In the soccer game strategy Radio Frequency data transmitter is used to communicate among robot . The development of the controllers is carried out by means of a reconfigurable platform based on field-programmable gate arrays. This platform combines specific hardware to implement fuzzy inference modules with a general-purpose processor, thus allowing the realization of hybrid hardware/software solutions . The merger method is applied to fuzzy rule base simplification by automatically replacing the fuzzy sets corresponding to a given cluster with that pertaining to cluster prototype . Target tracking requires team coordination to maintain a desired formation and to keep team-mates and target together. Generally, distributed autonomous systems using multiple robots are considered superior to others in terms of reliability, expandability, and flexibility. In contrast to a single robot system; they provide increased robustness by taking advantage of inherent parallelism and redundancy. Moreover, the versatility of a multi-robot system can provide the heterogeneity of structures and functions required to undertake different missions in unknown environmentalconditions . Research in autonomous multi-robot systems often focuses on mechanisms to enhance the efficiency of the group through some form of cooperation among the individual agents. One of the greatest challenges in robotics is to create machines that are able to interact with unpredictable environments in real time . Intriguingly, a similar relationship between group size and efficiency has been documented in social robots.
This document is organized as follows: Chapter 2 presents the RFNN architecture, training and adaptive learning rate math models in detail. Chapter 2 also introduces the “shocking” algorithm which is used to stabilize the adaptive learning rate models. Chapter 3 validates the “shocking” algorithm on two inherently unstable benchmark problems. Chapters 4 and 5 present two implementaions of the RFNN to actual pattern analysis problems. Specifi- cally, Chapter 4 shows how an optical character recognition (OCR) approach with mapped sonar data and the RFNN can be used to solve the global self-localization (GSL) problem for autonomous mobilerobots. Chapter 5 uses images of outdoor traffic signs to demon- strate a solution to outdoor landmark recognition. Both Chapters 4 and 5 demonstrate the concept of using previously learned features to expedite the training process, as well as transferring “knowledge” between neural networks. Chapters 4 and 5 also demonstrate how changes in the architecture (pruning and/or adding neural units and synaptic weights) do not necessarily entail a redesign penalty. Each of these implementations demonstrate how features that were matured on different data and/or on a small subset of classes can significantly reduce the training time required for learning a new and/or larger set of classes. Chapter 6 presents the HEC Kohonen neural network architecture, training and recall algorithms in detail. All math models are furnished so that the reader can duplicate the HEC Kohonen. So that the HEC Kohonen can autonomously regulate its size, we devote a significant amount of space to the issue of measuring compactness. Specifically, we es- tablish a set of standards expected of a compactness test, and compare these to existing compactness tests. From each test we extract the elements that partially satisify these stan- dards to develop a hybrid compactness nest which allows a user to control the sensitivity to significance values. We add even greater utility to the hybrid compactness test by en- abling it to detect V-shaped clusters which might have otherwise gone undetected. Armed with a robust compactness test, we then give the HEC Kohonen the ability to add neural units through the mitosis algorithm. Removing neural units is also accomplished through pruning. We validate our models on two-dimensional synthetically generated clusters and the four-dimensional IRIS data set. In Chapter 7 we justify using the HEC Kohonen for autonomous mobile robot map building on the basis of environment representation, self- organization, updatability, unlimited dimensionality, multifunctionality, data size, complex- ity and the significant utility of the stochastic measurement inherent to the HEC Kohonen. We then employ the HEC Kohonen to learn several different indoor environments using actual two-dimensional sonar data gathered from mobilerobots as they explored different rooms.
(Camacho et al., 1998; Peña, 2002), although this strategy is considered heavy due to its computational effort in practice. The NMPC stability analysis with finite receding horizon has been studied in Mayne et al. (2000) and Fontes (2001). Recently, the qualities of predictive control have been explored and applied in robotics, woks like Dongbing et al. (2006), Hedjar et al. (2005), Künhe et al. (2005) and Ramírez et al. (1999) show different approaches and strategies in MPC with good results for tracking control and regulation. This paper applies NMPC to dynamic model of mobile robot and makes an analysis by computes times for optimization algorithm so that to be able to implement the controller in experimental works.
Navigation of autonomous mobilerobots in dynamic and unknown environments needs to take into account different kinds of uncertainties. Type-1 fuzzy logic research has been largely used in the control of mobilerobots. However, type-1 fuzzy control presents limitations in handling those uncertainties as it uses precise fuzzy sets. Indeed type-1 fuzzy sets cannot deal with linguistic and numerical uncertainties associated with either the mechanical aspect of robots, or with dynamic changing environment or with knowledge used in the phase of conception of a fuzzy system. Recently many researchers have applied type-2 fuzzy logic to improve performance. As control using type-2 fuzzy sets represents a new generation of fuzzy controllers in mobile robotic issue, it is interesting to present the performances that can offer type-2 fuzzy sets by regards to type-1 fuzzy sets. The paper presented deep and new comparisons between the two sides of fuzzy logic and demonstrated the great interest in controlling mobile robot using type-2 fuzzy logic. We deal with the design of new controllers for mobilerobots using type-2 fuzzy logic in the navigation process in unknown and dy- namic environments. The dynamicity of the environment is depicted by the presence of other dynamic robots. The per- formances of the proposed controllers are represented by both simulations and experimental results, and discussed over graphical paths and numerical analysis.
Abstract This paper uses the general framework of dynamic feedback linearization for stabilization of mobilerobots. Instead of using unicycle model for control design, this paper uses a comprehensive model which is based on the physics of differential drive robots. The model used in the paper describes nonholonomic underactuated behavior of robot in terms of the physical dimensions and velocities of the wheels. Next, the proposed control is applied to this model and it is theoretically proven that dynamic feedback linearization can successfully solve the stabilization problem. To evaluate the performance of proposed control, another controller is designed based on the Lyapunov’s method. The performance of the two controllers and the complexity of control gain tuning process are compared. Next, the robustness of the proposed control against uncertainties is studied. The results of analysis and simulations show that the proposed control has very good performance against parametric uncertainties.
The very first step of the analysis is the formal validation of the com- ponent models by verifying for example the non-locking aspect of the task. Once the model has been checked, an instance of the component can be gen- erated using the code generation feature of the Mauve framework in order to ensure the validity of the running code.
As widely known, kinodynamic planning is the most difficult task when developing mo- tion planners, and generating feasible paths is usually one of the most computationally expensive operation, because the planner has to deal with dynamic constraints given generally in the form of non-linear differential constraints. What we want to study in this chapter is the effect of generating quasi-feasible (controllable) trajectories, com- posed as sequences of piece-wise feasible trajectory. The goal is to analyze the intercon- nection of the low-level control law for trajectory tracking with the planner that gener- ates such trajectories and what’s the impact of this choice in the planner. What we obtain is a practical tracking (since asymptotic tracking is impossible due to non-feasibility of the path), where we want to derive bounds on tracking error of such trajectories   . The advantages of this analysis is that the planner can be very simple and generate simple non-feasible trajectories, while still guaranteeing bounded tracking er- ror. This information can be used to plan safe and robust paths without directly dealing with differential constraints. As we’ll see later in this chapter, piece-wise controllable trajectories for many mobilerobots can mean simple straight lines, which are very easy to concatenate with existing algorithms and with the proposed algorithms in this the- sis. This reduces by many times the runtime of the planner, making it suitable for fast replanning but still considering the dynamic of the vehicles. Finally we study the same conditions taking into account uncertainties and disturbances on the system. Using ISS (Input to State Stability) Lyapunov analysis we derive bounds on tracking error of piece- wise controllable trajectories in the presence of disturbances on the system, allowing for robust and fast kinodynamic planning algorithms.
Article represents method for probability determining of concepts conjunction consistency and Kruskal’s algorithm modification based on developed method. It is applied for non- determinism reducing on individuals to merging selection in n R >= rule. Experiment results shows that developed algorithm allows reducing time for concept consistency checking. In future research, we will apply developed techniques to cover SROIQ logic. In addition, we will research field of ontologies application and in future, we will present knowledge base approach for program static analysis.
The implementation of global distributed information systems based on cloud and grid approaches. There are many problems of ensuring a high level of information security of these systems because they operate critical or confidential data, and the elements of these systems found in different physical locations to communicate with that uses open standards and protocols of the Internet. The existing distributed information systems implemented using a variety of architectural and technology platforms, which usually do not meet the current challenges in the field of ensuring a high level of information security. In addition, the actual question of the integration of these systems with corporate information systems, and providing a high level of security used integration solutions. The aim of this work was the systematization and analysis of proven technologies for building high reliable information security infrastructure of global distributed computing systems. As part of the work identified approaches to implementation of information security infrastructure based on technical standards Globus Toolkit, OGSA, UNICORE, gLite. The features of the implementation of security infrastructure based on these standards, as well as the possibility to interact with external systems based on industry standards such as SOA, Web Services.
In this paper the method of synthesis of distributed regulator, uniform control object is regarded, which is based on the specified inaccuracy. The function of the initial heating has been received; the mathematical modeling of the process has been conducted as well as the analysis of the results. With the help of the obtained regulator hardware and software complex has been designed in the Pascal programming language, the complex allows to simulate the behavior of the temperature fields in the isotropic rod. The article presents the simulation of the temperature process for different configurations of the system. Namely, there is simulation with different number of impulsive heating sources with the relay control principle. The practical results of these studies suggest the possibility of building silicon carbide heating element, made in the form of an isotropic rod.
Flexible Viterbi decoder becomes extremely important as a result of increasingly modern wireless communication standards in SDR (Software Defined Radio) systems. In order to support multi-standard service and area saving, a flexible Viterbi decoder chip with cascaded ACS ( Add Compare Select ) unit is preferred. In such a decoder chip, there is a big irregular addressing problem for temporary ACS computing results storing. To solve this, a generalized efficient state metric memory management method has been developed. Analysis shows the design is highly flexible and efficient.
We investigated the radio signal path attenuation behavior by conducting a measurement survey in a GSM network, which is transmitting at 1.8GHz and 2.1GHz band in the Vijayawada city, Andhra Pradesh, India. Initially the measured field strength data collected at various locations from the base stations are used to estimate the path loss. It has been observed that the path loss increases with distance in this case. In this paper a detailed analysis for the calculation of path loss by using Okumura Hata model and the Cost 231 Hata model. We calculated the path loss data and compared with real time data obtained for both 1.8GHz and 2.1GHz in an urban environment by using the received signal strength (RSS) of the base station with and without noise. Our experimental result shows that the Okumura Hata model is one of the best models for calculation path loss at urban environment.
their subsystem satisfies the bounds broadcast to the other controllers. Each controller solves a local min-max problem on each iteration to optimize performance with respect to worst-case disturbances. Richards and How  presented a decentralized algo- rithm for systems with coupled constraints. Relevant plan data is exchanged between subsystems to ensure that all decisions are consistent with satisfaction of the coupled constraints, e.g., collision avoidance. The decentralized method employs at each time step a sequential solution procedure, in which the subsystems solve their planning prob- lems one after the other. Keviczky et al.  presented decentralized MPC schemes for decoupled systems where cost function and constraints couple the dynamical behav- ior of the systems. Each MPC controller is associated to a different node and computes the local control inputs based only on its current states, its neighbors current states, its terminal region, its neighbors terminal regions and models and constraints of its neigh- bors. Based on such information each node computes its optimal input and its neighbors optimal inputs. The input to the neighbors will only be used to predict their trajectories and then discarded while the first component of its optimal input will be implemented. In [32, 106], a distributed MPC algorithm for unconstrained, linear time-invariant (LTI) systems in which the dynamics of the subsystems are influenced by the states of inter- acting subsystems was described. A contractive state constraint is employed in the MPC optimization of each subsystems and asymptotic stability is guaranteed if the systems satisfies a matrix stability condition. Dunbar and Murray  used the exchange of the most recent optimal control trajectory between coupled subsystems prior to each up- date. The stability analysis is more difficult in this case. The asymptotic stability of a multi-vehicle formation system without collision avoidance constraints is guaranteed by requiring that each distributed optimal control does not deviate too far from the previous optimal control.
Wen and Lin presented an integral information technology study for geographic information. They covered the teaching and learning processes on an electronic environment using the Moodle system, as well as promoting students’ achievements interactively. Another analysis conducted on the use of Moodle system reports contained views and posts of 4 different SME’s training courses Nagi . The concept pf MILES( Military English Learning System) was introduced by Tick, it dels with software components used in OSS LMS application. Into addition to that, the paper gives thorough details on course development and evaluation chances available. Furthermore, it analyzes the usability and learning habits of the material present to the end users (students) .
In the last 3 decades, the idea of robots doing human works has come to reality which was earlier considered as cannot be done and just an imagination. Robotics devices and machineries are now becoming the part of human life. Now a days robots are very commonly used in service industry, armed forces, manufacture industry, etc. The one of the most challenging and demanding field of robotics is wheeled mobilerobots. One of the reasons for this is mobile robot needs mobility that helps it to move unrestrained all over its environment. As given in , a mobile robot can move its surrounding in many different ways. Therefore for a mobile robot, how it moves in its environment depends upon the type of approach used for its motion. A substantial portion of wheeled mobile robotics exploration/research includes developing robot model that mimic a car-like motion without the help of any human being. Also it has been seen as in case of well-known work in the field of mobile robotics the system strategy need not required to be very complex even with simpler one we can achieve our desired result. In case of mobile robotics, sometimes it becomes necessary that to perform a specific job we need group of mobile robot in formation. The requirement for formation of a group of mobile robot performing a specific task has leads to the growth of a new research field. The formation control problem for mobilerobots can be defined as finding a system which makes sure that the group of mobilerobots can hold on a given formation or precise set of formations. The objective of this work is to develop leader-follower structure, such that multiple mobilerobots can move in a given condition in formation. We are considering an obstacle free environment for our work. At first we need to know how our of mobile robot move in its surroundings. For understanding this process we need to understanding kinematic equation of motion. Kinematics is said to be a geometrical or mathematical analysis of how our system behaves in its environment without taking into considering the forces that cause this.
28. Martin-Guillerez, D., Guiochet, J., Powell, D., Zanon, C.: 1954 A UML-based method for risk analysis of human-robot 1955 interactions. 2nd International Workshop on Software Engi- 1956 neering for Resilient Systems, pp. 32–41 (2010) 1957 29. Nehmzow, U.: Flexible control of mobilerobots through 1958 autonomous competence acquisition. Meas. Control 28, 1959
configuration of the optimum potential field is automatically determined by genetic algorithm. Simulation experiments performed with three different obstacle configurations, and ten different routes, showed that the scheme reported has a good performance in environments with high obstacle densities, achieving a success rate of 93 per cent. Xin et al.  have proposed a method of global path planning based on neural network and genetic algorithm. They constructed the neural network model of environmental information in the workspace for a robot and used this model to establish the relationship between a collision avoidance path and the output of the model. Then the two- dimensional coding for the path via-points was converted to one-dimensional one and the fitness of both the collision avoidance path and the shortest distance are integrated into a fitness function. The simulation results showed that the proposed method is correct and effective. Wong et al.  proposed, a method based on Genetic Algorithms (GA) is to design a fuzzy system to control an omni-directional mobile robot so that it can move to any direction and spin at a rotating rate. In this method, an individual of the population in the GA-based method is used to automatically generate fuzzy sets of the premise and consequent parts of fuzzy system. A fitness function is proposed to guide the search procedure to select an appropriate parameter set of the fuzzy system such that the output of the fuzzy system can approach the output of data base established from the kinematics model of the three-wheeled mobile robot.
developed fuzzy control based on forecast learning. They have shown their results in simulation as well as experiment mode to drive the control of the robot. An approach for building multi‐input and single‐output fuzzy models has been proposed by Joo et al. . They have applied their technique to construct a fuzzy model for the navigation control of a mobile robot. Montaner et al.  have designed a fuzzy controller for autonomous mobile robot navigation to reduce the travel time from an initial to final position. Their technique was used on an experimental mobile robot, which uses a set of seven ultrasonic sensors to perceive the environment. Simulation and experimental results show that their method can be used satisfactorily on a mobile robot moving on unknown static terrains. An evolutionary learning of robot behaviours has been designed by Iwakoshi et al.  for Fuzzy Classifier System (FCS). They have presented eight different conditions in simulation to validate their technique. Li et al.  have designed a real‐time fuzzy target tracking control scheme for autonomous mobile robot by using infrared sensors. They have used infrared transmitters on the target and reflective sensors on the tracker mobile robot for target tracking control. They have shown their results in simulation mode. Xu et al.  have presented real‐time fuzzy reactive control for automatic navigation of an intelligent mobile robot in an unknown and changing environment. The reactive rule base governing the robot behaviour is synthesized corresponding to the various situations defined by the instant robot motion, environment and target information. Simulation results have been presented by the authors to validate their approach. Their techniques have not been investigated for target seeking and multiple mobile robot navigation.
algorithm should be employed at any particular time. This was updated with the new measurements provided by the active system for following. When the mea- surements varied significantly from those predicted by the model, another algorithm for following was used and the model was adapted according to this new al- gorithm for following. As the following of the road was being carried out, a neural network was trained in such a way that, while there was no drastic change in the road conditions, or the paths were repeated, the neural network directly provided the information nec- essary for steering the vehicle. In this way, the system imitated the behaviour of a human driver who, as well as steering according to the markings that he finds on the road, memorizes situations, thus decreasing the re- sponse time when these are repeated.
It has been previously shown in  that adding a social component to individual learning can improve the perfor- mance of a population of autonomous robots developing a simple group behaviour, i.e. foraging. Here we used a social seed as the social component in the arena. The social seed is a robot that is immobile but its social effect is the same as other robots meaning that other robots can perceive its presence and react to it as a robot. In a previous work  we investigated the effect of social seeds in simulation. Here we are interested in investigating if this effect also exists in robots controlled by the BEECLUST algorithm and how strong the effect is compared to the results from the simu- lation experiment. Therefore, we created a setup similar to the simulation setup: The main swarm consists of 10 robots. In the local optimum we placed an immobile robot as a social seed which can be recognised by other robots (see figure 3). To keep the conditions fair for the two optima (e.g. in terms of available space), we placed a dummy robot in the global optimum. The dummy robot is perceived as an obstacle by other robots.