Arab J Sci Eng https://doi.org/10.1007/s13369-017-2917-0 RESEARCH ARTICLE - COMPUTER ENGINEERING AND COMPUTER SCIENCE A Vision-Based Real-Time Mobile Robot Controller Design Based on Gaussian Function for Indoor Environment Emrah Dönmez 1 · Adnan Fatih Kocamaz 1 · Mahmut Dirik 1 Received: 18 March 2017 / Accepted: 24 October 2017 © King Fahd University of Petroleum & Minerals 2017 Abstract In this study, a visual servoing go-to-goal behav- ior controller is designed to control a differential drive mobile robot for a static target. Inputs for the controller method are based on a weighted graph or a triangle trigonometry kinematic model. The controller is designed with general Gaussian function by adapting the differential drive mobile robot dynamics. State parameters of dynamics are obtained by processing images in real time. It is aimed to develop an efficient internal sensor-independent visual-based control method. The single-head camera takes image frames from indoor environment. A real-time tracking process tracks the robot and target in sequential frames. The distances between graph nodes or the angles between edges are assigned as main control inputs according to utilized kinematic model. The velocity of wheels is computed for both models by using the general Gaussian function. We compare our method with two classical control methods that are PID and fuzzy-PID. Control of mobile robot has been made with high accuracy by using the designed visual-based controller. Keywords Visual servoing · Gaussian function · Triangle/graph models · Real-time control B Emrah Dönmez emrahdonmez@msn.com Adnan Fatih Kocamaz fatih.kocamaz@inonu.edu.tr Mahmut Dirik mahmut.dirik@inonu.edu.tr 1 Department of Computer Engineering, Faculty of Engineering, ˙ Inönü University, Malatya, Turkey 1 Introduction Control task is a challenging issue in robotic applications. There is a remarkable number of studies generally focusing on internal sensor-based control with classical based methods such as PID, fuzzy control, fuzzy PI and heuristics [1–5]. The control task is generally applied with global position and angular heading information by control procedures [6, 7]. These methodical tasks depend on data from internal sensors like accelerometer, gyroscope, encoders and external sensors like range sensors, infrared, thermal camera. By using these sensory informations, the angular states are calculated and parameters for controllable parts are updated to form next motion. Visual-based control methods aim to control a dynamic system by utilizing visual features acquired from images ensured by one or multiple cameras [8–11]. In other words, controlling a robot can be modeled through a visual per- ception infrastructure. This is done by applying image processing techniques on each of the frames acquired from the imagining device. The aim of all visual-based controls is decreasing errors and the motion cost to an admissible level. There are two types of errors in robotic systems: systematic and non-systematic errors. Systematic errors generally stem from the encoder, sensor and physical structure of robot parts. On the other hand, non-systematic errors generally stem from sliding, hitting, falling and so on. Eventually, aim of all robot control methods is amortizing such errors until accomplish- ing the given task [12]. The main advantages of the visual servoing are that it requires fewer sensor data, suitable to con- trol multiple robots, internal and external sensors on robots generally are not needed, in terms of scalability; it provides more operating area by increasing imagining devices and so on. Visual servoing is implemented in a wide range of robotic studies. In early studies, robotic arm manipulators have 123