Mainul Hossain

MD Muhaimin Rahman, SM Hasanur Rashid, M. M Hossain

In this paper, the implementation of two Reinforcement learnings namely, Q Learning and Deep Q Network(DQN) on a Self Balancing Robot Gazebo model has been discussed. The goal of the experiments is to make the robot model learn the best actions for staying balanced in an environment. The more time it can stay within a specified limit , the more reward it accumulates and hence more balanced it is. Different experiments with different learning parameters on Q Learning and DQN are conducted and the plots of the experiments are shown.

MD Muhaimin Rahman, SM Hasanur Rashi, KM Rafidh Hassan et al.

. This paper is aimed to discuss and compare three of the most famous Control Theories on a Two wheeled Self Balancing Robot Simulation using Robot Operating System (ROS) and Gazebo. Two Wheeled Self Balancing Robots are one of the most fascinating applications of Inverted Pendulum System. In this paper, PID, LQR and Fuzzy logic controllers are discussed . Also,0 the modeling and algorithms of the robot simulation is discussed. The primary objectives of this paper is to discuss about the building of a robot model in ROS and Gazebo , experimenting different control theories on them, documenting the whole process with the analysis of the robot and comparison of different control theories on the system.