Abstract
AbstractThis article presents the construction of an intelligent automatic navigation system for mobile robots in a flat environment with defined and unknown obstacles. Programming tools used in the studies are the operating system for mobile robots (Robot Operating System – ROS). From the updated information on maps, operating environment, robot control position and obstacles (Simultaneous Localization and Mapping (SLAM)), we can calculate the motion trajectory of the mobile robot. The navigation system calculates the global and local trajectory for the robot based on the application of Actor-Critic (AC) algorithm. The results of simulation studies in the Gazebo environment and the experimental run on the real Turtlebot mobile robot showed the practical efficiency of automatic navigation for this mobile robot.KeywordsIntelligent controlMobile robotObstacle robotsReinforcement learningAutonomous navigationActor-critic algorithm
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
