Automatic Control Department, Technical University of Catalonia, c/ Pau Gargallo, 5 E-08028 Barcelona, Spain.
Sensors (Basel). 2010;10(3):1511-34. doi: 10.3390/s100301511. Epub 2010 Mar 1.
Simultaneous Localization and Mapping (SLAM) is perhaps the most fundamental problem to solve in robotics in order to build truly autonomous mobile robots. The sensors have a large impact on the algorithm used for SLAM. Early SLAM approaches focused on the use of range sensors as sonar rings or lasers. However, cameras have become more and more used, because they yield a lot of information and are well adapted for embedded systems: they are light, cheap and power saving. Unlike range sensors which provide range and angular information, a camera is a projective sensor which measures the bearing of images features. Therefore depth information (range) cannot be obtained in a single step. This fact has propitiated the emergence of a new family of SLAM algorithms: the Bearing-Only SLAM methods, which mainly rely in especial techniques for features system-initialization in order to enable the use of bearing sensors (as cameras) in SLAM systems. In this work a novel and robust method, called Concurrent Initialization, is presented which is inspired by having the complementary advantages of the Undelayed and Delayed methods that represent the most common approaches for addressing the problem. The key is to use concurrently two kinds of feature representations for both undelayed and delayed stages of the estimation. The simulations results show that the proposed method surpasses the performance of previous schemes.
同时定位与建图（SLAM）也许是机器人学中最基本的问题，只有解决了这个问题，才能制造出真正的自主移动机器人。传感器对 SLAM 算法的使用有很大的影响。早期的 SLAM 方法主要集中在使用测距传感器，如声纳环或激光。然而，相机的使用变得越来越多，因为它们提供了大量的信息，并且非常适合嵌入式系统：它们轻便、廉价、节能。与提供距离和角度信息的测距传感器不同，相机是一种投影传感器，它测量图像特征的方位。因此，无法在单个步骤中获得深度信息（距离）。这一事实促成了一类新的 SLAM 算法的出现：仅方位 SLAM 方法，它主要依赖于特征系统初始化的特殊技术，以便在 SLAM 系统中使用方位传感器（如相机）。在这项工作中，提出了一种新颖而强大的方法，称为并发初始化，它的灵感来自于延迟和非延迟方法的互补优势，这两种方法是解决该问题的最常见方法。关键是在估计的非延迟和延迟阶段同时使用两种特征表示。仿真结果表明，所提出的方法优于以前的方案。
