AI-IMU Dead-Reckoning

被引:210
作者
Brossard, Martin [1 ]
Barrau, Axel [1 ,2 ]
Bonnabel, Silvere [1 ,3 ]
机构
[1] PSL Res Univ, MINES ParisTech, Ctr Robot, F-75006 Paris, France
[2] Safran Tech, Grp Safran, Rue Jeunes Bois Chateaufort, F-78772 Magny Les Hameaux, France
[3] Univ New Caledonia, Sea, Noumea 98851, New Caledonia
来源
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES | 2020年 / 5卷 / 04期
关键词
Localization; deep learning; invariant extended Kalman filter; KITTI dataset; inertial navigation; inertial measurement unit (IMU); KALMAN FILTER; MODEL; LOCALIZATION; CONSTRAINTS; ODOMETRY;
D O I
10.1109/TIV.2020.2980758
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a novel accurate method for dead-reckoning of wheeled vehicles based only on an Inertial Measurement Unit (IMU). In the context of intelligent vehicles, robust and accurate dead-reckoning based on the IMU may prove useful to correlate feeds from imaging sensors, to safely navigate through obstructions, or for safe emergency stops in the extreme case of exteroceptive sensors failure. The key components of the method are the Kalman filter and the use of deep neural networks to dynamically adapt the noise parameters of the filter. The method is tested on the KITTI odometry dataset, and our dead-reckoning inertial method based only on the IMU accurately estimates 3D position, velocity, orientation of the vehicle and self-calibrates the IMU biases. We achieve on average a 1.10% translational error and the algorithm competes with top-ranked methods which, by contrast, use LiDAR or stereo vision.
引用
收藏
页码:585 / 595
页数:11
相关论文
共 53 条
[1]  
Abbeel P., 2005, RSS, V2, P1
[2]   Robust Relative Navigation by Integration of ICP and Adaptive Kalman Filter Using Laser Scanner and IMU [J].
Aghili, Farhad ;
Su, Chun-Yi .
IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2016, 21 (04) :2015-2026
[3]  
Barrau A., 2016, Patent, Patent No. [15/037,653, 15037653]
[4]   Invariant Kalman Filtering [J].
Barrau, Axel ;
Bonnabel, Silvere .
ANNUAL REVIEW OF CONTROL, ROBOTICS, AND AUTONOMOUS SYSTEMS, VOL 1, 2018, 1 :237-257
[5]   The Invariant Extended Kalman Filter as a Stable Observer [J].
Barrau, Axel ;
Bonnabel, Silvere .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2017, 62 (04) :1797-1812
[6]   Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving [J].
Bresson, Guillaume ;
Alsayed, Zayed ;
Yu, Li ;
Glaser, Sebastien .
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2017, 2 (03) :194-220
[7]  
Brossard M, 2019, IEEE INT C INT ROBOT, P2068, DOI [10.1109/iros40897.2019.8968593, 10.1109/IROS40897.2019.8968593]
[8]  
Brossard M, 2019, IEEE INT CONF ROBOT, P291, DOI [10.1109/ICRA.2019.8794237, 10.1109/icra.2019.8794237]
[9]  
Brossard M, 2018, IEEE INT C INT ROBOT, P649, DOI 10.1109/IROS.2018.8593627
[10]   Odometry 2.0: A Slip-Adaptive EIF-Based Four-Wheel-Odometry Model for Parking [J].
Brunker, Alexander ;
Wohlgemuth, Thomas ;
Frey, Michael ;
Gauterin, Frank .
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2019, 4 (01) :114-126