ROBOT MANIPULATOR CONTROL USING INTELLIGENT AND EVOLUTIONARY COMPUTING TECHNIQUES

Abstract

The rapid development of factory automation involves industrial robot manipulators, which are mostly used in manufacturing processes to increase the productivity and quality of the products. The current thrust of research in robotics is to control robots which can operate in dynamic and partially known environments. Control of an industrial robot includes nonlinearities, uncertainties and external perturbations that should be considered in the design of control laws. Most non-adaptive control schemes for the control of robot manipulator systems, usually assume a full knowledge of the system dynamics. This is an unrealistic assumption in many cases as these complex systems are subjected to the presence of uncertainties. If not dealt appropriately, these uncertainties may have a remarkable effect on the controller performance and even induce instability. The ability of learning provides the robot manipulator with autonomous intelligence to handle such situations. Recent studies strongly stipulate that the learning based intelligent controllers reduce the adverse effects of time-varying behaviour and unmodelled dynamics when the analytical design is tedious or is not satisfactory. Hence, developing model-free adaptive control structure using computationally intelligent soft computing techniques has become an interesting research topic. The main objectives of the present work are; (a) investigation of the ability of soft computing approaches for addressing various design tasks and issues associated with the control of robot manipulators, (b) development of high performance tracking control algorithms in the presence of time-varying structured and unstructured uncertainties using computationally intelligent soft computing based controllers, (c) Integration and hybridization of fuzzy logic, neural networks, genetic algorithm, and other evolutionary optimization techniques with conventional controllers to overcome each other’s weakness, leading to new approach for solving robot manipulator control problem., (d) investigation of new hybrid adaptive neuro-fuzzy control algorithms for manipulator control with structured and unstructured uncertainties, (e) Fuzzy PD plus Integral (FPD+I) Control of an Industrial Robot manipulator with Velocity Observer, (f) Intelligent hybrid force/position controllers for an Industrial Robot Manipulator with velocity observer (g) Imperialist Competitive Algorithm optimized adaptive neuro fuzzy controller for hybrid force position control of an Industrial Robot Manipulator (h) Using the ability of ANFIS (Adaptive Neuro-Fuzzy Inference System) to provide fast and acceptable solutions of the inverse kinematics problem under kinematical uncertainties, and (i) study of hybrid fuzzy logic based pre-compensation scheme consisting ii of fuzzy PD pre-compensator and a conventional PD Controller for superior steady state and transient performance, good stabilization and tracking performance. In chapter three, tracking control of a six degrees of freedom robot arm (PUMA Robot) using hybrid Fuzzy PD plus conventional I controller, for unknown joint velocities as well as dynamics of a robot manipulator, is carried out as a new approach. For sensing the unknown joint velocity, a high gain velocity observer is introduced, which estimates the joint velocity from the positional component. The three input and one output fuzzy system is too complex to construct the PID controller. It is very difficult to decide the fuzzy control rules intuitively. Proposed fuzzy controller is mainly focused to mitigate such problems. Complexity of the proposed Fuzzy PD plus conventional I controller is minimized and only two design variables are used to adjust the rate of variations of the proportional gain and derivative gain. Numerical simulation using the dynamic model of six DOF robot arm shows the effectiveness of the approach in trajectory tracking problems. Comparative evaluation with respect to PID and Fuzzy PID controllers are presented to validate the controller design. The results presented emphasize that a satisfactory tracking precision could be achieved using velocity observer based Fuzzy PD plus conventional I controller structure when compared to their respective fuzzy PID only or conventional PID counterparts. An unpaired pooled t-test was executed to prove the statistically significance of the outcome of the proposed velocity observer based fuzzy proportional, derivative plus integral (VOB-FPD+I) controller in comparison with other controllers. Simulation results show the usefulness of the approach. Neuro-Fuzzy techniques that have emerged from the fusion of neural networks and fuzzy inference systems form a popular framework for solving real world problems. In chapter four, three novel hybrid adaptive neuro-fuzzy control algorithms have been proposed for manipulator control with uncertainties for solving hybrid force/ position control problem in a constrained environment for two cases: (1) when joint velocity is present, (2) when joint velocity is absent. Comparative analysis of simulated performance of some controllers (PID controller, FPID controller, FPD+I controller) is presented to validate the proposed controller design. The output of these controllers is applied to produce the final actuation signal based on current position and velocity errors. Numerical simulation using the dynamic model of six DOF puma robot arm with uncertainties shows the effectiveness of the approach in trajectory tracking problems. The results obtained show that adaptive neuro fuzzy based hybrid force/position controller perform better with uncertainties of the dynamics parameters and friction changes during manipulator operation. Performance indices such as Root Mean iii Square Error (RMSE), Normalised Mean Square Error (NMSE) and Mean Absolute Percentage Error (MAPE) IAE are used for comparison. Genetic Algorithm, Particle swarm Optimization (PSO) and Imperialist competitive algorithm (ICA), is currently gaining popularity in the research community, for its effectiveness in solving certain real world optimization problems. While the ICA is inspired by social evolution of human species, the GA and PSO are based on biological evolution of species. In chapter five, an ICA based hybrid adaptive neuro fuzzy inference system based force/position controller problem is presented under constrained environment. Numerical simulation using the dynamic model of six degree of freedom robot arm shows the effectiveness of the approach in trajectory tracking problems. Comparative evaluation is presented with respect to genetic algorithm and particle swarm optimization based hybrid adaptive neuro fuzzy inference system based force/position controller. The controller parameters optimized using ICA shows better results in trajectory tracking problems. Obtaining the joint variables that result in a desired position of the robot end-effector called as inverse kinematics is one of the most important problems in robot kinematics and control. As the complexity of robot increases, obtaining the inverse kinematics solution is difficult and computationally expensive. In chapter six, using the ability of Adaptive Neuro-Fuzzy Inference System (ANFIS), an implementation of a representative fuzzy inference system using a back propagation neural network-like structure, the inverse kinematics problem with limited mathematical representation of the system is solved. Computer simulation conducted on five degree of freedom (DOF) SCORBOT- ER-V PLUS manipulator shows the effectiveness of the developed approach to provide fast and acceptable solutions of the inverse kinematics and thereby making ANFIS as an alternate approach to map the inverse kinematics solution. The results of the developed intelligent algorithms have been very encouraging and would certainly open new opportunities for dealing with robot control of complex structures in manufacturing industry to increase the productivity and quality.