By Topic

AI & Robotics and 5th RoboCup Iran Open International Symposium (RIOS), 2013 3rd Joint Conference of

Date 8-8 April 2013

Filter Results

Displaying Results 1 - 25 of 29
  • Honorary chairs

    Page(s): 1 - 3
    Save to Project icon | Request Permissions | PDF file iconPDF (150 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (39 KB)  
    Freely Available from IEEE
  • [Title page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (495 KB)  
    Freely Available from IEEE
  • A novel self-adaptive search algorithm for unstructured peer-to-peer networks utilizing learning automata

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (296 KB) |  | HTML iconHTML  

    Designing an efficient search algorithm is an important issue in unstructured peer-to-peer networks when there is no central control or information on the locations of objects. There are various search strategies with different effects on network performance. In k-random walks as a search strategy, having an adaptive value of k instead of a random value can affect performance of the network. Therefore in this paper, a distributed novel self-adaptive search algorithm has been developed by application of learning automata to overcome this challenge. This method does not aim to determine the value of k for k-random walks algorithm and each peer can issue walkers in a self adaptive manner. Simulation results show that the proposed search algorithm improves some features such as average number of walkers per query, average number of produced messages, number of hits per query and also success rate efficiently in comparison with the k-random walks algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent position control of slider-crank mechanism in the ship's propeller

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1065 KB) |  | HTML iconHTML  

    A wide range of design efforts has been done and continue to be investigated in the development of slider-crank mechanism in the ship's propeller. The position control of a slider-crank mechanism, which is driven by the piston cylinder actuator using a nonlinear control strategy to adjust the blade pitch angle, is studied. The Computed Torque Control (CTC) is an effective motion control strategy, which can ensure global asymptotic stability. However, this control scheme requires a precise system model. In addition, when the derivative gain is sufficiently large, a small amounts of measurement or process noise can cause large amounts of change in the output and even cause the process to become unstable. Therefore, to handle these issues, we proposed a Genetic Algorithm based CTC system that attempts to compensate any parameter deviation and disturbances as well as minimize the error by adjusting the PD gains. Computer simulations are carried out, and it is proved that asymptotically stability is achieved the results confirm the high tracking capability and effectiveness of the proposed control scheme. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New applied methods for optimum GPS satellite selection

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (629 KB) |  | HTML iconHTML  

    Geometric dilution of precision (GDOP) is a powerful, simple and widely used measure for assessing the effectiveness of potential measurements to specify the precision and accuracy of the data received from global positioning system (GPS) satellites. The most correct method to classify or approximate the GPS GDOP is to use inverse matrix on all the combinations and choosing the lowest one, but inversing a matrix puts a lot of computational burden on the navigator's processor. This approach however is a time-consuming task. To overcome the problem, basic back propagation neural network (BPNN) was used. Since the BPNN is too slow for practical problems, including the GPS GDOP classification, in this paper several methods, namely, resilient back propagation (RBP) to train a NN, naive Bayes classifier, Fisher's linear discriminant (FLD) and k-nearest neighbor (KNN) for classification of the GPS GDOP are proposed. Simulation results show that these methods are much more efficient to classify the GPS GDOP data than previous methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human-inspired ensemble pruning using hill climbing algorithm

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (586 KB) |  | HTML iconHTML  

    Hill climbing algorithm is one of the famous optimization algorithms which has been applied to solve the problem of pruning an ensemble of classifiers. In this study, we propose an ensemble pruning method using Hill Climbing algorithm whose evaluation measure is “Human-Like Foresight” (HLF). To invent this novel measure, we are inspired by human foresight in facing different situations in his life. Experimental comparisons on 10 datasets indicate that pruning a hetrogeneous ensemble of classifiers using the proposed measure achieves higher accuracy compared with the state-of-the-art measures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combination of krill herd algorithm with chaos theory in global optimization problems

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (621 KB) |  | HTML iconHTML  

    Krill herd optimization algorithm is a biological optimized algorithm which simulates Krill group social behavior in order to solve global optimization problems. The position of each krill in time period is dependent on induced movement of other krills, foraging activity and physical diffusion. In this paper, chaos theory is combined with KHA to improve global optimization problems, which acts on random specifications of this algorithm and logistic chaotic mapping is used in physical diffusion. The proposed method is being evaluated in some problems. Result indicate that krill chaotic algorithm has better performance than standard krill algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Biped robot joint trajectory generation using PSO evolutionary algorithm

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1104 KB)  

    In last decades, interest in biped robots (specially humanoid robots) have been growing up. Stable Walking is one of the critical challenging problems in these kinds of robots and many researches have been done to achieve a walking model similar to human. Central Pattern Generator (CPG) is one of the biological gait generation models which can produce complex nonlinear oscillation as a pattern for walking. In our model we use polynomial equation for the support leg and Sinusoid Fourier series equation for the swing leg in sagittal plane for producing a single step of walk. For balancing, the same values are used for both swing and support leg with Sinusoid Fourier series equation in frontal plane. PSO is used as an evolutionary algorithm to optimize equation parameters and achieve the best speed and performance in walking. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An improved PSO-based path planning algorithm for humanoid soccer playing robots

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (249 KB) |  | HTML iconHTML  

    In this paper we introduce an improvement in the path planning algorithm of the humanoid soccer playing robot which uses Ferguson splines and PSO (Particle Swarm Optimization). Ferguson splines create preliminary paths by using random generated parameters. The random parameters are then iteratively feed into the PSO for optimization and converging to optimal paths. The objective of the algorithm is to find a path between the humanoid soccer playing robot and the ball which should be as short as possible and yet satisfying the specified safety in the path in terms of the distance from the obstacles. Our proposed method make a balance between the path shortness and the safety which makes it more efficient in the specified case study for humanoid soccer playing robots and also any path planning among various obstacles in other crowded environments. Finally the experimental results show that our proposed algorithm converges in at most 60 iterations with the average accuracy of 92 % and path length overhead of 14%, planning the shortest and yet safest path. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimizing cognition cost using conditional vision for humanoid soccer robot

    Page(s): 1 - 4
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (435 KB) |  | HTML iconHTML  

    In this paper we show how the vision module can be divided to stationary and mobile object detection subsystems. According to the results, by active management of the robot image processing, the robot processing load is reduced and yet the accuracy of object tracking and self-localization is preserved. Our proposed conditional vision method is used to decrease the robot cognition cost. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel adaptive hybrid framework for job shop scheduling problem

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (263 KB) |  | HTML iconHTML  

    This paper deals with the Job Shop Scheduling Problem (JSP) with the objective of minimizing the makespan criterion, the time elapsed between the start of the first job and end of the last job arranged in a job sequence. We propose a novel multi-population based framework called HADP-JSP to solve the JSP. In the HADP-JSP the main population is divided into several groups. Each group adaptively chooses one algorithm from the algorithm pool and then uses it to find solutions (schedules). The operation of selecting an algorithm is done based on the algorithm fitness. The fitness of the algorithms implies the average improvement which they make on the makespanes of the schedules in a group. The algorithm pool consists of five algorithms developed using the Memetic Algorithm, Genetic Algorithm, and Simulated Annealing Algorithm. We have assessed the efficiency of HADP-JSP by running it on a set of 20 well known instances introduced by Lawrence. We have compared the results obtained with those of the three algorithms established in the literature during the last five years. The results indicate that in 95% of all cases the proposed approach can yield the solutions that their values of the makespan are equal to the Best Known Solution (BKS). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approach to design a robust software architecture and an intelligent model for multi-agent systems

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (555 KB) |  | HTML iconHTML  

    A successful multi-agent system requires the intelligent agents to perform within a dynamically complex environment where proper and quick response in a cooperative manner is a primary key to successfully complete a task. This paper proposes a non-deterministic decision making method using electric fields and high-level decision making. Different layers are designed, defined, and implemented for the software architecture with focus on system adaptability, sustainability, and optimization. Consequently, a software architecture is proposed in this paper to complement the AI algorithms. The proposed architecture aims to provide a well-structured and managed system for control, behavior, and decision making of multi-agent systems. The proposed decision making approach in this paper is based on layered artificial intelligence implemented using vector-based fuzzy electric fields and a decision tree. Furthermore, an approach to model the world which, in this paper, is called Agent Relative Polar Localization is introduced. This world model is based on fuzzy measurements and polar coordinates. In order to optimize the overall performance of the system learning methods have been introduced to the system. The proposed system in this paper has been implemented on soccer robots to evaluate the performance of the system. The results show that the proposed system implemented on the soccer robots is reliable and robust. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An IMU-based system identification technique for quadrotors

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (593 KB) |  | HTML iconHTML  

    Accurate system identification has an important role in designing high-performance controllers for robotic platforms. Most advanced controllers are designed based on the plants' dynamic models and their identified parameters. However, some models and their parameters change because of payload or condition variations. Online identification of these changes leads to develop high performance adaptive controllers. In this research, a rigorous amount of study is carried out to identify the parametric variations of a multi-rotor using a sensory system. The proposed method applies an inertial measurement unit (IMU) to identify the exact center of mass and its displacements. This method, which is based on the genetic algorithm (GA), is independent of the IMU location. The proposed algorithm is theoretically investigated while experimental results are presented to validate the performance of the algorithm. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Flexible snake robot: Design and implementation

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (405 KB) |  | HTML iconHTML  

    This paper presents a snake robot able to pass different and difficult paths because of special physical form and movement joints mechanism. These snake robots have no passive wheels. The robot moves by friction between the robot body and the surface on which it is. The joints have been designed and fabricated in a way that each joint has two freedom grades and it may move 228 degrees in every direction. Each joint has two DC servo motors and the power is transferred from the motors output to the joint shaft through bevel gear. The flexibility of the robot makes possible to move forward, back and laterally by imitating real snake's moves. In this paper different measures have been presented in order to design and assemble the joints, motors driver, different ways to guide the robot and its vision. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hand gestures recognition using dynamic Bayesian networks

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (680 KB) |  | HTML iconHTML  

    In this study a method for hand gesture recognition using dynamic Bayesian networks was presented. This study includes two main subdivisions namely: hand posture recognition and dynamic hand gesture recognition (without hand posture recognition). In the first session, after hand segmentation using a method based on histogram of direction and fuzzy SVM classifier, we train the posture recognition system. In the second session, after skin detection and face and hands segmentation, their tracing were carried out by means of Kalman filter. Then, by tracing the obtained data, the positions of hand was achieved. For combining the achieved data and output of hand posture recognition unit we utilize Bayesian dynamic network. For recognition of 12 hand gestures in this study, 12 Bayesian dynamic networks with two distinct designs were used. The difference between these two models is in the utilizing features and their relations with each other. Therefore, one of these models was used based on each gesture feature. The results of implementation show the about 90% average accuracy for all gestures. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrating disparity and edge detection algorithms to autonomously follow linear-shaped structures at low altitude

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1236 KB) |  | HTML iconHTML  

    One of the main requirements in enabling autonomous flight of Micro Aerial Vehicles is the ability of autonomous navigation. One possible solution to solve this navigation problem is to use vision-based line-following algorithms. Such vision-based algorithm could rely on the various linear structures, which are present in the human constructed environment. Edge detection and disparity estimation have proven to be strong algorithms for the detection of nearby objects. However, these detection algorithms have their weaknesses. The candidate lines found by both algorithms are input for the Probabilistic Hough Transform, which is used to select the best candidate and to determine a directional vector from this line. This paper is a survey for the experimental circumstances to fairly test both algorithms for a line-following task, which is one of the challenges of the Indoor Micro Aerial Vehicle competition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Resource allocation in grid systems using collective case based reasoning methods and learning automata

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (517 KB) |  | HTML iconHTML  

    At this article, we study the solutions about resources allocation in grid systems by means of synthetic method of collective case based on reasoning and learning automata. The collective case based on reasoning method in relation to agents, solves problems according to main agent method as scheduler agent. In fact, scheduler agent chooses a method within all present methods and sends it to other agents. All other agents use this method to find identical cases. These methods can be homogeneous or inhomogeneous. We try to study the effect of homogeneous or inhomogeneous agents and also using an identical case base or several discrete case bases for final answer so that each base pertains to one of the agents. The agents use ICBR-LA procedure in homogeneous methods and different kinds of CBR procedures like CBR-LA and ICBR-LA and also Max-Min and Min-Min methods in inhomogeneous cases. The scheduler agent chooses a method for solving a problem according to mentioned methods and sends it to other agents. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Persian handwritten digits recognition by using zoning and histogram projection

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (274 KB) |  | HTML iconHTML  

    In this paper, Persian handwritten digits reorganization by using zoning features and projection histogram for extracting feature vectors with 69-dimensions is presented. In classification stage, support vector machines (SVM) with three linear kernels, polynomial kernel and Gaussian kernel have been used as classifier. We tested our algorithm on the dataset that contained 8600 samples of Persian handwritten digits for performance analysis. Using 8000 samples in learning stage and another 600 samples in testing stage. The results got with use of every three kernels of support vector machine and achieved maximum accuracy by using Gaussian kernel with gamma equal to 0.16. In pre-processing stage only image binarization is used and all the images of this dataset had been normalized at center with size 40 × 40. The recognition rate of this method, on the test dataset 97.83 % and on all samples of dataset 100% was earned. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improvement of robot navigation using fuzzy method

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (413 KB) |  | HTML iconHTML  

    In this paper a technique for autonomous navigation of mobile robots is presented. The most important advantage of this method is to ignore the physical model of the robot and that the robot model is considered as an unknown but predictable system. This approach can be executed in environments which robot navigation is done using global sensors e.g. a camera installed in the environment to sense and control the robot and also every feedback system which is able to measure the velocity of the robot can be used for this technique. In this approach, the well-known fuzzy method, Takagi-Sugeno, has been applied to estimate the dynamic model of robot. Our technique has been applied successfully in small-size soccer robots league for improvement of soccer robots navigation. In this league a shared vision system is used to obtain the position and orientation of the playing robots and position of the ball and no interference is performed by human during a game. The fuzzy system produces the desired model between inputs and outputs of navigation system with less process time and more accuracy rather than other available methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simulation robocup by agent oriented methodology: Prometheus

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (986 KB) |  | HTML iconHTML  

    Engineering has always tried to develop tools and techniques for software development on different systems. Meanwhile, researchers are constantly looking to find very powerful and effective techniques in software engineering. One of the issues that had been introduced in the past decade Agent-Oriented system. Agent oriented methodologies have recently become more and more popular as general way in software engineering. Nowadays, with the development of agent-oriented system 'Various agent oriented methodologies have emerged. So in this paper, at first we have introduction. Then in Section 2 we will explain the agent-oriented methodology (Prometheus) and we try to implement the Robocup environment by one of the agent-oriented methodologies (Prometheus Design Tool) in Section 3. Finally, we will take result. We hope this article is guidance for researchers in this field. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of flat terrain for the atlas robot

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1344 KB) |  | HTML iconHTML  

    This paper gives a description of an approach to analyze the sensor information of the surroundings to select places where the foot of a humanoid can be placed. This will allow apply such robot in a rescue scenario, as foreseen in the DARPA Robotics Challenge, where a robot is forced to traverse difficult terrain. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evolutionary approach for developing fast and stable offline humanoid walk

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (691 KB) |  | HTML iconHTML  

    To make stable and fast walking in humanoid robot possible, lots of works has to be done including attitude estimation, dynamic stability controls, path planning and online position tracking. These processes need an exact mechanic modelling of the robot's body structure. In this paper, an evolutionary approach is used to model the human walk for a standard humanoid robot named NAO. This method makes use of inverse kinematics for trajectory generations. Additionally a novel method is proposed for mapping from gait design to genetic algorithm, in order to optimize generated trajectory parameters. The proposed method leads us to forward velocity of 64 cm/s, which is a superior result compared to the other common methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A high quality image hiding scheme based upon noise visibility function and an optimal chaotic based encryption method

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3038 KB) |  | HTML iconHTML  

    This paper presents a novel image steganographic approach for hiding a secret image in the cover image deals with improving both visual quality of the stego-image and the security of the secret image, while still providing a large embedding capacity. First, to improve both the visual quality and to keep the embedding capacity at an acceptable level, the payload of each region of the cover image is determined dynamically based on Noise Visibility Function (NVF). Second, to ensure the security of the secret image, an optimal chaotic based encryption method is generalized to transform the secret image into an encrypted image. Third, the optimal chaotic based encryption method is obtained by using GAiPSO algorithm to find an optimal secret key. The optimal secret key is able to encrypt the secret image in such a way that after embedding, the rate of changes in the stego-image can be decreased which result in increasing the quality of the stego-image. The experimental results demonstrate that the proposed scheme is able to achieve a good trade-off between the payload and the setgo-image quality. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A debugger tool for vision on humanoid framework

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (740 KB) |  | HTML iconHTML  

    In the RoboCup Standard Platform League (SPL), NAO biped robots are used for all teams in competitions. The robots have two on-board directional cameras and should perform fully autonomous, which requires precise data. The debugging tools always play critical role in developing reliable algorithms and calibrating sensors. In this paper we present a debugger and visualizer for vision of a standard platform league robot. This tool can be utilized for running off-line image processing algorithms aside calibrating the vision parameters like camera offsets and color lookup table. It also provides a very simple connection manager for transferring data with multiple robots and simulator. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.