Scene-Aware Error Modeling of LiDAR/Visual Odometry for Fusion-based Vehicle Localization

TL;DR

This paper introduces a scene-aware error modeling approach for LiDAR and visual odometry, enhancing vehicle localization accuracy through a fusion framework trained with sparse global poses, tested in diverse environments.

Contribution

It presents a novel scene-aware error model for exteroceptive sensor odometry and an end-to-end learning method for training, improving fusion-based vehicle localization.

Findings

Significant accuracy improvement in vehicle localization.

Effective adaptation to unexperienced environments.

Validated with both simulation and real-world data.

Abstract

Localization is an essential technique in mobile robotics. In a complex environment, it is necessary to fuse different localization modules to obtain more robust results, in which the error model plays a paramount role. However, exteroceptive sensor-based odometries (ESOs), such as LiDAR/visual odometry, often deliver results with scene-related error, which is difficult to model accurately. To address this problem, this research designs a scene-aware error model for ESO, based on which a multimodal localization fusion framework is developed. In addition, an end-to-end learning method is proposed to train this error model using sparse global poses such as GPS/IMU results. The proposed method is realized for error modeling of LiDAR/visual odometry, and the results are fused with dead reckoning to examine the performance of vehicle localization. Experiments are conducted using both simulation and real-world data of experienced and unexperienced environments, and the experimental results demonstrate that with the learned scene-aware error models, vehicle localization accuracy can be largely improved and shows adaptiveness in unexperienced scenes.