By Topic

Robot and Human Communication, 1994. RO-MAN '94 Nagoya, Proceedings., 3rd IEEE International Workshop on

Date 18-20 July 1994

Filter Results

Displaying Results 1 - 25 of 67
  • Proceedings of 1994 3rd IEEE International Workshop on Robot and Human Communication

    Publication Year: 1994
    Save to Project icon | Request Permissions | PDF file iconPDF (44 KB)  
    Freely Available from IEEE
  • A two-stage method for selective modeling of unknown teleoperation environments

    Publication Year: 1994 , Page(s): 333 - 338
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (436 KB)  

    A semi-automatic method for the construction of geometric object models in unknown teleoperation environments is proposed. The problem is divided in two parts: detection and designation of the target and target model generation, In the first, interactive phase of the method the operator observes and designates some feature points on at least two different perspective images of the target environment. In the second phase range measurements are automatically generated across the estimated target 3D-sub-volume. Finally, a surface model is reconstructed from the measurement data View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Emotion and social factors in communication

    Publication Year: 1994 , Page(s): 12 - 17
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (380 KB)  

    Various new issues would arise if one wishes to create robots worth having as partners in the human society. Since these robots have to be able to communicate with humans more or less in equal standing, they need to understand human emotional expressions to some degree, as well as to produce some of them as if they owned their own emotions. This is because emotional expressions are indispensable ingredients of human daily communication. In this paper analyses of many issues concerning the role of communication in the human society are attempted in a rather deep level. A special emphasis will be placed upon the versatile structure of the society, created by using competitiveness of its members for the purpose of acquiring more adaptability of the society as a whole against mutable external conditions. It will also be shown that this versatile aspect of the society reflects heavily upon the daily communication we are engaged in View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dempster-Shafer theoretic design of a decision support system for a large-complex system

    Publication Year: 1994 , Page(s): 345 - 350
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (264 KB)  

    This paper discusses the design of a decision support system (DSS) which can process and display uncertainty contained in information regarding operating conditions of the plant. The authors take a probabilistic approach to evaluate effectiveness of a decision support system. Either of the plant state information provided by the DSS and operator's opinion regarding the plant state is represented in terms of a belief structure. These two belief structures are combined into one by the operator. Criteria for determining a control action based on the combined belief structure are given. The authors classify the operator into three types according to his decision criterion. The authors analyze conditions for which the DSS can provide the operator with a support so that the expected loss of the plant may be reduced when a combination rule is given and the operator's knowledge of characteristics of the plant is assumed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-autonomous teleoperation system using virtual tool

    Publication Year: 1994 , Page(s): 327 - 332
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (340 KB)  

    Proposes a semi-autonomous control algorithm for a telemanipulator system based on a task-oriented virtual mechanism. The authors design a task-oriented virtual mechanism, or a task-oriented tool dynamics for a given task and separate its coordinate system into the coordinates in autonomous mode and the coordinates in manually-controlled mode. Then, the authors design a controller for the telemanipulator system so that the system has the dynamics of the task-oriented tool. Thus, the maneuverability of the system is improved by controlling the telemanipulator system so that the system, behaves as a tool. By assuming the passivity of an operator, the total stability of the resultant system is guaranteed for a passive environment with unknown dynamics. The proposed control algorithm is experimentally applied to a telemanipulator system. The experimental results illustrate the validity of the proposed control algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Control of a tripod robot based on reaction forces

    Publication Year: 1994 , Page(s): 368 - 372
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (160 KB)  

    High-speed locomotion of walking robots has been studied. The most considered gaits are trot gait and pace gait. In trot gait, the diagonal legs are operated by turning the support legs. In pace gait, the right or left legs are operated by turning the support legs. High-speed walk is a variable gait. However, an efficient method for high-speed walk does not only consist of a variable gait, it also requires a positive use of reaction forces. A control method of a tripod robot for high-speed walk is presented with simulation experiments based on reaction forces View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mutual entrainment based human-robot communication field-paradigm shift from “human interface” to “communication field”

    Publication Year: 1994 , Page(s): 118 - 123
    Cited by:  Papers (8)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (496 KB)  

    A mutual entrainment based communication field is proposed as a new communication paradigm to realize a human-robot collaboration system. The most interesting ability of this field is to spontaneously generate a control information field for autonomous coordination including both human and robotic dynamics. Applying it to the coordinative walking process between human and robotic system as an example, the authors show that the control information field indicating functional relationship between human and robot is self-organized in the communication field. It is encoded on the spatial phase pattern generated by the mutual entrainment between walking rhythms. Interpreting this information, each subsystem would be able to coordinately behave as one whole system. This result suggests that the essence of communication is not in any definite and separated order as is seen in conventional human interfaces but in the ability to self-organize flexible and integrated order in the communication field View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constructing experimental stimuli for evaluation of 3D faces

    Publication Year: 1994 , Page(s): 180 - 185
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    We report our preliminary experiments for 3D human faces in order to investigate the importance of their structural and textural information concerned with the view angle. A new sensing method was developed for creating highly-accurate 3D images. By this method, we can arbitrarily synthesize new images to compound a person's structural model and other surface textural information of the person's face. We will show the importance of structural and textual information concerned with the view angle and the validity of the compound method, in investigating the trade-off between quality and efficient image generation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of the neural network recognition characteristics of 6 basic facial expressions

    Publication Year: 1994 , Page(s): 222 - 227
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (396 KB)  

    In order to develop an “Active Human Interface” that realizes heart-to-heart communication between intelligent machine and human being, we have been investigating the machine recognition of human emotions from facial expressions. By using a neural network(NN), we obtained a high recognition ratio of about 90% for 6 basic facial expressions, but we find that, depending on the NN learning information, there exist certain characteristics between correct/incorrect recognition ratios. This paper analyses these characteristics by using the action units (AUs) used in the psychological field for describing the basic muscle movement of human face and analyzing the relationship between the NN input and output information. We found, in this paper, how AUs influenced the recognition results by assigning O value to each AU using NN input information View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generating fuzzy rules by genetic algorithms

    Publication Year: 1994 , Page(s): 362 - 367
    Cited by:  Papers (9)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (316 KB)  

    A general method is developed to generate fuzzy rules by using genetic algorithms (GAs) and a fuzzy logic controller (FLC). By using GAs as a learning procedure and a FLC as the system's performance evaluator, the proposed architecture can construct an input-output mapping in the form of fuzzy if-then rules. The performance of the new architecture is compared with an artificial neural networks controller and pure limited-rule fuzzy rule controller for the truck back-upper problem View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of virtual shape using visual and tactual sense under optical illusion

    Publication Year: 1994 , Page(s): 294 - 298
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB)  

    In addition to visual display, tactual-feedback system will play an important role in interactive computer interface design. Though the human visual system is generally more sensitive than the tactual one, the visual system is more subject to optical illusions. In this study, we have conducted experiments to obtain visual and/or haptical sensitivity of recognition of virtual figure features, such as the deformation of a circle and the bending of a line, under optical illusion. It was found that the figure which the subject judges to be a true circle or a straight line is closer to the true figure, when he/she used haptic exploration than by visual alone. However, the probable error by haptics is larger than that by vision alone. Therefore, if multi-modal sensation are used in the graphical interface, it is important to consider such phenomena. Because the total recognition quality may become worse in multimodal sensation than in either single one under optical illusion View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object grasping in virtual environment using dynamic force simulator

    Publication Year: 1994 , Page(s): 261 - 264
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (328 KB)  

    Realizes force feedback with the dynamic force simulator (DFS) that the authors proposed previously. DFS simulates object dynamics, contact model and friction characteristics of human hand interacting object in virtual reality. After derivation of kinematic and force relations between hand and object space the authors realize desired feedback forces to human operator. Interaction with DFS allows the calculation and feedback of appropriate forces to the force controlled actuators of the sensor glove the authors have developed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An autonomous eye robot for tele-watching

    Publication Year: 1994 , Page(s): 323 - 326
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (320 KB)  

    This paper proposes an autonomous eye robot which autonomously acquires appropriate visual informations of an indicated target. By using this robot, the watcher can have appropriate images of the target without adjusting the camera position. The authors show the hardware structure and the basic motion strategy of the robot View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cooperative motion control of a robot and a human

    Publication Year: 1994 , Page(s): 112 - 117
    Cited by:  Papers (33)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (284 KB)  

    Robots are expected to be human-friendly and to execute tasks cooperating with humans. The control system for the robots should be constructed so as to work adaptively with human characteristics. In this paper, human characteristics in a cooperation task by two humans is analyzed and it is shown that the human performance can be expressed by impedance control. We then applied the principle in making a robot and a human to execute a cooperative task. It is shown that the impedance parameters obtained in the experiment performed by two humans gave the best result for robot's cooperation with human View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Micro-macro manipulator with haptic interface-2nd report: control by using virtual model

    Publication Year: 1994 , Page(s): 130 - 133
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (356 KB)  

    This paper treats a basic system which realizes a scaled manipulation environment. Tools for scaled manipulation are necessary when one manipulates an extremely large or small size target. In the case of manipulation without scaling, it is possible to let the slave-manipulators have the same configuration as the master-manipulators. But in the case of different scale, it is difficult to design these manipulators with the same configuration. Thus different configurations with some intelligent control is necessary for such master-slave manipulators. In this paper the authors propose a control method for different scale master-slave manipulator View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A basic study on dynamic control of facial expressions for Face Robot

    Publication Year: 1994 , Page(s): 168 - 173
    Cited by:  Papers (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    In order to develop an active human interface that realizes heart-to-heart communication between intelligent machine and human being, we've been undertaking the investigation of method for improving the sensibility or KANSEI communication between them. We've already reported the “Face Robot” that has a human-like face and can display facial expressions by using the flexible microactuator driven by air pressure. In this paper, we investigate the method of dynamic control of facial characteristic point movement for expressing time-changing facial expressions on Face Robot. From the facial expressions expressed by human being dynamically, we obtain the timewise movement of facial characteristic points which sequentially change from neutral to one of basic facial expressions. Using these experimental results, we investigate the time-dependent displacement of characteristic points of Face Robot in relation to the electric-valve closing time, and obtain the appropriate electric-valve closing time for each actuator. According to this control method of electric-valve closing time, the dynamic facial expressions expressed by Face Robot can be controlled in a similar way as in human being View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reasoning about the transition between facial expressions

    Publication Year: 1994 , Page(s): 186 - 191
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (468 KB)  

    Building on earlier work on fuzzy modeling of facial expressions we consider the problem of reasoning about the transition between two facial expressions. To deal with this problem we propose a hybrid reasoning scheme combining generalized modus tollens and fuzzy backward reasoning. The approach is illustrated by an example, and we conclude with a discussion about possible applications to an intelligent human-computer interface using the transition model View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spatial characteristics of visual attention reflected in illusory conjunctions

    Publication Year: 1994 , Page(s): 151 - 155
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (336 KB)  

    In order to examine the shape of the spotlight of attention, dependence of illusory conjunctions on the stimulus configuration is investigated, based on the model that illusory conjunctions occur only if different stimuli exist simultaneously in the spotlight of attention. It was found, by experiment, that when the stimulus items were arranged along a line radiating from the fixation point, illusory conjunctions occur very frequently; when the items were arranged along a line perpendicular to the radiating line, illusory conjunctions occur less frequently. Based on the model of the static spotlight of attention, the obtained results indicate that the shape of the spotlight extends along the radiating line. Another explanation is that the attentional spotlight scans each item rapidly and the spotlight is ready to shift along the radiating line. The fact that features were incorrectly combined with a specific tendency can be explained more easily by the latter model View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of neural networks to virtual reality

    Publication Year: 1994 , Page(s): 26 - 30
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB)  

    Neural networks and virtual reality technology have a potentially strong linkage because of the need for adaptation driven by the complexity of inter human variability. This short paper describes two applications to illustrate this point. The first uses artificial neural networks to generate facial animation models for use in virtual reality telecommuting systems. The second uses virtual environments to view, manipulate, model, analyze, and move through complex data sets of insect brain tissue, as though actually in the experimental domain, to decode the interconnections of the circuitry View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An interactive voxel data manipulation system for surgical simulation

    Publication Year: 1994 , Page(s): 204 - 209
    Cited by:  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (416 KB)  

    In this paper, we describe an interactive surgical simulation system by voxel manipulation in a virtual space. In this system, we can manipulate a 3D image on a computer screen as if we treated a 3D object in real world. In order to treat a 3D image provided as a 3D array with high level interaction and real time operation, we developed techniques such as fast representation of surface figure with polygons, a new data structure for 3D image description, interactive processing with mouse and real-time result evaluation method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Advanced human integrated assembly system

    Publication Year: 1994 , Page(s): 311 - 316
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (516 KB)  

    The concept of flexible production has been around for several years now. But why are there so few really flexible production systems around? The problem is that flexibility has usually been seen either as a technical or as a human factors issue. It is neither, but both. This paper discusses some questions related to reducing the time, risk and complexity of flexible production line design and cutting product lead time to market by providing on-the-job information support on the shop floor View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A method of correcting provisional boundaries of “bunsetsu”

    Publication Year: 1994 , Page(s): 289 - 293
    Cited by:  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (340 KB)  

    In order to solve the problem that the amount of computer memories required for translating the non-segmented “kana” sentences into the “kanji-kana” sentences grows rapidly in proportion to the increasing of the length of the sentence, a new method of finding provisional boundaries of “bunsetsu” using 2nd-order Markov chain probability has been developed. This paper proposes a method to correct the provisional boundaries of “bunsetsu” for non-segmented “kana” sentences, by looking up all the word candidates in the dictionary. The improvements of “relevance factor” P and “recall factor” R for provisional boundaries of “bunsetsu” determined and corrected by these methods were evaluated by experiment using the statistical data for 70 issues of a daily Japanese newspaper View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A virtual environment display with constraint feeling based on position/force control switching

    Publication Year: 1994 , Page(s): 255 - 260
    Cited by:  Papers (7)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (400 KB)  

    This paper presents a technique for the design of force-reflecting systems which simulate realistic virtual environments. In tasks that involve interactions with the environment, such as assembling blocks and inserting pegs in holes, there are many sliding motions along intervening edges and faces. To perform these tasks, force sensation is the most important information to recognize the interactions between the objects. The authors previously proposed a system that realizes constraints due to the environment by modeling the interaction forces. However, the modeling of the complex contact forces required a servo loop that took a long time to execute. In this paper, the authors introduce a virtual environment display system which uses a switching position/force control mode. The improved performance of this new system presents a more realistic simulation to the operator. Finally the authors report some experimental results which confirm the validity of the proposed method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A speech dialogue management system for human interface employing visual anthropomorphous agent

    Publication Year: 1994 , Page(s): 277 - 282
    Cited by:  Papers (5)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (460 KB)  

    A visual anthropomorphous agent with a realistic human face which moves in real-time on CRT responding to a user may become an important approach of advanced human interfaces in the near future. We are constructing such an interface system. This paper describes a speech dialogue function attached to the system. It enables one to develop a friendly guidance system through naturalistic conversation and facial expressions. Speech is an important medium for a human interface. The notable feature of our system is the integration of visual expression and speech dialogue; these two communication modalities can work together in human brain for better cognitive View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A number of fundamental emotions and their definitions

    Publication Year: 1994 , Page(s): 156 - 161
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (180 KB)  

    The research is divided into two parts. The first part is a rating experiment of KABUKI dramas using the SD method and an analysis of the rated data using the principal component analysis. Following these analyses, the author decided the number of fundamental emotions to be seven. In the second part, the author tried to define the seven fundamental emotions. Accordingly, the first part can be explained more precisely View full abstract»

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