This seminar presents an overview of the recent research efforts in the field of intelligent robotic systems conducted within the Laboratory for Robotics and Artificial Intelligence at the Department of Production Engineering (KaProm), University of Belgrade – Faculty of Mechanical Engineering. The presentation of the research results is divided into two main topics.
The first topic relates to Image-based visual servo (IBVS) control algorithm as one of the approaches used to control the motion of robot manipulators in a structured manufacturing environment. In order to eliminate measurement and modeling errors, a novel intelligent visual servo controller for a robot manipulator based on neural network Reinforcement Learning is presented. Two different algorithms (Q-learning and SARSA) coupled with neural networks are developed and tested through different visual control scenarios. Real-world experiments are conducted on a 6 DOF NeuroArm Manipulator System and a low-cost camera in an eye-in-hand configuration. The experimental results demonstrate that the proposed method can provide the high accuracy of a manipulator positioning in a situation when the low-resolution image is used.
The second topic covers control and scheduling of mobile robot systems used to achieve reliable and efficient indoor material transport in intelligent manufacturing environment. A novel approach that integrates Learning from Demonstrations (LfD) methodology and chaotic biologically inspired optimization algorithms for the reproduction of desired motion trajectories is proposed to enable a nonholonomic mobile robot to learn from human and/or robot teacher through demonstrations or observations and to improve its behavior in real time. The desired trajectories are results of novel swarm intelligence based methodology for optimally scheduled intelligent material transport based on single mobile robot. The proposed approaches are evaluated through the real-world experiments carried out on a real mobile robot system (Khepera II mobile robot, low-resolution camera, and gripper) in an indoor structured environment. The experimental results show that the mobile robot realizes the scheduled trajectory with minimal error in the final robot pose and successfully finishes the transportation task.