide scanning and automotive radar data respectively. The results show that our approach surpasses state-of-the-art RO using either automotive or scanning radar by reducing translational error by 51% and 30%, respectively, and rotational error by 17% and 29%, respectively. Besides, we show that our RO achieves centimeter-level accuracy as lidar odometry, and automotive and scanning RO have similar accuracy.
引用
收藏
页码：14417 / 14423
页数：7
相关论文
共 32 条
[1]  
aftescu S. S., 2020, ARXIV200109438
[2]  
Aldera R, 2019, IEEE INT C INTELL TR, P2835, DOI 10.1109/ITSC.2019.8917111
[3]  
Aldera R, 2019, IEEE INT CONF ROBOT, P1190, DOI [10.1109/ICRA.2019.8794014, 10.1109/icra.2019.8794014]
[4]  
[Anonymous], 2015, 2015 EUR C MOB ROB E
[5]  
Barnes D., 2019, C ROBOT LEARN CORL
[6]  
Barnes D, 2020, IEEE INT CONF ROBOT, P6433, DOI [10.1109/ICRA40945.2020.9196884, 10.1109/icra40945.2020.9196884]
[7]  
Barnes D, 2020, IEEE INT CONF ROBOT, P9484, DOI [10.1109/ICRA40945.2020.9196835, 10.1109/icra40945.2020.9196835]
[8]   The normal distributions transform: A new approach to laser scan matching [J].
Biber, P .
IROS 2003: PROCEEDINGS OF THE 2003 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, 2003, :2743-2748
[9]   Do We Need to Compensate for Motion Distortion and Doppler Effects in Spinning Radar Navigation? [J].
Burnett, Keenan ;
Schoellig, Angela P. ;
Barfoot, Timothy D. .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (02) :771-778
[10]   nuScenes: A multimodal dataset for autonomous driving [J].
Caesar, Holger ;
Bankiti, Varun ;
Lang, Alex H. ;
Vora, Sourabh ;
Liong, Venice Erin ;
Xu, Qiang ;
Krishnan, Anush ;
Pan, Yu ;
Baldan, Giancarlo ;
Beijbom, Oscar .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :11618-11628
1234