ASL-SLAM: An Asynchronous Formulation of Lines for SLAM with Event Sensors
ASL-SLAM: An Asynchronous Formulation of Lines for SLAM with Event Sensors
复制标题
ASL-SLAM：带有事件传感器的 SLAM 的异步线路公式
DOI：
10.1145/3523132.3523146
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Nong X
中科院分区：
文献类型：
--
作者：
Nong X
工业自动化的发展与移动的机器人定位导航方式的演变密切相关。在本文中，我们介绍了ASL-SLAM，第一个基于线的SLAM系统直接使用事件传感器的机器人上运行。这种方法最大化了由生物启发传感器生成的事件信息的优点。我们估计本地活动事件表面（SAE），以获得事件流中每个传入事件的平面。然后利用直线提取算法恢复图像的边缘和运动。我们展示了如何包含基于事件的线跟踪显着提高性能相比，最先进的基于帧的SLAM系统。该方法是在公开的数据集上进行评估的。结果表明，当机器人面对简单或低纹理环境时，我们的方法对纹理较差的帧特别有效。我们还尝试了具有挑战性的照明情况，以适应各种工业环境，包括低光和高运动模糊场景。我们表明，我们的方法与基于事件的相机具有天然的优势，并提供了高达85%的减少错误时，在这些条件下进行SLAM相比，传统的方法。
The development of industrial automation is closely related to the evolution of mobile robot positioning and navigation mode. In this paper, we introduce ASL-SLAM, the first line-based SLAM system operating directly on robots using the event sensor only. This approach maximizes the advantages of the event information generated by a bio-inspired sensor. We estimate the local Surface of Active Events (SAE) to get the planes for each incoming event in the event stream. Then the edges and their motion are recovered by our line extraction algorithm. We show how the inclusion of event-based line tracking significantly improves performance compared to state-of-the-art frame-based SLAM systems. The approach is evaluated on publicly available datasets. The results show that our approach is particularly effective with poorly textured frames when the robot faces simple or low texture environments. We also experimented with challenging illumination situations to order to be suitable for various industrial environments, including low-light and high motion blur scenarios. We show that our approach with the event-based camera has natural advantages and provides up to 85% reduction in error when performing SLAM under these conditions compared to the traditional approach.
影响因子：
7.8
作者：
Mur-Artal, Raul;Tardos, Juan D.
通讯作者：
Tardos, Juan D.