Journal of Computer and Robotics
Volume:11 Issue: 1, Winter and Spring 2018

Solution to the safe and collision-free trajectory of the wheeled mobile robot in cluttered environments containing the static and/or dynamic obstacle has become a very popular and challenging research topic in the last decade. Notwithstanding of the amount of publications dealing with the different aspects of this field, the ongoing efforts to address the more effective and creative methods is continued. In this article, the effectiveness of the real-time harmonic potential field theory based on the panel method to generate the reference path and the orientation of the trajectory tracking control of the three-wheel nonholonomic robot in the presence of variable-size dynamic obstacle is investigated. The hybrid control strategy based on a backstepping kinematic and regressor-based adaptive integral sliding mode dynamic control in the presence of disturbance in the torque level and parameter uncertainties is employed. In order to illustrate the performance of the proposed adaptive algorithm, a hybrid conventional integral sliding mode dynamic control has been established. The employed control methods ensure the stability of the controlled system according to Lyapunov’s stability law. The results of simulation program show the remarkable performance of the both methods as the robust dynamic control of the mobile robot in tracking the reference path in unstructured environment containing variable-size dynamic obstacle with outstanding disturbance suppression characteristic.

Chaos is a nonlinear behavior that shows chaotic and irregular responses to internal and external stimuli in dynamic systems. Chaos appears in the system which is very sensitive to initial condition. Study of chaos dynamic systems has quickly spread in the last three decades, and it has become a very attractive area of research to remove dynamic chaotic behaviors and make nonlinear systems stable. Stabilization has been considered as a high usage tool to eliminate aberrant behaviors of chaotic system and can be divided into two categories, regulation and tracking. In regulation stabilizing, system becomes stable by designing proper control signals to one of the available balance points or one of the alternate unstable paths on strange absorbers in chaos system. Another set of chaos systems stabilizing is tracking. In this type of stabilization, a reference signal varying with time and a control frame are considered in the way the system responses follow that signal. In this thesis, both regulation and tracking stabilizing are considered, first without chaos and then with chaos. For this purpose, smart and powerful adaptive neuro fuzzy inference system (ANFIS) technic is used. The proposed method is examined by a famous example of a chaos system called the Lorenz system. The simulation results show the ability of the proposed method. Our proposed approach is ANFIS which is designed for Lorenz chaotic system. it is compare with PID controller in the system .

Biped robot locomotion is one of the active research areas in robotics. In this area, real-time stable walking with proper speed is one of the main challenges that needs to be overcome. Central Pattern Generators (CPG) as one of the biological gait generation models, can produce complex nonlinear oscillation as a pattern for walking. In this paper, we propose a model for a biped robot joint trajectory in order to be able to walk straight, exploiting polynomial equations for the support leg’s joints and Truncated Fourier (TFS) Series equations for the swing leg’s joints in the sagittal plane and frontal plane. Four customized genetic algorithms (GA-1 to GA-4) with different implementations for the crossover steps are used as evolutionary algorithms to optimize equation parameters and achieve the best speed and performance in walking motion. These four GAs differ in crossover step and parent selection parts. After a primary evaluation to make sure the next generation is better off than before, we consider a clever comparison feature between the best of two generations (parent and child) in GA-4. The algorithms have been tested on the Darwin humanoid robot in the Webots simulator environment where the results show that the GA-4 model has the best performance and achieves the desired fitness value.

By introducing Colpitts oscillator as a chaotic system, this paper deals with back-stepping control method and investigates the restrictions and problems of the controller where non-existence of a suitable response in the presence of uncertainty is the most important problem to note. In this paper, the back-stepping sliding mode method is introduced as a robust method for controlling nonlinear Colpitts oscillator system with chaotic behavior. Thereafter, we simulated the proposed method and compared its advantages with that of the previous method.  The experimental results show that the most important advantages of the proposed method are making system robust in case of uncertainties and disturbances, and also having a fast response.

Nowadays, online social networks are considered as one of the most important emerging phenomena of human societies. In these networks, prediction of link by relying on the knowledge existing of the interaction between network actors provides an estimation of the probability of creation of a new relationship in future. A wide range of applications can be found for link prediction such as electronic commerce and recommender systems or identification of terroristic relations in social networks. In this article, a new idea is presented for the prediction. It is an integration of the two methods of prediction of similarity score based link and prediction of probabilistic link, which is placed in a new category of link prediction methods. This idea acquires the similarity score between nodes from probabilistic techniques and through using learning automata, and provides better results compared to other criteria methods on standard datasets.

In this paper, we propose a fuzzy-servoing controller method for automatic welding. The proposed method uses a vision based arc tracking to find the initial points of the weld seam and to track them without a prior knowledge. Due to a serious melt down in the weld pool during the welding process, the method requires to control the welding torch in two directions, up-down and left-right directions. To perform these, an IR, two CCD cameras and two stepper motors by inference of fuzzy rules are used to control the movement of the welding torch tip. Therefore, the proposed method canaccomplish different tasks such as welding a curved seam or moving into multi directions, while majority of autonomous arc-welding approaches are single-purpose so that they are designed to accomplish only one task, like welding in a direct line or a predefined arc seam. This method is applied on several workpieces and then the maximum error in both directions is shifted to zero in 30ms. This time is proper for workpieces with thickness in the range of [1-5] mm.

A key step for success of marketer is to discover influential users who diffuse information and their followers have interest to this information and increase to diffuse information on social media. They can reduce the cost of advertising, increase sales and maximize diffusion of information.  A key problem is how to precisely identify the most influential users on social networks. In this paper, we propose a method to discover influential users based on knowledge management cycle that is called KMIU. The knowledge management cycle consists of several stages including capture, organize, storage, retrieval and mining stages. We try to analyze influential users in two micro bloggings networks as Facebook and twitter by KMIU method. The experimental results showed the proposed method maximize diffusion and has an accuracy 0.55. These maximization and accuracy are more than those of the previous methods.

In a robotic soccer team, goalkeeper is an important challenging role, which has different characteristics from the other teammates. This paper proposes a new learning-based behavior model for a soccer goalkeeper robot by using Petri nets. The model focuses on modeling and analyzing, both qualitatively and quantitatively, for the goalkeeper role so that we have a model-based knowledge of the task performance in different possible situations. The different primitive actions and behaviors as well as the events to switch between them, and also environment models were designed and implemented. For this purpose, a modeling and analysis framework based on Petri nets is used, which enables modeling a robot task, analyzing its qualitative and quantitative properties and using the Petri net representation for actual plan execution. The proposed model building blocks and some tasks of robot are detailed. The novelty of approach is considering some alternatives through tasks execution, which are implemented by conflicts in their Petri net models, and also Q_learning employment in these decision points in order to learn the best policy. Therefore, the execution of actions in different tasks will be controlled effectively. The results of theoretical analysis of some case studies show impressive performance improvement in goalkeeper task execution.