A Robust Vehicle Localization Approach Based on GNSS/IMU/DMI/LiDAR Sensor Fusion for Autonomous Vehicles

Sensors

Heng Wang¹  Bingbing Liu²  Xiaoli Meng² 

[1] College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore;

关键词: sensor fusion;    Unscented Kalman Filter (UKF);    vehicle localization;   

DOI  :  10.3390/s17092140

来源: DOAJ

【 摘 要 】

Precise and robust localization in a large-scale outdoor environment is essential for an autonomous vehicle. In order to improve the performance of the fusion of GNSS (Global Navigation Satellite System)/IMU (Inertial Measurement Unit)/DMI (Distance-Measuring Instruments), a multi-constraint fault detection approach is proposed to smooth the vehicle locations in spite of GNSS jumps. Furthermore, the lateral localization error is compensated by the point cloud-based lateral localization method proposed in this paper. Experiment results have verified the algorithms proposed in this paper, which shows that the algorithms proposed in this paper are capable of providing precise and robust vehicle localization.

【 授权许可】

Unknown