Robust RGB-D SLAM in Dynamic Environments for Autonomous Vehicles

Abstract

Vision-based SLAM has played an important role in many robotic applications. However, most existing visual SLAM methods are developed under a static world assumption and the robustness in dynamic environments remains a challenging problem. In this paper, we propose a robust RGB-D SLAM system for autonomous vehicles in dynamic scenarios which uses geometry-only information to reduce the impact of moving objects. To achieve this, we introduce an effective and efficient dynamic points detection module in a feature- based SLAM system. Specifically, for each new RGB-D image pair, we first segment the depth image into a few regions using the KMeans algorithm, and then identify the dynamic regions via their reprojection errors. The feature points located in these dynamic regions are then removed and only static ones are used for pose estimation. A dense map that contains only static parts of the environment is also produced by removing dynamic regions in the keyframes. Extensive experiments on public dataset and in real-world scenarios demonstrate that our method provides significant improvement in localization accuracy and mapping quality in dynamic environments.