By Topic

Robot and Human Communication, 1992. Proceedings., IEEE International Workshop on

Date 0-0 1992

Filter Results

Displaying Results 1 - 25 of 70
  • Proceedings. IEEE International Workshop on Robot and Human Communication (Cat. No.92TH0469-7)

    Publication Year: 1992
    Save to Project icon | Request Permissions | PDF file iconPDF (28 KB)  
    Freely Available from IEEE
  • Concept and realization of adaptive interface based on user's skill and uncomfortableness

    Publication Year: 1992 , Page(s): 171 - 176
    Cited by:  Papers (2)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (460 KB)  

    The authors consider a realization method on intelligent interface which is comfortable and useful for both beginners and experts to carry out a given task. They show the concept of the adaptive interface and the realization method based on user's skill level and evaluation of human impatience/uncomfortableness View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Selective attention in motion perception

    Publication Year: 1992 , Page(s): 300 - 304
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (380 KB)  

    The effects of selective attention on the duration of motion aftereffects were examined for investigating the hierarchical structure in a motion processing system. In the psychophysical experiments, the human subjects were adapted to each of the various kinds of motion, such as simple translation, expansion, contraction and rotation, and they carried out a concurrent task of alphanumeric discrimination, which required voluntary selective attention. The results showed that the selective attention did not reduce the duration of the motion aftereffects caused by the expansion/contraction/rotation, though it was affected by the simple translation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intelligent tutors in simulated environments that evolve to operator associates in actual systems

    Publication Year: 1992 , Page(s): 166 - 170
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (432 KB)  

    Effective operator training is possible via the use of intelligent tutoring systems. Such systems incorporate system knowledge and operational information under normal and degraded conditions. They can be designed to adapt to the skill levels of the operators, and function as operator associates that share responsibility for system operation. The author discusses the characteristics necessary for the evolution of tutors into operator associates View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MIT-MANUS: a workstation for manual therapy and training. I

    Publication Year: 1992 , Page(s): 161 - 165
    Cited by:  Papers (53)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (304 KB)  

    This paper presents some recent work on the development of a workstation for teaching and therapy in manual and manipulative skills. The experimental workstation, MANUS, as well as the overall concept are described. State-of-the-art aspects of the workstation under development are introduced View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of mixed facial expressions by neural network

    Publication Year: 1992 , Page(s): 387 - 391
    Cited by:  Papers (15)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (400 KB)  

    Deals with a neural network method for the machine recognition of mixed facial expressions by decomposing mixed facial expression into 2 or 3 components of 6 basic ones. The authors obtain the facial images, which show mixed facial expressions, from video tape recorded facial images and from the information of facial expressions in terms of the (x,y) coordinates of facial characteristic points. Then the position information of facial image is generated for 19 clients, and is used for the neural network training and recognition test. The recognition test is done by inputting the facial information, not being used in training the neural network, to the trained neural network. The recognition results obtained by the neural network are compared with those by humans. The neural network method is found to give a rather high agreement rate of about 70% compared with those obtained by humans View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hybrid architectures for intelligent robotic systems

    Publication Year: 1992 , Page(s): 329 - 334
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (484 KB)  

    Hybrid architectures, based on combinations of analogic, symbolic, and neural methods, are well suited for real-time applications in advanced robotics. Real-time industrial applications are mainly based on the correction of preplanned programs. So far, the planning and control modules of these kind of applications are often unable to react and/or classify un-expected events. The approach described attempts to integrate the sensor-based analogic method and the neural method into a multiple-level architecture that operates on an analogic world model, so that the action planning can be performed in a smart, reactive way. Given the task, the system builds the world model of the scenario. The reasoning and planning modules act both at the strategic as well as reactive levels, and the activated sensor-based motor strategies handle the sensorial data inputs and drive the robot controller module in the execution of the stream of motor commands. The interaction between the different levels is mainly based on the idea of maintaining and updating in real-time the world model, so that each module can locally operate on specific parts of the whole world model View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of Six basic facial expression and their strength by neural network

    Publication Year: 1992 , Page(s): 381 - 386
    Cited by:  Papers (48)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (568 KB)  

    Develops an `Active human interface' that realizes interactive communication between machine (computer and/or robot) and human. The authors investigate the method of machine recognition of human facial expressions and their strength. They deal with the neural network method of recognition of facial expressions. Considering 6 groups of facial expressions, i.e. surprise, fear, disgust, anger, happiness and sadness, they obtain 30 x- and y-coordinates of facial characteristic points representing 3 face components (eyes, eyebrows and mouth). Then they generate the facial position information which is input to the input units of a neural network; the network learning is done by backpropagation algorithm and the recognition test is carried out. For the six basic facial expressions, the correct recognition ratio was found to be about 90%. This paper further investigates the method of recognizing the strength of the six basic facial expressions by a neural network View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computer graphics for expressing robot-artificial emotions

    Publication Year: 1992 , Page(s): 155 - 160
    Cited by:  Papers (12)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (852 KB)  

    The concept of active human interface (AHI) is proposed to accomplish a friendly communication between human and robot/computer, and this paper deals with 3D computer graphics technique to display the inner state of AHI, i.e., robot-artificial emotion by means of facial expression solid model of a human face is used as a media of displaying the robot artificial emotions and an action units (AUs) system is utilized to generate six basic facial expressions on 3D solid model of a human face. A neural network mapping between six basic facial expressions and AUs can succeed in displaying various mixed facial expressions on the human face model View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A tele-machining system using multi-axis force data and stereo sound information

    Publication Year: 1992 , Page(s): 227 - 234
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (720 KB)  

    This paper describes a tele-machining system using multi-axis force data and stereo sound information. In the proposed system, the force information from the multi-axis force sensor is used not only to determine the machining and the operation state but is also reflected back to the operator through a three degree-of-freedom joystick to give the human operator the impression that he is directly manipulating the object. This illusion is created by mapping the multi-axis force information obtained in the cutting zone to the joystick system. As a further aid to understanding the process state, stereo sound, including both verbal and non-verbal information, is included in the system to enhance the user interface. Changes in the cutting state are perceived by the operator as changes in the tone quality. Verbal information is transmitted to the system by the operator in the case of an extraordinary cutting state and is also used to confirm the instructions of the operator. The availability of such verbal and non-verbal information decreases the anxiety of the operator. The effectiveness of the system was demonstrated by experiment View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A prototype of goldfish software robot with real-time response function by a parallel computer

    Publication Year: 1992 , Page(s): 323 - 328
    Cited by:  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (744 KB)  

    This paper describes a parallel computing system and a software algorithm for real-time interaction between a human user and the synthesized moving goldfish images. Two realistic goldfish agents appearing on a display can recognize the palm position and finger motion (finger sign) of the user, then respond to them in real-time. The authors have named this kind of interactive agent a `software robot'. A modeling software named `BSSM' (Bone-Structured Solid Modeler), which is suitable for representing deformable objects (such as living things) plays an important role in the synthesis of realistic goldfish images. To realize the real-time interaction, they have developed an image recognition and synthesis system `TN-VIT' (Transputer Network with Visual Interface for Transputers). The image synthesis speed of the TN-VIT is about 25 frames per second including the finger-sign recognition process. The technology discussed is expected to play an important role in the realization of future visual human interfaces View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A force display system for virtual environments and its evaluation

    Publication Year: 1992 , Page(s): 246 - 251
    Cited by:  Papers (20)  |  Patents (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (464 KB)  

    This paper describes a virtual-force display system that presents force sensations during the manipulation of objects in a virtual environment. In the tasks that have interactions with the environment, force sensation is the most important information used to recognize the interactions between the objects. The authors discuss a method of virtually generating the constraint forces in the model world, and propose a virtual force display system. In this system, the operator obtains the visual information from a graphic display and feels real-time reaction forces through an operating handle. This operating handle is used for the force exertion and the motion sensing. These visual and kinesthetic senses help the operator to understand the virtual world with high fidelity. Using this system, the performed experiments to confirm its effectiveness. In the experiments, an operator manipulates an object in model space using a 4-DOF master arms as an operating handle. Results of the experimental operation show that the operator can feel the contact state with a realistic sensation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An upper extremity prosthesis using SMA actuator

    Publication Year: 1992 , Page(s): 52 - 57
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (520 KB)  

    Many kinds of powered upper extremity prostheses with multi-degree-of-freedom have been studied and developed. However, in daily life, there are few upper extremity prostheses which the handicapped can use. In the superior limits of weight and size, the prostheses with multi-degree-of-freedom and multi-functions are requested by the handicapped. To achieve this, the authors tried to develop a prosthesis which imitates the human arm. The prosthesis is made up of internal frames, quasi-ligaments and quasi-muscles. Therefore it can be made light and compact like a human arm, and it can move more naturally than other mechanical prostheses. The design concept, method and trial production of the prosthesis are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An analysis method for human assembly operations

    Publication Year: 1992 , Page(s): 398 - 403
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB)  

    A method of describing human movements in a symbolic manner is discussed. Human workers learn operation skills by repeating the task. It is not easy for the worker to describe his skill as robot commands or motion control parameters. To transfer human skills to robots, they must be represented in a symbolic form. In this analysis, the human operator's movements are converted into a sequence of triplets (states, movement parameters, rotation parameters). Dextrous movement is defined as the difference set between triplets among the tasks. Results of experiments using a six-degree-of-freedom manipulator are discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CCD camera model and its physical characteristics consideration in calibration task the robotics

    Publication Year: 1992 , Page(s): 75 - 77
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (256 KB)  

    In most robotic vision systems the very first step towards the real application is to perform the camera calibration. The authors describe some important aspects about CCD (charged coupled-device) camera characteristics which affect the precision of their calibration procedure. They discuss first the optic image forming using a CCD camera, the digital image acquisition and the possible deformation in this stage, then they establish a pin-hole model derived from a thin and a thick lens optical model as well as the errors caused in the model approximation. Finally, they suggest some consideration about physical characteristics of these sorts of camera in robotic calibration task View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Control of manipulator/vehicle system for man-robot cooperation based on human intention

    Publication Year: 1992 , Page(s): 188 - 193
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (380 KB)  

    Proposes a control method for the manipulator/vehicle system which has redundant degrees of freedom. In order to control the system, the authors decompose the motion of the end effector in the inertial coordinate system into the vehicle's motion and the manipulator's motion because the motion of the end effector with respect to the inertial coordinate system is realized by both the manipulator's motion and the vehicle's motion. How to decompose the end effector's motion is one of the key issues for the manipulator/vehicle system. If one wants to move the system to another place, the motion of the end effector should be realized by the vehicle's motion. On the other hand, if one wants to manipulate an object, the motion of the end effector should be done by the manipulator's motion. That is, the decomposition of the end effector's motion in the inertial coordinate system should be done based on the human intention. The method proposed controls the motion of the manipulator and the motion of the vehicle based on the operator's intention modelled by fuzzy rules. The experimental results illustrates the effectiveness of the proposed control method for the manipulator/vehicle system for man-robot cooperation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A tool for artificial reality: from views to object representation

    Publication Year: 1992 , Page(s): 222 - 226
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (384 KB)  

    Deals with a robust technique which is able to synthesize the volumetric structure of an object from a set of 2D perspective views where the object silhouette has been extracted. The surface texture is also recovered from the views. The final model is a closed polygon mesh surface integrated with texture informations, and it is thus suitable for standard graphic rendering. The proposed procedure can be used to obtain real world object representations starting from real views instead of manually building them by means of solid modeling and painting systems. As shown by the reported experiments, the results are promising in all cases where the objects can be accurately reconstructed from the occluding contours technique, i.e. when the concavities, if present, are visible in the projected object silhouettes View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feeling the overturn stability of a platform

    Publication Year: 1992 , Page(s): 241 - 245
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (460 KB)  

    Overturn stability is an important safety factor for platforms such as swing cranes, wheeled or legged vehicles and mobile robots. Human operators have no feeling for mass distribution. Inclination is estimated inaccurately, thus resulting in a latent risk of overturn especially for platforms operating in rough terrain. This paper presents an approach to feed the margin of overturn stability back to the operator. Opposing forces exerted by an active control level inform the operator about the margin of overturn stability. This provides a fast, unignorable and instantly interpretable feedback. Feeling the overturn stability of the platform the operator can focus fully on his task while safety and performance of the platform is improved View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interface design for man-machine mechanical interactions

    Publication Year: 1992 , Page(s): 143 - 148
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (384 KB)  

    A mechanical system, such as a robot system for man-robot cooperation, a master-slave manipulator system, a power-steering system, an extender etc. has interactions among the system, the operator and its environment. How to control the interactions so that the desired interaction is realized, is one of the key issues for the control of such a mechanical system. The design of the controller of mechanical systems with man-machine interactions is discussed. The authors first model the mechanical system, which has interactions with its environment and an operator, then propose a control algorithm so that the desired interaction is realized. The proposed control system, consists of two controllers: one generates the desired motion of the mechanical system based on the force applied to the system, and the other one controls the interaction between the system and its environment. The proposed control algorithm specifies both force augmentation and maneuverability of the system. The algorithm is applied to a planar manipulator with one degree of freedom and the experimental system illustrates the concept of the system View full abstract»

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

    Publication Year: 1992 , Page(s): 269 - 274
    Cited by:  Papers (12)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (332 KB)  

    This paper describes a basic control structure for scaled manipulation. Tools for scaled manipulation are necessary when one manipulates a target of quite different size from one's body. In such case, the tool has to scale up or down not only `size' but also `force' in bilateral way. This paper asserts that `time scale' should also be considered together with size and force in order to build up an intelligent tool which provides an imaginary work environment as if one can feel one's body size is scaled to the target size. And this paper propose two simple time scaling methods which can be used in bilateral force-position controls View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Facial feature measurements with photometric stereo

    Publication Year: 1992 , Page(s): 392 - 397
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (460 KB)  

    This paper introduces an application of photometric stereo to facial feature measurements. First, the authors propose a modified photometric stereo which reduces the size of the table and errors of the table lookup. Then, three applications are described, all of which use the gradient data obtained by the modified photometric stereo. These examples show that the photometric stereo is quite sufficient for facial feature measurements though the albedo of human face does not completely agree with the Lambertian reflectance View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An interfacing method between an artificial hand and human

    Publication Year: 1992 , Page(s): 194 - 198
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (376 KB)  

    First, the flexible grasping motion control for a hand with two fingers is explained. For this control the reference grasping force must be decided in advance of the operation and the property of the reference grasping force is explained. Second, the way to extend the grasping control by including the operator to the control loop is explained. Through consideration of the property of the reference grasping force the design of the master hand mechanism is explained View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A robot teaching method using Hyper Card system

    Publication Year: 1992 , Page(s): 410 - 412
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (240 KB)  

    Human and robot communication is becoming more important for the next generation robot systems. This paper describes a robot teaching system with user friendly interfaces in order to improve the conventional teaching methods. The hyper card system in the Macintosh computer is used for the robot teaching system because of its easy handling and excellent human interfaces. The program in the Hyper Card is written in HyperTalk and XCMD for sending commands to a robot system; each joint of the robot can be controlled by clicking the mouse buttons. As an example of this system, the robot teaching operations of grasping a bin and pouring liquid into a cup are carried out using only one third of the teaching time as compared with the conventional teaching method. Consequently, this robot teaching method using Hyper Card system provides a foundation for realizing a user friendly human and robot communication View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A request of the robot: an experiment with the human-robot interactive system HuRIS

    Publication Year: 1992 , Page(s): 204 - 209
    Cited by:  Papers (4)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (300 KB)  

    Discusses about the interface for personal robot systems that are not supported by social authority. The paper consists of two parts. The paper describes HuRIS, a human-robot interactive system for supporting human-robot and human-human communication. HuRIS aims to be acting as an agent of a user. The robot of HuRIS can accept voice commands by its voice recognizer, and can reply via its simple natural language processing system and voice synthesizer. The robot has the ability of asking a human for help by using the voice synthesizer when it is trapped in failure. However, the humans around the robot do not always accept its commissions. The necessary condition that a human accepts a request of a robot is not known. The authors describe experiments on robot's commission in some detail. In Experiment 1, they show that a request of a robot supported by no social authority is not accepted by a human. In Experiment 2, they show that by using the HuRIS's interface, the performance of the subjects is generally similar for human and robot commission. The paper concludes that the interface for HuRIS as a personal mobile robot system is effective View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • What the human face tells the human mind: some challenges for the robot-human interface

    Publication Year: 1992 , Page(s): 44 - 51
    Cited by:  Papers (7)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (892 KB)  

    The human face serves a variety of different communicative functions in social interaction. The face mediates person identification, the perception of emotional expressions and lipreading. Perceiving the direction of social attention, and facial attractiveness, also affect interpersonal behaviour. This paper reviews these different uses made of facial information, and considers their computational demands. The possible link between the perception of faces and deeper levels of social understanding is emphasised through a discussion of developmental deficits affecting social cognition. Finally, the implications for the development of communication between robots and humans is discussed. It is concluded that it could be useful both for robots to understand human faces, and also to display human-like facial gestures themselves View full abstract»

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