JournalTOCs

Artificial Life and Robotics

[8 followers] Follow
Full-text available via subscription

Subscription journal
ISSN (Print) 1614-7456 - ISSN (Online) 1433-5298
Published by Springer-Verlag

[2216 journals]

Eye-vergence visual servoing enhancing Lyapunov-stable trackability
- Abstract: Abstract Visual servoing methods for hand–eye configuration are vulnerable for hand’s dynamical oscillation, since nonlinear dynamical effects of whole manipulator stand against the stable tracking ability (trackability). Our proposal to solve this problem is that the controller for visual servoing of the hand and the one for eye-vergence should be separated independently based on decoupling each other, where the trackability is verified by Lyapunov analysis. Then the effectiveness of the decoupled hand and eye-vergence visual servoing method is evaluated through simulations incorporated with actual dynamics of 7-DoF robot with additional 3-DoF for eye-vergence mechanism by amplitude and phase frequency analysis.
  PubDate: 2013-05-11
Medical image diagnosis of lung cancer by multi-layered GMDH-type neural network self-selecting functions
- Abstract: Abstract In this study, a revised Group Method of Data Handling (GMDH)-type neural network self-selecting functions is applied to the computer aided image diagnosis (CAD) of lung cancer. The GMDH-type neural network algorithm has an ability of self-selecting optimum neural network architecture from three neural network architectures, such as sigmoid function neural network, radial basis function neural network and polynomial neural network. The GMDH-type neural network also has abilities of self-selecting the number of layers, the number of neurons in hidden layers and useful input variables. This algorithm is applied to CAD of lung cancers, and it is shown that this algorithm is useful for the CAD, and is very easy to apply to practical complex problems because optimum neural network architecture is automatically organized.
  PubDate: 2013-04-02
A detection method for intronic snoRNA genes using extended-weight-updating SOM with appearance probability of bases
- Abstract: Abstract Small nucleolar RNAs (snoRNAs) are known that they will participate with RNA modification. However, detail functions of snoRNAs have not been clear still yet. In order to make clear functions of snoRNA, finding more snoRNAs and studying their works in cells are required. In this paper, we propose a method to detect snoRNA genes using extended-weight-updating self-organizing map (eSOM). An input vector to eSOM consists of a feature vector and a target vector. Different from a conventional SOM, a winner node for an input vector is decided by the feature vector only, and all the weights around the winner node are updated to be close to the input vector. We employ bases appearance probabilities and complementary base pair ratio for a feature vector. A target vector is a flag which is 1.0 or 0.0 for a positive or a negative sample, respectively. Experimental results showed our method achieved 91 and 93 % detection ratio for boxC/D and boxH/ACA type snoRNA genes, respectively.
  PubDate: 2013-02-01
A proposal of experimental education system of mechatronics
- Abstract: Abstract Recently, many studies on educational system are being conducted. In this manuscript, a unique education system is proposed for mechanical engineers to be able to efficiently learn basic mechatronics techniques. The system is composed of three subsystems. The first subsystem is used to learn input/output port operations, periodically LED lights ON/OFF and a stepping motor control. The second subsystem is effective to learn AD transformation for several sensor information, DA transformation for DC motor control and a PID control method. Further, the third subsystem is multiple mobile robots system to learn the subsumption architecture for schooling behavior. The effectiveness of the proposed systems was confirmed through experimental instructions in Tokyo University of Science, Yamaguchi.
  PubDate: 2013-02-01
A high-sensitivity 3D shape measurement method using a microscope
- Abstract: Abstract Optical microscopes generally have magnifications ranging from several tens to several thousands and they are often used to observe micro-specimens. Three-dimensional (3D) shape measurements of specimen surfaces are used in a wide range of fields including medicine, pharmacy, life science, and materials science. Conventional methods invariably employ 3D measurement techniques that involve adjusting the focal length of a microscope, which requires a complex automatic adjustment mechanism. Furthermore, since the depth is determined by controlling the focal length, 3D measurements have a low sensitivity. To realize a 3D measurement system with a simple configuration and a high measurement accuracy, we propose a high-sensitivity 3D shape measurement method that employs a microscope and is based on a pattern projection technique. The measurement system consists simply of a conventional optical microscope, a line laser, and a computer. The 3D measurement method employs slit pattern projection. A slit pattern produced by the line laser beam is projected onto the target surface and a reflected image is obtained using a camera installed on the microscope. 3D shape information of the target is obtained using image processing based on the triangulation method. We obtain 3D shape information of the target surface by scanning the slit projection pattern across most of the target surfaces by translating the stage on which the specimen is mounted. The experimental results demonstrate the effectiveness of the proposed method.
  PubDate: 2013-02-01
Synaptic redistribution and variability of signal release probability of Hebbian neurons at low-firing frequencies in a dynamic stochastic neural network
- Abstract: Abstract This paper presents the finding of the research we conducted to evaluate the variability of signal release probability at Hebb’s presynaptic neuron under different firing frequencies in a dynamic stochastic neural network. A modeled neuron consisted of thousands of artificial units, called ‘transmitters’ or ‘receptors’ which formed dynamic stochastic synaptic connections between neurons. These artificial units were two-state stochastic computational units that updated their states according to the signal arriving time and their local excitation. An experiment was conducted with three stages by updating the firing frequency of Hebbian neuron at each stage. According to our results, synaptic redistribution has improved the signal transmission for the first few signals in the signal train by continuously increasing and decreasing the number of postsynaptic ‘active-receptors’ and presynaptic ‘active-transmitters’ within a short time period. In long-run, at low-firing frequency, it has increased the steady state efficacy of the synaptic connection between the Hebbian presynaptic and the postsynaptic neuron in terms of the signal release probability of ‘active-transmitters’ in the presynaptic neuron as observed in biology. This ‘low-firing’ frequency of the presynaptic neuron has been identified by the network by comparing it with the ongoing frequency oscillation of the network.
  PubDate: 2013-02-01
Hash-based early recognition of gesture patterns
- Abstract: Abstract In these days, “early recognition” of gesture patterns has been studied by many researchers. Early recognition is a method to make a decision of gesture recognition at the beginning part of it. In traditional method, the key postures for a gesture are utilized for recognition and early recognition is performed frame-by-frame. However, this method has a problem that computational time in recognition processing increases in proportion to size of posture database. If the processing time becomes longer, some input frames will be ignored from the processing. It results in lower recognition accuracy. In this paper, we introduce a hash-based approach to search the posture database. It realizes real-time processing, and keep high performance of recognition.
  PubDate: 2013-02-01
Stochastic analysis of OneMax problem using Markov chain
- Abstract: Abstract Experimental and analytical investigations are performed for OneMax problem using Wright–Fisher model. This study investigates the distribution of the first order schema frequency in the evolution process of Genetic Algorithm (GA). Effects of mutation in GA are analyzed for the standard mutation and asymmetric mutation models. If a population is in linkage equilibrium, it can be shown that OneMax problem is equivalent to the asymmetric mutation model. Thus, we can apply theoretical results obtained in the asymmetric mutation model to OneMax problem and investigate the convergence time of GA calculation within the framework of Wright–Fisher model.
  PubDate: 2013-02-01
A discontinuous exponential stabilization law for an underactuated X4-AUV
- Abstract: Abstract In this paper, stabilization of a class of second-order nonholonomic systems for an underactuated X4-AUV is investigated. We present a model of the underactuated X4-AUV with six degrees of freedom (DOF) and four control inputs. Then, the system is written in a control-affine form by applying a partial linearization technique, and a dynamic controller based on Astolfi’s discontinuous control is derived to stabilize all states of the system to the desired equilibrium point exponentially. The present approach does not necessitate the conversion of the system model into a “chained form”, and thus does not rely on any special transformation techniques to obtain a canonical form. A simulation is conducted to demonstrate the effectiveness of the proposed controller.
  PubDate: 2013-02-01
Robust facial expression recognition of a speaker using thermal image processing and updating of fundamental training data
- Abstract: Abstract We previously developed a method for the facial expression recognition of a speaker. For facial expression recognition, we selected three static images at the timing positions of just before speaking and while speaking the phonemes of the first and last vowels. Then, only the static image of the front-view face was used for facial expression recognition. However, frequent updates of the training data were time-consuming. To reduce the time for updates, we found that the classifications of “neutral”, “happy”, and “others” were efficient and accurate for facial expression recognition. Using the proposed method with updated training data of “happy” and “neutral” after an interval such as approximately three and a half years, the facial expressions of two subjects were discriminable with 87.0 % accuracy for the facial expressions of “happy”, “neutral”, and “others” when exhibiting the intentional facial expressions of “angry”, “happy”, “neutral”, “sad”, and “surprised”.
  PubDate: 2013-02-01
Evaluation of some user interfaces for elderly persons
- Abstract: Abstract We have already proposed a new concept of “universal multimedia access” intended to narrow the digital divide by providing appropriate multimedia expressions according to users’ (mental and physical) abilities, computer facilities, and network environments. Previous work has evaluated some types of multimedia user interfaces only for younger persons who can utilize keyword search functions. In this paper, we describe several multimedia contents particularly for elderly persons’ aid and evaluate them based on a questionnaire survey.
  PubDate: 2013-02-01
Two-dimensional merging path generation using model predictive control
- Abstract: Abstract A merging path generation method for automated vehicle merging is proposed. This method can make the relevant vehicles cooperate with each other with constraint accelerations, keep the vehicles in their lanes and generate collision free merging path. The merging problem is considered in the two-dimensional space. We set up the mathematic model of the system, formulate the two-dimensional merging problem as an optimization problem and solve it by model predictive control (MPC). To compare the simulation results with the practice, three typical cases were researched. In order to be more practical, the initial conditions of the cases were set according to the data obtained through analyzing the helicopter-shot video. The results represent that the MPC-controlled merging maneuver carried out safely and smoothly, and the relative positions after merging is also the same with the practical results in all the three representative conditions considered. The absolute values of the accelerations of the vehicles are all kept below a practical value 3 m/s2. The importance of cooperation in merging maneuver can also be noticed in the simulation results. By letting the relevant vehicles cooperate, this control algorithm would generate collision free merging path even in the very severe condition. The computational time for the three cases is also short enough for the method to be implemented in actual situation.
  PubDate: 2013-02-01
Study on mobile mechanism of a climbing robot for stair cleaning: a translational locomotion mechanism and turning motion
- Abstract: Abstract In human living environments, it is often the case that the cleaning area is three-dimensional space such as a high-rise building. An autonomous cleaning robot is proposed so as to move on all floors including stairs in a building. When a robot cleans in three-dimensional space, it needs to turn for direction in addition to climb down stairs. The proposed robot selects movement using legs or wheels depending on stairs or flat surfaces. In this paper, a mobile mechanism and a control method are described for translational locomotion. The translational mechanism is based on using two-wheel-drive type omni-directional mobile mechanism. To recognize a stair using the position-sensitive detector, the robot shifts from translational locomotion to climbing down motion or edge-following motion. It is shown that the proposed robot turns to face a stair with the accuracy of 5°.
  PubDate: 2013-02-01
Speech-based formation control of the multi-robot system
- Abstract: Abstract The article presents multiple pattern formation control of the multi-robot system using A* searching algorithm, and avoids the collision points moving on the motion platform. We use speech recognition algorithm to decide the various pattern formations, and program mobile robots to present the movement scenario on the grid-based motion platform. We have been developed some pattern formations to be applied in game applications, such as long snake pattern formation, phalanx pattern formation, crane wing pattern formation, sword pattern formation, cone pattern formation and so on. The mobile robot contains a controller module, three IR sensor modules, a voice module, a wireless RF module, a compass module, and two DC servomotors. The controller of the mobile robot can acquire the detection signals from reflect IR sensor modules and the compass module, and decide the cross points of the aisle. The mobile robot receives the command from the supervised computer, and transmits the status of environment to the supervised computer via wireless RF interface. We develop the user interface of the multi-robot system to program motion paths for various pattern formation exchanges using the minimum displacement. Users can use speech to control the multiple mobile robots to execut pattern formation exchange. In the experimental results, users can speak the pattern formation. The speech recognition system receives the signal to decide the pattern formation. The multiple mobile robots can receive the pattern formation command from the supervised computer, and arrange the assigned pattern formation on the motion platform, and avoid other mobile robots.
  PubDate: 2013-02-01
System development of an artificial assistant suit
- Abstract: Abstract The artificial assistant suit is one which can be put on the human upper body and help human’s two arms act. It is actuated by the Mckibben pneumatic artificial muscle (simply call it as the Mckibben muscle). The whole system is introduced including both the artificial assistant suit itself and the support subsystem. The configuration of the Mckibben muscles is analyzed. The measurement and control system is discussed. The characteristics of the electropneumatic valve are analyzed. The detection method of the action intention of the human arms by SEMG signals is discussed too.
  PubDate: 2013-02-01
Erratum to: Hyper-gourd theory: solving simultaneously the mysteries in particle physics, biology, oncology, neurology, economics, and cosmology
- PubDate: 2013-02-01
Tele-immersive environment with tiled display wall for intuitive remote collaborative work
- Abstract: Abstract In remote collaborative work via WAN, sharing and recognizing various high-quality visual contents such as photography, visualization image, and real video streaming is extremely important. Supporting a high-quality display of these contents on a large-scale display system is necessary to support intellectual remote collaborative work. However, these contents are currently magnified in low resolution on a general projector used as large-sized display equipment, and these equipments are difficult to display the contents with sufficient quality. In this paper, we have focused on the tiled display wall technology which configure a wide-area screen with two or more LCD and tried to display realistic high-resolution visual contents to solve these issues. We have constructed a tele-immersive environment with a tiled display wall, and have studied the availability for intuitive remote collaborative work by implementing various collaborative applications for the effective display of high-resolution contents as well as developing interaction techniques for enormous visual contents in this environment. As a result, we have showed that the practical use of a tiled display wall is useful in the construction of intellectual remote collaborative environment.
  PubDate: 2013-02-01
A control method to suppress the rotational oscillation of a magnetic levitating system
- Abstract: Abstract A magnetic levitation technique has a potential to realize a non-contact object manipulation. As a result, it is expected that a lot of problems caused by contacts can be evaded. Then, the authors developed a magnetic levitation system that was able to manipulate a magnetically levitated hand by non-contact. In this system, four electromagnets are assigned on a horizontal plane for 3-D positioning of the hand. However, it had been examined only about the movement of three directions so far. In this study, a new controller was presented which was developed to suppress the rotation around z-axis, and its effectiveness was conformed through magnetic levitating experiments.
  PubDate: 2013-02-01
Microscopic image restoration based on tensor factorization of rotated patches
- Abstract: Abstract In microscopic image processing for analyzing biological objects, structural characters of objects such as symmetry and orientation can be used as a prior knowledge to improve the results. In this study, we incorporated filamentous local structures of neurons into a statistical model of image patches and then devised an image processing method based on tensor factorization with image patch rotation. Tensor factorization enabled us to incorporate correlation structure between neighboring pixels, and patch rotation helped us obtain image bases that well reproduce filamentous structures of neurons. We applied the proposed model to a microscopic image and found significant improvement in image restoration performance over existing methods, even with smaller number of bases.
  PubDate: 2013-02-01
Study on evolution of the artificial flying creature controlled by neuro-evolution
- Abstract: Abstract The objective of this study is to realize efficient learning for the high generalization ability of evolutionary artificial neural network (EANN). In order to achieve this objective, the evolutionary process of behavior acquisition is analyzed, and then an efficient evaluation function is led by the analysis. An artificial flying creature (AFC) is controlled to fly towards a given target point by EANN. The three-dimensional motion of the AFC is calculated by the physical engine PhysX and a numerical expression of the simple drag force. To evolve ANNs and to have the AFC flight suitably for given target points, particle swarm optimization optimizes parameters of ANNs. The results of evolutionary simulation show that generalization ability of ANNs does not always increase as evolution progresses, and it depends on given tasks of the AFC. It is also shown that diversity of input signals about target points, which the AFC goes through in flight, has positive correlation with generalization ability.
  PubDate: 2013-02-01