This paper presents a knowledge model of everyday objects for semantic grasp. This model is intended for extracting the grasp areas of everyday objects and approach directions for grasping when the 3D point cloud data and the intended purpose are given. Parts that make up everyday objects have functions related to their manipulation. We therefore represent everyday objects in terms of connected parts of functional units. This knowledge model describes the structure of everyday objects and information on their manipulation. The structure of an everyday object describes component parts of the object in terms of simple shape primitives to provide geometrical information and describes connections between parts with kinematic attributes. The information on the structure is used to map the manipulation knowledge onto the 3D point cloud data. The manipulation knowledge of the object includes the grasp areas and approach directions for the intended purpose. Fine grasps suitable for the intended task can be generated by performing a grasp planning with consideration for stable grasp and the kinematics of the robot in the grasp areas and approach directions.

This paper proposes a method for bin-picking for objects without assuming the precise geometrical model of objects. We consider the case where the shape of objects are not uniform but are similarly approximated by cylinders. By using the point cloud of a single object, we extract the probabilistic properties with respect to the difference between an object and a cylinder and consider applying the probabilistic properties to the pick-and-place motion planner of an object stacked on a table. By using the probabilistic properties, we can also realize the contact state where a finger maintain contact with the target object while avoiding contact with other objects. We further consider approximating the region occupied by fingers by a rectangular parallelepiped. The pick-and-place motion is planned by using a set of regions in combination with the probabilistic properties. Finally, the effectiveness of the proposed method is confirmed by some numerical examples and experimental result.

Dexterous manipulation is an important function for working robots. Manipulator tasks such as grasping, assembly and disassembly can generally be divided into several motion primitives. We call such motion primitives “skills” and explain how most manipulator tasks can be composed of sequences of these skills. We will address the issues involved with various types of robots such as maintenance robots and service robots. We have considered hierarchizing the manipulation tasks of these robots since their tasks have become more complex than ever before. Additionally, as errors are seen likely to increase in complex tasks, it is important to implement effective error recovery technology. This paper presents our proposal for a new type of error recovery that uses the concepts of task stratification and error classification which can be expressed specifically using flow charts.

In Japanese Digital Terrestrial Television Broadcasting (DTTB), the identification of multi-path is important to improve its reception characteristics. In order to enhance the resolution of the delay profile, it is effective that continuous multiple channel transfer functions are connected and the frequency bandwidth is extended. However, the guard band is existing between each channel and the transfer function is not obtained directly. The phases of each channel are not synchronized because the each channel is broadcasting independently. In this paper, the scheme to connect multiple channel transfer functions is proposed. In the proposed scheme, interpolation of guard band by using the linear prediction filter based on the RLS(Recursive Least Square) algorithm and compensation of phase between adjacent channels are performed. As the result, it was conformed that resolution enhancement of the delay profile is possible. It is possible to improve the time resolution of the delay profile that has 0.024[μs].

Wikipedia is an Internet encyclopedia where any user can edit articles. Because editors act on their own judgments, editors' biases are reflected in edit actions. When editors' biases are reflected in articles, the articles should have low credibility. However, it is difficult for users to judge which parts in articles have biases. In this paper, we propose a method of clustering editors by editors' biases for the purpose that we distinguish texts' biases by using editors' biases and aid users to judge the credibility of each description. If each text is distinguished such as by colors, users can utilize it for the judgments of the text credibility. Our system makes use of the relationships between editors: agreement and disagreement. We assume that editors leave texts written by editors that they agree with, and delete texts written by editors that they disagree with. In addition, we can consider that editors who agree with each other have similar biases, and editors who disagree with each other have different biases. Hence, the relationships between editors enable to classify editors by biases. In experimental evaluation, we verify that our proposed method is useful in clustering editors by biases. Additionally, we validate that considering the dependency between editors improves the clustering performance.

This paper proposes a method for planning the pick-and-place motion of an object by dual-arm manipulators. Our planner is composed of the offline and the online phases. The offline phase generates a set of regions on the object and the environment surfaces and calculates several parameters needed in the online phase. In the online phase, the planner selects a grasping pose of the robot and a putting posture of the object by searching for the regions calculated in the offline phase. By using the proposed method, we can also plan the trajectory of the robot, and the regrasping strategy of the dual-arm. Here, the putting posture of the object can be planned by considering stability of the object placed on the environment. The effectiveness of the proposed method is confirmed by simulation and experimental results by using the dual-arm robot NX-HIRO.

In this paper, we propose a new visual communication system where eye contact is possible by using a virtual image. The virtual image is obtained by view synthesis with stereo matching from two real camera views. We developed a region based dynamic programming (DP) approach with improved matching cost, occlusion cost and vertical smoothness constraint. We also proposed a fast view interpolation method. To achieve real time performance, we developed a hardware system. Furthermore, to avoid the reordering problem in the foreground region, a view change approach with disorder detection is adopted. Experimental results demonstrate the validity of our improved DP matching algorithm and eye-contact visual communication system.

In this paper, an approach to detection of caption text invideo frames is described. Text recognition in video can beapplied to various applications, however there are stillproblematic issues such as insufficient resolution,complexity of layouts and backgrounds. This study attemptsto solve these problems with a segmentation-free approach,called MAP matching method. Besides extending the methodto grayscale images, a strategy for character size variationusing Gaussian filtering and multi-sized reference patternsis discussed, as well as a method for detecting framescontaining caption text. Results show the proposed matchingmethod is able to detect characters of unknown size incaption text. Although over-detection is not negligible,verifying the positions of detected characters can identifythe location of keywords with practical precision. It is alsoshown that the frames containing caption text are detectedwith nearly 98% accuracy.

Manipulator tasks such as assembly and disassembly can generally be divided into several motion primitives. We call these "skills" and explain how most manipulator tasks can be composed of skill sequences. Skills are also used to compensate for errors both in the geometric model and in manipulator motions. There are dispensable data in the shapes, positions and orientations of objects when achieving skill motions in a task Therefore, we can derive simplified geometric models by considering both dispensable and indispensable data in a skill motion. We call such robust and simplified models "false models." This paper describes our definition of false models in planning and visual sensing and shows the effectiveness of our method using examples.

In this paper, we will introduce some variations of tree adjoining grammars which generate the sets of quadtrees as their languages and investigate their effectiveness to describe the sets of digital images. In those variations, two types of parallel operations, multicomponent and multifoot adjoining, will be introduced. Both of them are quite different parallelisms from ordinary ones (such as Indian parallelism of grammars, or L-systems).

We found suitable direction-change features of the imaginary strokes in the pen-up state for online handwritten cursive character recognition. Our method simultaneously uses both directional features, otherwise known as off-line features, and direction-change features, which we designed as on-line features. Direction-change features express both written strokes in the pen-down state and unwritten imaginary strokes in the pen-up state. It is important to get suitable direction-change features when using this method. We tried to examine the influence on character recognition rates when changing the functions used to get each direction-change feature based on the imaginary stroke lengths. Then, we found that the best function is the function which puts no weight on the imaginary stroke lengths. The recognition rate for freely-written Japanese characters was improved from 82.37% to 86.32% by our new method using the best function as opposed to our old method using a function which gets each direction change feature in inverse proportion to the imaginary stroke lengths.

We propose a new method for extracting character strings which have various directions and sizes. In our method, we regard a character string as a rectangular region crowded with short segments. Then two kinds of the segment crowdedness (local segment crowdedness and global segment crowdedness) are introduced to extract the rectangular regions (i.e. strings). The method was applied to many images which involve strings in various directions and sizes. The result shows that almost all strings were correctly extracted.

Generally, a manipulator task can be divided into several motion primitives called "skills". Skill-based motion planning is an effective way to execute a complicated task. Also when planning tasks, a technique of fine motion planning such as the backprojection method in configuration space is often used. In this paper we introduce the concept of skill into the backprojection method. A backprojection is shaped by a pattern of motion on each skill primitive, and a skill library is constructed. Motion planning based on backprojection is achieved by combining several skills in the skill library. Therefore, a general and skilful motion planning can be derived.

In robot motion planning, geometric modeling plays an important role. Generally the shapes of objects such as factory products can be stored in a computer software database, so the elements that need to be decided are positions and orientations. In this paper surface-based geometric modeling using a task-oriented teaching tree is proposed. In this modeling, combinations of surfaces for deciding positions and orientations of objects are represented in a depth-first tree based on a kind of task. Therefore, the operator can choose easily one combination out of several compared with the obtained data. Moreover a geometric model of the object suited to the manipulation task can be obtained.

The paper proposes a system for recognizing numeric strings from topographical maps, which is composed of an automatic recognition stage and an interactive recognition stage. In this method, uncertain numeric strings extracted through the automatic recognition stage based on topographical map features only are confirmed and corrected by the interactive recognition stage. Therefore one can obtain highly precise recognition results. The method was applied to numeric string recognition from a map image which includes 102 strings made up of 249 numerals. As a result, 95.1% of 102 numeric strings were correctly recognized.

The paper proposes a method for extracting slant characters from complicated background figures efficiently and rapidly. In this method, slant character candidates are extracted using the black pixel density features, that is, matching rate of two different sized circular templates, which are inscribing and circumscribing a target character, with an original image. In order to estimate performance of the proposed method, the method was applied to 41 topographic map images (512/spl times/512 pixels) involving 1032 slant characters. As a result, the average number of character candidates per character was reduced to about 41 candidates, and 94.3% of 1032 slant characters were extracted correctly.

Geometric modeling of the environment is important in robot motion planning. Generally, shapes can be stored in a database, so the elements that need to be decided are positions and orientations. In this paper surface-based geometric modeling using a teaching tree is proposed. In this modeling method, combinations of surfaces are considered in order to decide the positions and orientations of the object. The combinations are represented by a depth-first tree, which makes it easy for the operator to select one combination out of several. This method is effective not only in the case when perfect data can be obtained but also when conditions for measurement of three-dimensional data are unfavorable which often is the case in the environment of a working robot.

In a coordinate grammar, the rewriting rules replace sets of symbols having given coordinates by sets of symbols whose coordinates are given functions of the coordinates of the original symbols. Usually, at each step of a derivation, only one rule is applied and only one instance of its left hand side is rewritten. This type is referred to sequential grammars. As a counterpart of this grammar, parallel coordinate grammars are defined as generalized parallel isometric grammars. In the parallel grammars, the rewriting rule are used in parallel in a derivation application. The paper discusses some properties of parallel coordinate grammars and examines a relationship between the sequential coordinate grammars and parallel ones.

The paper presents a new hearing aid system intended to compensate the degradation of perceptual functions in the central auditory pathways which can be found typically with elderly people, while conventional hearing aid systems are effective only for conductive hearing impairments. A typical type of such functional deterioration is the decrease of rate of processing speed for identification of speech and effective cognitive capacity. The new system is designed to compensate it by slowing the input speech rate instead of a direct processing of the related auditory functions. This system enables a user to convert a speech rate as desired by him/her-self on real time, with invariance in pitch as well as small impairments in quality.>

The graph structure is a strong formalism for representing pictures in syntactic pattern recognition. Many models for graph grammars have been proposed as a kind of hyper-dimensional generating systems, whereas the use of such grammars for pattern recognition is relatively infrequent. One of the reasons is the difficulty of building a syntax analyzer for such graph grammars. In this paper, we define a subclass of nPCE graph grammars and present a parsing algorithm of O(n) for both sequential and parallel cases.

It is difficult to recognize character strings from maps, which involve various figures. The authors describe a method for recognizing character strings from these topographical maps. The method consists of a bottom-up process and a top-down process. First, in the bottom-up process, character candidates are extracted from a map. Second, in the top-down process, these character candidates are grouped into strings using linguistic knowledge of strings. Through the top-down process, character strings are recognized correctly and efficiently from low precise character candidates extracted through the bottom-up process. The method was applied to 13 maps (512/spl times/512 pixels) involving 98 strings. As a result, 95% of 98 strings were extracted correctly.>

In this paper, we will define array grammars on the hexagonal grid. One of the advantages obtained from using the hexagonal grid is that each point has only one kind of neighbor. It is shown that the class of the context-free array grammars on the hexagonal grid includes the class of the rectangular ones even if their languages are restricted to the pictures connected on the rectangular grid. It is also shown that, in the monotonic case, they own the same class of languages jointly.

We define a graph grammar called node-replacement graph grammar with path controlled embedding (nPCE grammars) which use a sequence of edges instead of the single edge to embed a newly replaced graph into the host graph, then show some relationships between two-dimensional "coordinate grammars" and nPCE grammars. We also suggest an extension of PCE grammars to describe "disconnected coordinate languages".

This paper presents a technique for data compression of a grey-level still image. The image is considered to be a two-dimensional homogeneous random field that satisfies a noncausal stochastic difference equation driven by a white noise field. The difference equation model is isotropic and characterized by the two parameters of the variance and the correlation length of an image only. This model is simple and can easily fit various types of images. Based on the above model, we develop a hybrid algorithm which combines a one-dimensional cosine transformation and a one-dimensional prediction. The algorithm is applied to a real image to check its validity.

This correspondence proposes one-pass algorithms that compute the numbers of objects, cavities, and holes in three-dimensional (3-D) digital pictures. Also, it is shown that a one-way, 3-D parallel/sequential acceptor cannot accept the class of 3-D binary arrays in which the set of 1's is connected, unlike the situation in the two-dimensional (2-D) case; but it can do so if multipasses are allowed.

It is proved that the emptiness problem for deterministic bottom-up triangle acceptors (BTA's) over a single input symbol is recursively unsolvable. From this result, it is also shown that certain decision problems involving BTA's and BPA's (deterministic bottom-up pyramid acceptors) are unsolvable.