“Brains” for Robots: Application of the Mivar Expert Systems for Implementation of Autonomous Intelligent Robots

Abstract

Recently the contemporary robotic systems can manipulate different objects and make decisions in a range of situations due to significant advances in innovation technologies and artificial intelligence. The new expert technologies can handle millions of instructions on computers and smartphones, which allow them to be used as a tool to create “decision-making systems” for autonomous robots. The goal of this paper was to create a dynamic algorithm of robot actions that can be used in the decision module has been considered. It is proposed to use Mivar expert systems of a new generation for high-level control. The experiment results showed that Mivar decision-making systems can control groups of small robots and even an unmanned autonomous car in real time. The algorithms created in the Mivar environment can be very flexible, and their build-up depends only on engineering approaches. In addition to traditional low-level robot control systems, a Mivar decision-making system has been implemented, which can be considered as universal “Brains” for autonomous intelligent robots and now knowledge bases can be created and various robots can be trained for practical tasks. • On the basis of Mivar expert systems based on rules, logical brains for robots in the form of decision-making systems have been created. • A method for combining multiple domains to create intelligent autonomous robots capable of reasoning at the rate of 5 million production rules per second is proposed. • Fundamentally new Mivar expert systems with linear inference complexity and extremely low hardware requirements are described and implemented in traditional low-level robot control systems.