(IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 6, 2022 An E2ED-based Approach to Custom Robot Navigation and Localization Andr´ es Moreno, Daniel P´ aez, Fredy Mart´ ınez Universidad Distrital Francisco Jos´ e de Caldas Bogot´ a D.C., Colombia Abstract—Simultaneous mapping and localization or SLAM is a basic strategy used with robots and autonomous vehicles to identify unknown environments. It is of great attention in robotics due to its importance in the development of motion planning schemes in unknown and dynamic environments, which are close to the real cases of application of a robot. This is why, in parallel with research, they are also important in specialized training processes in robotics. However, access to robotic platforms and laboratories is often complex and costly, with high demands on time and resources, particularly for small research centers. A more efficient and affordable approach to working with autonomous algorithms and motion planning schemes is often the use of the ROS-Gazebo simulator, which allows high integration with customized non-commercial robots, and the possibility of an end-to-end design (E2ED) solution. This research addresses this approach as a training and research strategy with our ARMOS TurtleBot robotic platform, creating an environment for working with navigation algorithms, in localization, mapping, and path planning tasks. This paper shows the integration of ROS into the ARMOS TurtleBot project, and the design of several subsystems based on ROS to improve the interaction in the development of service robot tasks. The project’s source code is available to the research community. Keywords—End-to-End design; localization; navigation; path planning; robotics; SLAM I. I NTRODUCTION Robotics is a field of research in constant growth, the need for support, cost reduction, safety, and reliability drives the development and study of problems related to its application in real tasks. There are major unsolved problems that hinder its wide use in applications such as service robotics (the area closest to our research), in general, related to interaction, autonomy, safety, and reliability [1]. Many research centers around the world are actively working in these niches, but in many cases, access to robotic platforms and specialized laboratories is restricted for reasons of cost, availability, and resources related to this activity. A working scheme of good acceptance in the scientific community is the use of high- performance simulators, which can replicate very faithfully the behavior of a robot, one of the most popular platforms today in this regard is ROS OS (Robotic Operating System). The operating system has more than 10 years of growth and interaction in robotic programming, and its particular details such as interoperability and open source generation provide services comparable to those of an operating system, such as hardware abstraction, low-level device control, inter-process message passing and packet management [2]. Though is not an operating system, it provides the same services to its users as an operating system does. In today’s social development, the implementation of mo- bile robots for problem-solving in industrial and non-industrial environments is of great relevance [3]. Applications in rural or agricultural areas, as well as those involving direct interaction with humans [4], [5], are of great current interest. In this respect, mobile robotic platforms have been proposed that can be used in a greenhouse to transport vegetables [6], [7], in some cases with safe interaction systems with humans. Another study proposes the control and tracking of trajectories based on simulations and experiments in real-time on the ROS platform, where the objective is to validate the effectiveness of the proposed control algorithm and compare it with a modified hybrid PID dynamic controller with feedback [8]. In these cases, ROS was fundamental in the design and performance evaluation stages. As for the concrete problem of mapping and navigation, whether in the land, water, or air vehicles, ROS allows SLAM simulation in the working environment, thus reconstructing the map and dynamically planning a trajectory to the target destination [9], [10]. The use of this type of software tool becomes essential when control schemes integrate a large variety of sensors [11]. Not only does it facilitate the preliminary performance evaluation of the scheme (reducing costs and implementation time), but it also speeds up the overall implementation time of the schemes. In assistive robotics, this is key, as new interaction schemes and control algorithms are continually being developed and need to be evaluated quickly [12]. These applications involve both the interaction problem and the navigation problem, which in many cases involve complex control algorithms, whose performance and coordination must be evaluated before implementation on real platforms [13], [14]. The emulation under ideal conditions, therefore, allows having an additional design tool that guarantees time and design reduction throughout the whole process [15]. Our research project is part of a macro project aimed at the development of robotic solutions for assistance tasks, particularly in applications related to the care of people (elderly and children). In previous years, we have developed a modular mobile platform with load capacity for integration with a manipulator robot (industrial application) and/or an anthro- pomorphic robot for services [16], [17]. Previous prototypes of this robot had been integrated with ROS to provide ease of handling and simulation of behaviors [18], [19]. At the time, the use of the platform with ROS in structured motion planning applications was justified due to the simplification www.ijacsa.thesai.org 910 | Page