Abstract
Recent work has shown impressive localization performance using only images of ground textures taken with a downward facing monocular camera. This provides a reliable navigation method that is robust to feature sparse environments and challenging lighting conditions. However, these localization methods require an existing map for comparison. Our work aims to relax the need for a map by introducing a full simultaneous localization and mapping (SLAM) system. By not requiring an existing map, setup times are minimized and the system is more robust to changing environments. This SLAM system uses a combination of several techniques to accomplish this. Image keypoints are identified and projected into the ground plane. These keypoints, visual bags of words, and several threshold parameters are then used to identify overlapping images and revisited areas. The system then uses robust M-estimators to estimate the transform between robot poses with overlapping images and revisited areas. These optimized estimates make up the map used for navigation. We show, through experimental data, that this system performs reliably on many ground textures, but not all.
Abstract (translated)
最近的工作表明,仅使用一张向下倾斜的单目相机拍摄的土地纹理图像,可以表现出令人印象深刻的的定位性能。这种方法提供了一种可靠的导航方法,能够 robustly 应对稀疏环境以及挑战性的照明条件。然而,这些定位方法需要与已有地图进行比较。我们的目标是通过引入全同时定位和映射(SLAM)系统来放松对地图的需求。不再需要已有地图,setup时间被最小化,系统更加 robust 于环境变化。这个 SLAM 系统使用了多种技术来实现这一点。图像关键点被识别并投影到地面平面上。这些关键点、词汇视觉包和几个阈值参数被用来识别重叠图像和重访区域。系统 then 使用鲁棒的 M-估计器来估计重叠图像和重访区域之间的机器人姿态变换。这些优化估计组成了用于导航的地图。通过实验数据,我们表明,该系统在许多土地纹理上表现出可靠的性能,但并非所有情况下。
URL
https://arxiv.org/abs/2303.05946