Abstract
In recent years in mobile robotics, the focus has been on methods, in which the fusion of measurement data from various systems leads to models of the environment that are of a probabilistic type. The cognitive model of the environment is less accurate than the exact mathematical one, but it is unavoidable in the robot collaborative interaction with a human. The subject of the research proposed in this paper is the development of a model for learning and planning robot operations. The task of operations and mapping the unknown environment, similar to how humans do the same tasks in the same conditions has been explored. The learning process is based on a virtual dynamic model of a mobile robot, identical to a real mobile robot. The mobile robot’s motion with developed artificial neural networks and genetic algorithms is defined. The transfer method of obtained knowledge from simulated to a real system (Sim-To-Real; STR) is proposed. This method includes a training step, a simultaneous reasoning step, and an application step of trained and learned knowledge to control a real robot’s motion. Use of the basic cognitive elements language, a robot’s environment, and its correlation to that environment is described. Based on that description, a higher level of information about the mobile robot’s environment is obtained. The information is directly generated by the fusion of measurement data obtained from various systems.
Highlights
Intelligent robotics is a merged field intersection of two other engineering fields, artificial intelligence (AI) and robotics
The third mode of operation is labelled “One Run”. It is an operation mode used for results validation or to simulate eMIR’s movement in an unknown environment after previously learned neural network
Research has shown that mobile robot controlled by a 5 × 5 neural network has poor movement performance, as it tends to the linear description of a motion path (Figure 27)
Summary
Intelligent robotics is a merged field intersection of two other engineering fields, artificial intelligence (AI) and robotics. Let us look at the solutions that have become common today, simulations, and apply the obtained results to the real systems. This is perhaps most notable in the Computer Aided Design/Computer Aided Manufacturing/Computer Numerical Control (CAD/CAM/CNC) production chain [2]. The virtual agent path sequence obtained by simulation training is converted into a real robot command with control coordinate transformation for the robot that performs tasks. It should be mentioned that many authors present outcomes of learning simulation without testing them on real robot systems. Implementing experimental results in two different robot control tasks on real root systems has been shown in [4], which is a rare example of a real robot system experiment. A convolutional neural network’s development to control a home surveillance robot has been described in [5]
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
