Sergei V. Ulyanov

Soft computing for the intelligent robust control of a robotic unicycle with a new physical measure for mechanical controllability

Abstract The posture stability and driving control of a human-riding-type unicycle have been realized. The robot unicycle is considered as a biomechanical system using an internal world representation with a description of emotion, instinct and intuition mechanisms. We introduced intelligent control methods based on soft computing and confirmed that such an intelligent control and biological instinct as well as intuition together with a fuzzy inference is very important for emulating human behaviors or actions. Intuition and instinct mechanisms are considered as global and local search mechanisms of the optimal solution domains for an intelligent behavior and can be realized by genetic algorithms (GA) and fuzzy neural networks (FNN) accordingly. For the fitness function of the GA, a new physical measure as the minimum entropy production for a description of the intelligent behavior in a biological model is introduced. The calculation of robustness and controllability of the robot unicycle is presented. This paper provides a general measure to estimate the mechanical controllability qualitatively and quantitatively, even if any control scheme is applied. The measure can be computed using a Lyapunov function coupled with the thermodynamic entropy change. Interrelation between Lyapunov function (stability condition) and entropy production of motion (controllability condition) in an internal biomechanical model is a mathematical background for the design of soft computing algorithms for the intelligent control of the robotic unicycle. Fuzzy simulation and experimental results of a robust intelligent control motion for the robot unicycle are discussed. Robotic unicycle is a new Benchmark of non-linear mechatronics and intelligent smart control.

Intelligent fuzzy motion control of mobile robot for service use

The intelligent mobile robot for service use with manipulators are moved in unstructured environments. Strategy for planning, environment recognition using two kinds of sensors and locomotion control to realize autonomous locomotion of the mobile robot are described. Fuzzy qualitative simulation, GA and hierarchical node map have revealed their effectiveness for path planning of the mobile robots. The results of fuzzy robot control simulation, monitoring and experimental investigations are presented.

Intelligent robust control of a robotic unicycle based on a new physical measure for mechanical controllability

The posture stability driving control of a human riding-type unicycle has been realized. The robotic unicycle is considered as a biomechanical system using an internal world representation with a description of emotion, instinct and intuition mechanisms. We introduced intelligent control methods based on soft computing, and confirmed that such an intelligent control and biological instinct as well as intuition together with a fuzzy inference is very important for emulating human behaviors or actions. For the fitness function of the generic algorithm, a new physical measure of the minimum entropy production for a description of the intelligent behavior in a biological model is introduced. The calculation of robustness and controllability of the robotic unicycle is presented. This paper provides a general measure to estimate the mechanical controllability both qualitatively and quantitatively, even if any control scheme is applied. The measure can be computed using a Lyapunov function coupled with the therm...

Design of self-organized intelligent control systems based on quantum fuzzy inference: intelligent system of systems engineering approach

This report presents a generalized design strategy of intelligent robust control systems based on quantum/soft computing technologies that enhance robustness of fuzzy controllers by supplying a self-organizing capability. It is demonstrated that fuzzy controllers prepared to maintain control object in the prescribed conditions are often fail to control when such a conditions are dramatically changed. We propose the solution of such kind of problems by introducing a generalization of strategies in fuzzy inference from a set of pre-defined fuzzy controllers by new quantum fuzzy inference based systems (prototype of intelligent system of systems engineering). We stress our attention on the robustness features of intelligent control systems.

Stochastic analysis of time-variant nonlinear dynamic systems. Part 1: The Fokker-Planck-Kolmogorov equation approach in stochastic mechanics

Abstract The probabilistic description and analysis of the response of time-invariant nonlinear dynamic systems driven by stochastic processes is usually treated by means of evaluation of statistical moments and cumulants of the response. The background of these methods is the Fokker-Planck-Kolmogorov (FPK) equation for a probability density function or the Pugachev equation for a characteristic function, respectively. The exact solutions of these equations are obtained only for isolated cases. For engineering probabilistic analysis of a complex nonlinear systems, different mixed (hybrid) methods in these cases are used. In this study a ‘benchmark’ solution is obtained on the basis of the FPK equation in conjunction with the method of statistical moments for nonlinear mechanical system with colored parametric excitations. In Part 1 (this part), an exact solution of FPK equation on the basis of asymptotic analysis of nonlinear dynamic behavior of parametric excitation system is discussed. In Parts 2 and 3, applications of this method to stochasticity and stability analysis of nonlinear time-variant systems are considered. A comparison with the accuracy of different statistical methods is discussed. In Parts 4 and 5, a method of stochastic analysis of relativistic and quantum dynamic systems is described on the basis of a generalized stochastic Hamilton-Jacobi equations on a differential manifold as Riemanian geometry. This involves the task of relativistic navigation and dissipative quantum models of a nonlinear parametric oscillator in the presence of stochastic excitations on a differential manifold with different metric tensors of the space-time continuum.

Soft computing algorithms for intelligent control of a mobile robot for service use

Abstract The arrangement principles and design methodology on soft computing for complex control framework of AI control system in Part 1 of this paper are developed. The basis of this methodology is computer simulation of dynamics for mechanical robotic system with the help of qualitative physics and search for possible solutions by genetic algorithms (GA). In Part 2 optimal solutions for navigation with avoidance of obstacles and technological operations as opening of door with a manipulator on GA and fuzzy neural network (FNN) are obtained and knowledge base (KB) for fuzzy controller is formed. Fuzzy qualitative simulation, GA and hierarchical node map (HN), and FNN have demonstrated their effectiveness for path planning of a mobile robot for service use. The results of fuzzy robot control simulation, monitoring, and experimental investigations are described.

A mobile robot for service use: behaviour simulation system and intelligent control

The structure of hardware and software of AI control system of a mobile robot for service use are described. Hardware of the mobile robot described include an autonomous wheel vehicle and a five degree of freedom manipulator. The software of the AI control system is based on soft computing including fuzzy control rules, fuzzy neural network and genetic algorithms. The intelligent control of cooperative motion between the autonomous vehicle and manipulator realises flexible operations such as navigation of a mobile robot in presence of static and dynamic obstacles, processes of opening door in rooms and pushing buttons of an elevator. New hierarchical structure of the AI control system includes direct human-robot communication line based on natural language and cognitive graphics, and a generator of virtual reality for simulation of artificial life conditions for the mobile service robot. Simulation and experimental results of navigation and technical operations with the manipulator mobile service robot used in office building are described.

Soft computing simulation design of intelligent control systems in micro-nano-robotics and mechatronics

Abstract The soft computing simulation design methodology of intelligent control system for mobile micro-nano-robots based on modeling of non-linear dissipative equations of robots motion with a minimum entropy production is described. It includes hierarchical levels for description of dynamic behavior of mobile micro-nano-robots based on laws of microphysics, quantum logic of intelligent dynamic behavior of control objects, optimal control of states and dynamic system theory of mechanical motion. The description of a thermodynamic intelligent behavior (with minimum entropy production) of control objects (robots) and their interrelations with Lyapunov stability conditions are introduced. The role of soft computing on the basis of GA with a fitness function as a minimum entropy production for intelligent control of mobile micro-nano-robots is discussed.

Principle of minimum entropy production in applied soft computing for advanced intelligent robotics and mechatronics

Abstract A new approach to design of smart intelligent control systems for advanced robotics and mechatronics is developed. The principle of minimum entropy production in a control object motion and a control system as a fitness function for genetic algorithm is used. Simulation results of a smart robust control of non-linear systems described as coupled oscillators are presented.

Stochastic analysis of time-variant nonlinear dynamic systems. Part 2: methods of statistical moments, statistical linearization and the FPK equation

In this, the second of a two part paper, the applications of the Fokker-Planck-Kolmogorov (FPK) method to stochastic analysis of time-variant nonlinear systems are considered. A new class of dynamic systems with stochastic nonlinearity and jump parametric exitations is introduced. The comparison of accuracy of different statistical methods such as statistical linearization is discussed.