Object Following Design for a Mobile Robot using Neural Network

Deciding the best method for robot navigation is the most important tasks in mobile robot design, defined as the robot's ability to reach the target or/and move around its environment safely using the installed sensors and/or predefined map. To achieve this objective, wall or object detection can be considered. It is common to derive kinematics and dynamics to design the controls system of the robot, however by giving intelligence system to the robot, the control system will provide better performance for robot navigation. One of the most applied artificial intelligence is neural networks, a good approach for sensors of mobile robot system that is difficult to be modeled with an accurate mathematical equations. Mostly discussed basic navigation of a mobile robot is wall following. Wall following robot has been used for many application not only in industrial as a transport robot but also in domestic or hospital. Two behaviors are designed in this paper, wall following and object following. Object following behavior is developed from wall following by utilizing data from 4 installed distance sensors. The leader robot as the target for the follower robot, therefore the follower robot will keep on trying reaching for the leader in a safe distance. The novelty of this research is in the sense of the simplicity of proposed method. The feasibility of our proposed design is proven by simulation where all the results shows the effectiveness of the proposed method.