Design Of Intelligent Controller Research Articles

Using direct competition to select for competent controllers in evolutionary robotics

Evolutionary robotics (ER) is a field of research that applies artificial evolution toward the automatic design and synthesis of intelligent robot controllers. The preceding decade saw numerous advances in evolutionary robotics hardware and software systems. However, the sophistication of resulting robot controllers has remained nearly static over this period of time. Here, we make the case that current methods of controller fitness evaluation are primary factors limiting the further development of ER. To address this, we define a form of fitness evaluation that relies on intra-population competition. In this research, complex neural networks were trained to control robots playing a competitive team game. To limit the amount of human bias or know-how injected into the evolving controllers, selection was based on whether controllers won or lost games. The robots relied on video sensing of their environment, and the neural networks required on the order of 150 inputs. This represents an order of magnitude increase in sensor complexity compared to other research in this field. Evolved controllers were tested extensively in real fully-autonomous robots and in simulation. Results and experiments are presented to characterize the training process and the acquisition of controller competency under different evolutionary conditions.

Intelligent robust tracking controls for holonomic and nonholonomic mechanical systems using only position measurements

Intelligent robust tracking control designs are proposed in this paper for both uncertain holonomic and nonholonomic mechanical systems. A unified and systematic procedure, that is based on an adaptive fuzzy (or neural network) system and a linear observer, is employed to derive the controllers for these two constrained mechanical systems. Adaptive fuzzy-based (or neural network-based) position feedback tracking controllers can be constructed such that all the states and signals of the closed-loop systems are bounded and the tracking error locally converges to a small region around zero. Only position measurements are required for feedback. The implementation of the fuzzy (or neural network) basis functions depends only on the desired reference information and so once a set of desired trajectories is given, the required basis functions can be explicitly preassigned. Consequently, the intelligent robust position feedback tracking controllers developed here possess the properties of computational simplicity and easy implementation. Finally, simulation examples are presented to demonstrate the effectiveness of the proposed control algorithms.

APPLICATION OF GENETIC ALGORITHMS IN OPTIMAL EXCITATION AND CONTROLLER DESIGN

Genetic Algorithms (GAs) are used in a set of covariance based optimum input signal algorithms using a proposed architecture suitable for on-line system identification. The optimal signals are computed recursively using a predictive filter. The relationships among these algorithms are investigated and compared based on a set of simulations. In addition, a nested GA is proposed for intelligent LQR controller design. The GAs are used to find the minimum distance to uncontrollability of a given system and to maximize that minimum distance by finding the optimal coefficients in the weighting matrices of the LQR controller.

A Multi-Layer Autonomous Intelligent Control Architecture for Unmanned Aerial Vehicles

In the past several years there has been a lot of interest in the design of efficient autonomous intelligent controllers for Unmanned Aerial Vehicles (UAV). This is a highly complex and challenging problem since future UAVs will be expected to complete autonomously a wide variety of complex missions, and achieve performance comparable to that of manned vehicles. In this paper a four-layer autonomous intelligent control architecture for UAVs is described, and related issues are discussed. The architecture consists of the following layers: (i) Redundancy Management Layer that consists of the online Failure Detection and Identification (FDI) and robust feedback Adaptive Reconfigurable Controller (ARC); (ii) Autonomous Trajectory Generation (ATG) layer whose role is to fit feasible trajectories through the desired way-points in real time; (iii) Autonomous Path Planning (APP) layer that generates way-points on-line in response to a dynamically changing environment; and (iv) Autonomous Decision Making (ADM) layer whose role is to assess the available control authority after failures, and make missionrelated decisions in near-real time. The main distinguishing feature of the architecture is that its layers are connected through the Achievable Dynamic Performance (ADP) calculation module which results in a system in which all the decisions are made based on the current available resources. Recent extensions of this architecture are also discussed and described in detail. At the end, a discussion is included on the Verification and Validation (V&V) of intelligent and adaptive control systems, and some recent results are presented.

CMACと階層型ニューラルネットワークを併用したインテリジェント制御系の一設計

CMACと階層型ニューラルネットワークを併用したインテリジェント制御系の一設計

Evolvable Hardware in Evolutionary Robotics

In recent decades the research on Evolutionary Robotics (ER) has developed rapidly. This direction is primarily concerned with the use of evolutionary computing techniques in the design of intelligent and adaptive controllers for robots. Meanwhile, much attention has been paid to a new set of integrated circuits named Evolvable Hardware (EHW), which is capable of reconfiguring its architectures unlimited time based on artificial evolution techniques. This paper surveys the application of evolvable hardware in evolutionary robotics. The evolvable hardware is an emerging research field concerning the development of evolvable robot controllers at the hardware level to adapt to dynamic changes in environments. The context of evolvable hardware and evolutionary robotics is reviewed, and a few representative experiments in the field of robotic hardware evolution are presented. As an alternative to conventional robotic controller designs, the potentialities and limitations of the EHW-based robotic system are discussed and summarized.

Integration of intelligent systems in development of smart adaptive systems

Different combinations of fuzzy logic and neural networks provide various ingredients for smart adaptive applications. Both expertise and data can be integrated in the development of intelligent systems. Evolutionary computation is also widely used in tuning of these systems. For small, specialised systems there is a large number of feasible solutions, but developing truly adaptive, and still understandable, systems for highly complex systems require more compact approaches in the basic level. Linguistic equation (LE) approach originating from fuzzy logic is an efficient technique for these problems. Insight to the process operation is maintained since all the modules can be assessed by expert knowledge and membership definitions relate measurements to appropriate operating areas. The LE approach increases the performance by combining various specialised models in a case-based approach: models can be generated automatically from data. The LE approach is also successfully extended to dynamic simulation and used in intelligent controller design. The integration of intelligent systems is based on understanding the different tasks of smart adaptive systems: modelling, intelligent analysers, detection of operating conditions, control and intelligent actuators. The system integration leads to a hybrid system: fuzzy set systems move gradually to higher levels, neural networks and evolutionary computing are used for tuning, and the whole system reinforced with efficient statistical analysis, signal processing and mechanistic modelling and simulation.

인터넷 기반 원격제어를 위한 임의의 시간지연을 갖는 지능형 제어기의 설계

This paper discusses a design of intelligent controller with time delay for Internet-based remote control. The finite Markovian process is adopted to model the input delay of the overall control system. It is assumed that the zero and hold devices are used for control input. The Takagi-Sugeno (T-S) fuzzy system with uncertain input delay is utilized to represent nonlinear plant. The continuous-time T-S fuzzy system with the Markovian input delay is discretized for easy handling delay, accordingly, the discretized T-S fuzzy system is represented by a discrete-time T-S fuzzy system with jumping parameters. The robust stochastic stabilizibility of the jump T-S fuzzy system is derived and formulated in terms of linear matrix inequalities (LMIs). An experimental results is provided to visualize the feasibility of the proposed method.

Drilling of Aramid and Carbon Fiber Polymer Composites

Drilling tests were conducted on aramid and carbon fiber-reinforced composite laminates using an instrumented machining center. Machining parameters for the damage-free drilling of these materials were established together with semi-empirical relationships between drilling forces and cutting parameters. The drilling force responses as a function of various feed rates and drill sizes were characterized to define the key process stages taking place during a drilling cycle. Using a previously established delamination-based criterion for initiating damage during drilling, the critical feed rate for damage-free drilling was established for the two composite material types: aramid and carbon fiber-reinforced polymer laminates. Independent measurements of the opening-mode delamination crack energy release rates were conducted on both materials to determine the critical thrust force for damage initiation. This study establishes the key process stages exhibited by carbon and aramid fiber composites during drilling, the critical threshold feed rates to avoid damage, and machining relations that can be utilized for the design of intelligent controllers for efficient drilling of composite laminates.

The design of intelligent control of a kitchen refrigerator

The article provides an example of how to design an “intelligent” digital control for maintaining the temperature at a predefined level in a common kitchen refrigerator. The control works on the basis of modeling a thermostatic appliance and the use of fuzzy logic. Thermostatically simulated and fuzzy controlled model are presented successively. The latter is set-up on the basis of the Sugeno’s type of fuzzy rules and the Jang’s procedure of learning. MATLAB, SIMULINK and Fuzzy Logic TOOLBOX (FLT) are the programming environments used for realization of the model. The principal aim in designing the control is to assure the fastest and best transition possible from an analogue to digital control of the refrigerating appliance, which represents the basis of a functional expansion demanded by the present market.

Intelligent feedback control-based adaptive resource management for asynchronous, decentralized real-time systems

Presents intelligent feedback control techniques for adaptive resource management in asynchronous, decentralized real-time systems. We propose adaptive resource management techniques that are based on feedback control theory and are designed using the intelligent control design paradigm. The controllers solve resource allocation problems that arise during run-time adaptation using the classic proportional-integral-derivative (PID) control functions and fuzzy logic. We study the performance of the controllers through simulation. The simulation results indicate that the controllers produce low missed deadline ratios and resource utilizations during high-workload situations.

Automation and process control of reverse osmosis plants using soft computing methodologies

At a time of intensive demand for producing fresh water at a reasonable cost, addressing automation, process control and cost optimization of desalination plants have become increasingly evident. Large-scale direct seawater reverse osmosis (RO) plants must perform at high standards due to the increasing cost of high quality water production, high equipment utilization, and rising government regulations on labor protection and the environment. In this keynote presentation, the recent innovation and technological advances in the design and implementation of soft computing methodologies for desalination processes are addressed. Such advances are mainly due to the recent developments of intelligent control design approaches for the integration of sensory information, computation, human reasoning and decision making. The principal partners in such an intelligent system include fuzzy logic (FL), neural network (NN), generic algorithms (GA) and probabilistic reasoning (PR). Various issues which is related to the design and implementation of soft computing methodologies including the trade-off between tolerance, precision and uncertainty are also addressed. As a case study, the design and implementation of an intelligent system for a direct seawater RO system located near Atlantic Ocean at Boca Raton, Florida is presented. The operation of the prototype plant indeed demonstrated the effective and optimum performance of the design for two types of membrane modules, spiral wound (SW) and hollow fine fiber (HFF), under forced diverse operating conditions. The system has achieved a constant recovery of 30% and salt passage of 1.026% while salt concentration of six major salts were kept below their solubility limits at all time. The implementation of the proposed intelligent control methodology has achieved a 5% increase in availability and reduction in manpower requirements as well as reduction in overall chemical consumption of the plant. Therefore, it is believed that the cost of producing water can be decreased using the proposed fully automated control strategy.

OPTIMAL CONTROL OF WASTEWATER TREATMENT PLANTS VIA INTEGRATED NEURAL NETWORK AND GENETIC ALGORITHMS

The successful operation of wastewater treatment plants involves many uncertain factors. Not only the physical and chemical properties of wastewater streams but also the complexity of biological mechanism would significantly influence the performance of treatment process. Due to the rising concerns of environmental and economic impacts, improved control algorithms, using artificial intelligence technologies, have gradually received wide attention in the scientific community. This paper develops a genetic algorithm-based neural network for the assistance of intelligent controller design. An industrial wastewater treatment plant in Taiwan verified the applicability of such a methodology. The hybrid intelligent control technology applied in this paper is suitable to many other types of wastewater treatment plants by a slightly modified concept.

Control of a Mobile Service Robot Using Human Evaluations of Task-related Movement Patterns

An important future application of robotics will be the utilization of mobile service robots in homes and offices, assisting people with their daily chores. Above all, these robots must be safe to use. In addition, service robots must be designed to be effective, productive, and user-friendly. In order for people to accept and use these robots, the robots must behave in a manner acceptable to humans. The intelligent control of service robots must take into. account the effects of robot behaviors on people. This paper focuses on the interactions between humans and mobile service robots, studying how people respond to a variety of robot behaviors as the robot performs certain tasks. Since different people could react differently to service robots, this paper reports on the effects of users' gender, age, technical background, and robot body preference on the responses to robot behaviors. The robot behaviors include the robot approaching a human, the robot avoiding a human while passing, and the robot performing non-interactive behaviors. The level of comfort the robot caused human subjects was analyzed according to the effects of robot speed, robot distance, and robot body design. It is hoped that information gained from human factor studies can be used to obtain a better understanding of acceptability of service robots by different people, resulting in the design and development of more effective intelligent controllers for service robots in the coming new generation.

Intelligent control of precision linear actuators

This paper presents and compares possible intelligent control designs for precision motion control applications which are based on the use of linear actuators. The control schemes developed include adaptive control, compositie control using a radial-basis function for nonlinear compensation and an iterative learning control scheme. The mathematical model for a permanent magnet linear motor is first presented on which the control designs are based. Theoretical analysis as well as full experimental results are provided for the control schemes. Practical issues in the overall implementation of a precision motion control system are also highlighted.

HYBRID INTELLIGENT CONTROL SCHEME FOR AIR H£ATING SYSTEM USING FUZZY LOGIC AND GENETIC ALGORITHM

ABSTRACT Fuzzy logic provides a means for converting a linguistic control strategy, based on expert knowledge, into an automatic control strategy. Its performance depends on membership function and rule sets. In the traditional Fuzzy Logic Control (FLC) approach, the optimal membership is formed by trial-and-error method. In this paper, Genetic Algorithm (GA) is applied to generate the optimal membership function of FLC. The membership function thus obtained is utilized in the design of the Hybrid Intelligent Control (HIC) scheme. The investigation is carried out for an Air Heat System ( AHS) an important component of drying process. The knowledge of the optimum PID controller designed, is used to develop the traditional FLC scheme. The computational difficulties in finding optimal memebership function of traditional FLC is allieviated using GA in the design of HIC scheme. The qualitative performance indicies are evaluated for the three control strategies, namely, PID, FLC and HIC. The comparison reveals that the HIC schene designed based on the hybridisation of FLC with GA performs better. Moreover, GA is found to be an effective tool for designing the FLC, eliminating the human interface required to generate the membership functions.

A behavior-based intelligent control architecture with application to coordination of multiple underwater vehicles

Presents a behavior-based intelligent control architecture for designing controllers which, based on their observation of sensor signals, compute the discrete control actions. These control actions then serve as the "set-points" for the lower level controllers. The behavior-based approach yields an intelligent controller which is a cascade of a perceptor and a response controller. The perceptor extracts the relevant symbolic information from the incoming continuous sensor signals, which enables the execution of one of the behaviors. The response controller is a discrete event system that computes the discrete control actions by executing one of the enabled behaviors. The behavioral approach additionally yields a hierarchical two layered response controller, which provides better complexity management. The inputs from the perceptor are used to first compute the higher level activities, called behaviors, and next to compute the corresponding lower level activities, called actions. The paper focuses on the discrete event subsystem, namely, the response controller. We illustrate the intelligent control architecture by discussing its application to the design of intelligent controllers for autonomous underwater vehicles used for ocean sampling missions. A complete set of discrete event models of the response controller of the underwater vehicles for the above application has been given, and their formal verification discussed.

Design patterns for intelligent control systems

This paper addresses the use of software design patterns and object oriented frameworks, to streamline the design and implementation of intelligent controllers for complex plants. It presents the ICa approach to intelligent control system development based on the reuse of control components over a real time integration middleware. The system described has been developed in the ESPRIT DIXIT project. This project was focused on the use of this technology in the construction of operational, tactical & strategical controllers for continuous process plants, but the ICa technology is addressed not only at this type of application, but to a broad spectrum of automated systems; from continuous process plants to autonomous vehicles or teleoperated robots.

Intelligent cross-coupled fuzzy feedrate controller design for CNC machine tools based on genetic algorithms

In this paper, an intelligent contour control strategy has been investigated to improve the contour error of CNC machine tools. An uncoupled contour control system is first analyzed and then a cross-coupled controller is added in the control loop to form a cross-coupled contour control system. An algorithm for an on-line estimation of the contour error in arbitrary curved contouring is also proposed. To further reduce the contour error, a cross-coupled fuzzy feedrate control scheme is presented. The controller parameters are all optimized by a genetic based learning algorithm. Experimental results show that the proposed control scheme is effective to improve the contouring accuracy of CNC machine tools.

Intelligent anti-skid brake controller using a neural network

The performance of current anti-skid brake controllers on aircraft becomes degraded due to the uncertain nature of the runway conditions. This paper presents the design of an intelligent anti-skid neural controller to overcome this problem. Their learning ability, nonlinear mapping ability and pattern-recognition capability are the features of neural networks that are ideally suited to the design of intelligent controllers. The controller described here identifies the runway condition from the aircraft-wheel responses, and modulates the brake torque for optimum braking. The proposed controller exhibits robustness under variations in brake characteristics and runway conditions. Simulation results confirm the satisfactory performance of the controller in adapting to changes in runway conditions.