MECHATRONICS VOLUME: 17 | NUMBER: 1 | 2019 | MARCH Autonomously Simultaneous Localization and Mapping Based on Line Tracking in a Factory-Like Environment Akif DURDU 1 , Mehmet KORKMAZ 2 1 Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Konya Technical University, Ankara Caddesi No:6, 42030, Karatay/Konya, Turkey 2 Department of Civil, Environmental and Geodetic Engineering, The Ohio State University, Columbus, 43210 Ohio, United States of America akifdurdu@gmail.com, mkorkmazeem@gmail.com DOI: 10.15598/aeee.v17i1.3048 Abstract. This study is related to SLAM, also known simultaneous localization and mapping which is highly important and an indispensable issue for autonomous mobile robots. Both an environment mapping and an agent’s localization are provided with SLAM systems. However, while performing SLAM for an unknown en- vironment, the robot is navigated by three different ways: a user guidance, random movements on an ex- ploration mode or exploration algorithms. A user guid- ance or random exploration methods have some draw- backs that a user may not be able to observe the agent or random process may take a long time. In order to answer these problems, it is searched for a new and au- tonomous exploration algorithm for SLAM systems. In this manner, a new kind of left-orientated autonomous exploration algorithm for SLAM systems has been im- proved. To show the algorithm effectiveness, a factory- like environment is made up on the ROS (Robot Op- erating System) platform and navigation of the agent is observed. The result of the study demonstrates that it is possible to perform SLAM autonomously in any similar environment without the need of the user inter- ference. Keywords Active SLAM, autonomous agents, indoor navi- gation, simultaneous localization and mapping. 1. Introduction It is a well-known fact that robotic applications have been increasing day after day and robots have per- formed an assistance to human from health to indus- trial applications [8], [12], [14], [18] and [28]. In order for a robot to be able to fulfil a task, it has to know its location and what the world looks like around it. It is agreed that the problem of where the robot is seen as a localization problem. Moreover, the prob- lem of constructing a map of the environment is spec- ified as a mapping one [3] and [25]. Despite the fact that these two issues tackle separately, it may be im- possible to give the robot neither location nor map in some cases. Therefore, it is necessary to build a map of an environment while simultaneously localize the robot within this map for such situations. When the litera- ture is scrutinized, it can be seen that this problem is called as simultaneous localization and mapping or acronym of it SLAM [6]. SLAM deals with a construc- tion of a map of an environment in which concurrently localize itself within it. Due to the fact that it could gain an autonomy to the robot, SLAM has been seen a ‘holy grail’ [6] and, it is an important milestone for the mobile robotic applications. From this point of view, a mobile robot is able to have an information about where it is or where to go by courtesy of SLAM. Many algorithms have been presented about SLAM from the 2-D maps and metrics maps to 3D or topologic ones, from the filter based approaches to the vision- based ones [1], [11], [19], [28] and [30]. According to the related previous studies, a guidance of robots in an unknown environment could be done in three different ways: • The first one is a user navigation and it can be thought an ideal and the most efficient solution due to the fact that it is based on human obser- vation. By way of this method, the robot can be navigated to an unmapped area. One of the lim- itations of this method is that it is not explicit c  2019 ADVANCES IN ELECTRICAL AND ELECTRONIC ENGINEERING 45