Journal of the Japanese Society for Artificial Intelligence
Online ISSN : 2435-8614
Print ISSN : 2188-2266
Volume 13, Issue 2
Displaying 1-33 of 33 articles from this issue
Print ISSN:0912-8085 until 2013
  • Ikuo OYAKE
    Article type: Preface
    1998 Volume 13 Issue 2 Pages 163
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (109K)
  • Seiichiro SAKURAI
    Article type: Cover article
    1998 Volume 13 Issue 2 Pages 164
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (105K)
  • Yoshiyuki MATSUMURA, Shozo OTA, Koichi OKAMOTO
    Article type: Special issue
    1998 Volume 13 Issue 2 Pages 165-172
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (883K)
  • Makoto HARAGUCHI
    Article type: Special issue
    1998 Volume 13 Issue 2 Pages 173-180
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (893K)
  • Katsumi NITTA
    Article type: Special issue
    1998 Volume 13 Issue 2 Pages 181-188
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (835K)
  • Takahira YAMAGUCHI, Masaki KUREMATSU
    Article type: Special issue
    1998 Volume 13 Issue 2 Pages 189-196
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (761K)
  • Hideki YAMAMOTO
    Article type: Corner article
    1998 Volume 13 Issue 2 Pages 197-204
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (873K)
  • Toshiyuki TAKEZAWA
    Article type: Cover article
    1998 Volume 13 Issue 2 Pages 205
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (91K)
  • Satoru HAYAMIZU, Toshiyuki TAKEZAWA
    Article type: Special issue
    1998 Volume 13 Issue 2 Pages 206-211
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (677K)
  • Yasuyuki KONO, Takehide YANO, Tomoo IKEDA, Tetsuro CHINO, Kaoru SUZUKI ...
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 212-220
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    Two requirements should be met in order to develop a practical multimodal interface system, i.e., (1) integration of delayed arrival of data, and (2) elimination of ambiguity in recognition results of each modality. This paper presents an efficient and generic methodology for interpretation of multimodal input to satisfy these requirements. It is able to integrate delayed-arrival data well, and is able to efficiently interpret multimodal input that contains ambiguity by regarding the multimodal interpretation process as hypothetical reasoning and formalizing the control mechanism of interpretation on the basis of the ATMS (Assumption-based Truth Maintenance System). The proposed method is incorporated into an interface agent system that accepts multimodal input consisting of voice and direct indication gesture on a touch display. The system communicates to the user through the interface agent's 3D motion image with facial expressions, gesture, and synthesized voice.

    Download PDF (989K)
  • Fumihisa SHIBATA, Masaya ASHIDA, Koh KAKUSHO, Tadahiro KITAHASHI
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 221-230
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    In this article, we discuss mobile robot navigation under linguistic instructions of a route to the goal in an unknown environment, aiming at man-robot communication by a natural language. It is assumed that the instructions given to a robot describe a route based on distinctive landmarks including intersections, for example, "turn right at the 2nd intersection, and ・・・". These linguistic instructions are composed from recognition of landmarks by the instructor using his/her own land-mark models, which give his/her own viewpoint to determine correspondence between each part of a route and landmark symbols available for instructions. In order to specify the route that is implied by the instructor in the environment correctly, the robot needs to have the landmark models identical to those of the instructor. But, as is shown in the previous works of pattern recognition, it is very difficult to define models that realize the same result of pattern recognition as humans, even if we assume only simple landmarks such as intersections in a two dimensional environment as those to be recognized. Instead of seeking such a complete model of each landmark, we propose to infer the route implied by the instructor from the result of landmark recognition based on usual landmark models that are easy to be given to the robot. The key idea is that it is possible to detect misunderstanding about each landmark in the instructions as contextual inconsistency between the instructions and the result of landmark recognition if the instructions are redundant to specify the route uniquely in the environment. We also propose to learn the evaluation of sensory data enough to recognize each landmark correctly from the result of navigation.

    Download PDF (1123K)
  • Daisuke KANJO, Hitoshi OGAWA
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 231-240
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    A multimodal presentation system is proposed, which explains how to operate an electrical device to realize a function of the devices. The explanation should be based on a sequence of operations from an initial state to a desired state. So, NOAH, the hierarchical planner that resolve conflicts between opetators, is used to generate an operator network that describe a process to obtain the desired state of the device. Explanations show each operator or state that compose the network with text and graphics. The operator connects a given state and an obtain state. Problems to translate a operator network to text with graphics are as follows: 1) which should be presented, operator itself, the given state, or the obtained state, 2) which should be presented by text, and 3) which should be presented by graphics. 6 paterns are defined as Describe Action (DA) to generate an expression of elements of the network. DAs are translated from the operator network, then the expression is generated using the suitable modalities. The multimodal presentation system consists of a controller, a planner, an analyzer and a generator. The controller manages an input from user, and makes the desired state. The planner generates an operator network to get the desired state. On the analyzer, the operator network is analyzed and translated to DAs. The generator receives DAs and generates the explanation with text and graphics.

    Download PDF (1025K)
  • Seiichi NAKAGAWA, Akihiro DENDA, Toshihiko ITOH
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 241-251
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    Recent improvements of speech recognition and natural language processing enable dialogue systems to deal with spontaneous speech. With the aim of supporting these systems, multi-modal man-machine interface has been introduced to the system widely. We have been aiming at realization of a robust dialogue system using spontaneous speech as main input modality. Although our conventional system was developed with a robust natural language interpreter, since its user interface was built only on speech, the system did not always give enough usability. However, in this case, response sentences became too long when they contained lots of information. And that may make user miss a part of response speech. Furthermore, user can not get any information on how a particular word in the response, e.g. a name of place, should be represented in Kanji-characters, and it was very difficult to input the position on the map through speech. These examples clearly indicate that the user interface only on speech doesn't always give enough information to the user and may cause some troubles. In order to solve these problems and realize more natural human -machine interaction, we have developed a multi-modal sightseeing guidance system with 1) speech input/output, 2) touch screen input (on map/in menu) and 3) graphical/text output (map, photograph, menu and dialogue history). Furthermore, we implemented an agent interface with real face image / animation and recorded speech / sinthesized speech to the system, and carried out evaluation experiments which consist of task completions and questionnaires to evaluate the interface and whole system. In this paper, we describe the system and the evaluation experiments.

    Download PDF (1181K)
  • Mikiya SAITO, Yoshifumi UKITA, Toshiyasu MATSUSHIMA, Shigeichi HIRASAW ...
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 252-262
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    This study presents how to deal with knowledge when it includes contradiction. We propose the ways to reject contradiction and decide a true interpretation as correct as possible by clearing the cause of contradiction. In this paper, we assume two reasons why contradiction is occurred. For one reason, it occurs due to erroneous information from transmitters which sometimes provide wrong information. Another is circumstances are always changing, the change of true interpretation causes contradiction. We define these models, and decide true interpretation or construct consistent knowledge by calculating transmitters' error rates or interpretation changing rates. Further, we consider this field from our point of view. There are many studies in this field including belief revision, belief update, combining theory and multisource reasoning. These studies can be dividbd into two groups. One is semantics dependent problem, which is mainly based on minimal change principle. The other is syntax dependent problem, which is chiefly based on maximal consistent princible. Either of them does not consider what circumstance they should be applied to, and what they guarantee. In this paper, we can classify and evaluate past various works by our model, and clarify the meanings what they intend.

    Download PDF (1100K)
  • Kazuaki TANAKA, Takashi TOMOOKA, Jiang Yu ZHENG, Norihiro ABE, Shoujie ...
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 263-273
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    The final purpose of the research is to build an AI system which automatically understands assembly procedures from an assembly manual and carries out the assembling of repairing tasks. An assembly manual consists of explanation and illustration. Part names and assembly sequences are obtainable from explanation, and configuration of a part in assembly is depicted in illustration. To combine the particular two parts specified in explanation, the system has to find the portion from illustration in which each part is located. Consequently, a part name is first extracted from illustration, then the figure is found from illustration which corresponds to the 3 dimensional model of the part with the extacted name. Part names are identified using a pattern matching method free from unknown words which allows a variable to be matched to any word sequence. The figure is examined to see if it can be matched to the model by referring to an auxiliary line which helps us understand assembly relation after inferring a line of sight used when the illustration was described. The illustration being drawn by hand, the figure may not be judged to be equal to the model of itself. By considering the fact, the posture of a model is discovered from illustration using a simple but robust matching method. As the result, except for the special cases not satisfying the assumption on parts used, assembly operations will be successfully simulated by moving each part along the auxiliary line using the new illustration in which all parts are replaced with their corresponding models.

    Download PDF (1088K)
  • Kiyoshi AKAMA, Yuichi KAWAGUCHI, Eiichi MIYAMOTO
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 274-282
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    While many conventional theories are based on the logic paradigm, our theory is based on the equivalent transformation (ET) paradigm, where computation is regarded as "equivalent transformation of declarative descriptions." In the ET paradigm, each domain is characterized by a mathematical structure called a "specialization system." The term domain, consisting of usual atoms and substitutions; is also formalized by a specialization system. The ET paradigm makes it possible to utilize not only the usual unfolding rule but also other equivalent transformation rules, which may often make execution more efficient without much additional cost. In this paper we develop a theory of two new equivalent transformation rules for member constraints in the term domain : the candidate elimination rule (CE rule) and the common pattern specialization rule (CPS rule). While the CE rule reduces the length of the candidate list of a member constraint, the CPS rule specializes the clause containing the given member constraint by unifying a common pattern of all the candidates with the first object of the member constraint. Natural language understanding examples show that, when used in preference to unfolding, these rules suppress clause splitting in the course of equivalent transformation, which makes computation more efficient.

    Download PDF (744K)
  • Tomoyuki FUJITA, Hitoshi OGAWA
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 283-291
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    Most of the former planners can generate a valid set of operators under a static condition. But,once operational failure has occured in executing the operators, the only way to recover is the reconstruction of whole operators. So,if the difference between the new plan and the old one is smaller than the whole plan, a modification of the plan must become very efficient way. The system proposed in this paper can rebuild the plan as suitable for changed situation by deletion and assertion of operators considering their effect to the plan. Furthermore, this system can make the range of modification to minimum with hierarchical definition of operators. It consists of four major systems : Non-linear Planner which makes a valid network of operator for given problems, and TMS (Truth Maintenance System) which verifies consistency of the network, Node Creater which translates dependencies among factors of plan into data structure for TMS, and Organizer which manages other three systems and makes decision of a range and a method of modification.

    Download PDF (784K)
  • Yasuyuki NISHIOKA, Shinichi NAKASUKA, Koichi HORI
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 300-311
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    This paper applies a concurrent problem solving (CPS) framework to a practical design of a mechanical pump: CPS is a new concept in which both spatial and temporal structures are dealt with in ill-defined problems. The system named PICCSS is developed on the framework, and used in this research to investigate applicability to a practical design. The objective of this paper is to evaluate the CPS framework by demonstrating an industrial application. The system consists of calculation modules, graphical user-interfaces and knowledge-base. In this system, every kind of knowledge is represented by primitives and their connections. Primitives are ontology which defines the problem domain as basic vocabulary in the system. Therefore, the system has to have domain-specific information of design and manufacturing as primitives in advance. Consequently, this paper, firstt, illustrates primitives of mechanical design knowledge. A product model and a production model can correspond to a spatial structure of primitives and a temporal structure of primitives respectively. Connections between these two structures are established according to templates which represent reusable patterns in the past. Secondly, this paper demonstrates an application of the system to an aired bump design. Using the proposed system, a designer solves his design problem in the computer interactively. The system supports the designer clarifying the problem itself and verifying it in terms of consistency of constraints and causality. After that, the system provides visualized charts such as product drafts and production plans. This paper concludes that the proposed system and the CPS framework are quite appropriate in supporting designers. Furthermore, it can be expected that decrease of a span of product development, elimination of human error in the design, and effective management of design and manufacturing knowledge are achieved.

    Download PDF (1177K)
  • Masaharu YOSHIOKA, Tetsuo TOMIYAMA
    Article type: Technical paper
    1998 Volume 13 Issue 2 Pages 312-319
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS

    In this study, we propose a framework of an integrated modeling environment for design. Since a mechanical engineering design process requires various kinds of design object models, such as a geometric model, a kinematic model, and a finite element model, this environment should maintain consistency among these models. Furthermore, commercial design tools are practically used in design processes, and these must be integrated as well. For dealing with multiple design object models, we have formalized a concept called a metamodel. A metamodel is a model which represents relationships among concepts used in various design object models. This paper proposes a framework of the pluggable metamodel mechanism that allows to plug in existing design tools, to support a modeling on it, and to maintain consistency among them. We describe a prototype system and illustrate an example of ball screw design.

    Download PDF (827K)
  • [in Japanese]
    Article type: Other
    1998 Volume 13 Issue 2 Pages 320-321
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (263K)
  • [in Japanese]
    Article type: Corner article
    1998 Volume 13 Issue 2 Pages 322-323
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (214K)
  • [in Japanese]
    Article type: Corner article
    1998 Volume 13 Issue 2 Pages 324
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (108K)
  • [in Japanese]
    Article type: Corner article
    1998 Volume 13 Issue 2 Pages 325
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (106K)
  • [in Japanese]
    Article type: Corner article
    1998 Volume 13 Issue 2 Pages 326
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (109K)
  • Article type: Activity report
    1998 Volume 13 Issue 2 Pages 327-332
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (490K)
  • Article type: Activity report
    1998 Volume 13 Issue 2 Pages 333
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (96K)
  • Article type: Activity report
    1998 Volume 13 Issue 2 Pages 334
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (98K)
  • Article type: Activity report
    1998 Volume 13 Issue 2 Pages 335
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (137K)
  • Article type: Activity report
    1998 Volume 13 Issue 2 Pages b001-b015
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (1127K)
  • Article type: Cover page
    1998 Volume 13 Issue 2 Pages c002
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (64K)
  • Article type: Cover page
    1998 Volume 13 Issue 2 Pages c002_2
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (82K)
  • Article type: Table of contents
    1998 Volume 13 Issue 2 Pages i002
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (78K)
  • Article type: Table of contents
    1998 Volume 13 Issue 2 Pages i002_2
    Published: March 01, 1998
    Released on J-STAGE: September 29, 2020
    MAGAZINE FREE ACCESS
    Download PDF (86K)
feedback
Top