189 / 2024-03-12 15:26:27

Environment perception and autonomous positioning for underground mining vehicles based on LiDAR-visual-inertial fusion in challenging dark roadway scenes

Hybrid features detection,visual-inertial fusion,inertial navigation system,autonomous positioning,LIDAR

Accurate positioning for autonomous driven underground mining vehicles (UMVs) is indeed one of the cores in the intelligentization of coal mining. Completely different from positioning on the ground and in parking scenes, there will be great difficulties in realizing the accurate active positioning for UMVs shuttled in dark and narrow roadways. We propose an effective multi-sensor fusion positioning method for autonomous UMVs in challenging roadway scenarios based on the odometer-aided inertial navigation system and light detection and ranging (LiDAR) and visual combining pose estimation system. Velocity information of the odometer is adopted to restrain the error accumulation of inertial positioning based on a Kalman filter. The hybrid LiDAR and visual combining feature detection algorithm is put forward based on the feature strength and geometric information to improve the accuracy and robustness of observation information in a dark environment. Autonomous positioning and environmental mapping experiments for UMVs are performed in a dark narrow roadway to demonstrate the applicability of our method. The proposed approach outperforms the state-of-art methods in both accuracy and stability.