Localization and Mapping Based on Multi-feature and Multi-sensor Fusion

Abstract

Simultaneous Localization and Mapping (SLAM) is the foundation for high-precision localization, environmental awareness, and autonomous decision-making of autonomous vehicles. It has developed rapidly, but there are still challenges such as sensor errors, data fusion, and real-time computing. This paper proposes an optimization-based fusion algorithm that integrates IMU data, visual data and LiDAR data to construct a high-frequency visual-inertial odometry. The odometry is employed to obtain the relative pose transformation during the LiDAR data acquisition process, and eliminate the distortion of the point cloud by interpolation. By utilizing the local curvatures, some edge and plane features are extracted by LiDAR after removing the distortion, which are further combined with local map alignment to reconstruct the LiDAR constrains. In addition, the LiDAR odometer can be obtained through the initial values provided by high-frequency visual-inertial odometry. To address the cumulative error in odometers, adjacent keyframe and multi descriptor fusion loop constraints are combined to construct back-end optimization constraints, solving for high-accuracy localization results and constructing a 3D point cloud map of the surroundings. Compared with some classical algorithm, results show that the accuracy of this paper's algorithm is better than the laser SLAM method and the multi-sensor fusion SLAM method. Besides, the laser-assisted multi-feature visual-inertial odometry localization accuracy is also better than that of the single-feature visual-inertial odometry. In summary, the newly proposed SLAM method can largely improve the accuracy of odometry in real traffic scenarios.