By Topic

Multisensor Fusion and Integration for Intelligent Systems, 1996. IEEE/SICE/RSJ International Conference on

Date 8-11 Dec. 1996

Filter Results

Displaying Results 1 - 25 of 112
  • International Conference on Multisensor Fusion and Integration for Intelligent Systems [front matter]

    Publication Year: 1996 , Page(s): i - xv
    Save to Project icon | Request Permissions | PDF file iconPDF (494 KB)  
    Freely Available from IEEE
  • Instrumented sensor systems

    Publication Year: 1996 , Page(s): 193 - 200
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (646 KB)  

    In modeling and designing sensor systems, there is always a tradeoff between increasing the robustness of the sensor system and increasing the efficiency of sensor use. To compare alternative solutions, we need to define quantitative measures that capture the required sensor system characteristics such as time and space complexity, robustness, error variance, etc. Our goal is to develop tools to assist selecting between the tradeoffs and defining models of global data values which establish a closer tie between data and its use. We propose to introduce the notion of instrumented sensor system for online monitoring and debugging. To achieve our goal, we start by defining a sensor model using formal semantics techniques. In this paper, we show that an operational semantics of logical sensor systems provides a strong computational and operational engine that can be used to define and propagate several quantitative measures to evaluate and compare between design alternatives. The application of the proposed modeling approach is illustrated by an example in which two sensing strategies for determining wall pose using sonar sensors are compared. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decision-theoretic multisensor planning and integration for mobile robot navigation

    Publication Year: 1996 , Page(s): 517 - 524
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (902 KB)  

    A decision-theoretic approach to multisensor planning and integration is investigated. The decision-theoretic framework allows for rational decision making under uncertainty and furthermore a highly modular system description that facilitates easy system integration. Experiments with a real robot show that the decision-theoretic sensor planner is capable of making rational real-time decisions about sensor use in an autonomous mobile robot context. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Proceedings 13th TRON Project International Symposium /TEPS '96

    Publication Year: 1996
    Save to Project icon | Request Permissions | PDF file iconPDF (818 KB)  
    Freely Available from IEEE
  • Conference Author Index

    Publication Year: 1996 , Page(s): 845 - 848
    Save to Project icon | Request Permissions | PDF file iconPDF (174 KB)  
    Freely Available from IEEE
  • A new sensing scheme for 3D active antenna

    Publication Year: 1996 , Page(s): 597 - 602
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (564 KB)  

    This paper discusses a new sensing scheme for 3D active antenna that can detect not only the contact location between an insensitive flexible beam and an object but also the normal direction of the object's surface where the beam makes contact. The active antenna is simply composed of an insensitive flexible beam, actuators to move the beam, position sensors to measure the rotational angle of the beam, and a moment sensor. In our former work (Kaneko and Kanayama, 1995), we have shown that both the normal direction and the contact distance can be obtained by more than three times pushing motions. Through the mathematical formulation between the pushing geometry and the contact force, we newly find that both the normal direction and the contact distance can be determined by just one time pushing motion, even though a lateral slip between the beam and an object appears during the pushing motion. We further verify the working principle by experiments View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multi-sensors localization for control of autonomous mobile robot

    Publication Year: 1996 , Page(s): 373 - 380
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (532 KB)  

    In this paper, we discuss an approach for designing and implementing a multisensory perception system in order to control an autonomous mobile robot when uncertainty and incomplete knowledge are the major characteristics of the situated environment. The approach relies on the combination of local and absolute localization methods. The former is lowly coupled to the environment and makes intensively use of odometric sensors. When high precision is required, telemetric sensors are used, being able to deal with error localization, Then, considering that these modules should cooperate in presence of constraints like limited resources, a knowledge-based system has to be used in order to approach the initially set goals View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human motion capture by integrating gyroscopes and accelerometers

    Publication Year: 1996 , Page(s): 470 - 475
    Cited by:  Papers (13)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (508 KB)  

    This paper describes a motion capturing system for human arm motion in real time; directly, simply and precisely by integrating two types of sensor; gyroscopes and accelerometers. A new sensor fusion technique is proposed which enlarges the merits of each sensor and compensates for their deficiencies. Its potential precision has been verified by experiment and simulation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The dead reckoning localization system of the wheeled mobile robot ROMANE

    Publication Year: 1996 , Page(s): 603 - 610
    Cited by:  Papers (16)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (684 KB)  

    This paper describes the dead reckoning localization system of the wheeled mobile robot ROMANE (Robot Mobile Autonome de Navigation de Exterieur). We are interested in quantifying the vehicle position estimation in an outdoor environment. The accuracy of position estimation by incremental shaft encoders on the wheels is very limited due to the poor quality of the rotational vehicle speed measurements. This paper shows how dead reckoning localization can be improved by the additional use of a gyroscope and a magnetic compass which are both also low cost sensors giving real-time information. We have developed a technique for compensation of magnetic field influences due to the robot itself under consideration of the vehicle dynamics the robot state is estimated by an extended Kalman filter which is developed for sequential data processing in order to reduce the computation time and to make the algorithm more flexible. Experimental results show the efficiency of our low cost dead reckoning localization system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An approach of the order identification for the transfer function of systems with superimposed noise

    Publication Year: 1996 , Page(s): 47 - 54
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (492 KB)  

    Conventional methods for estimating the transfer function models based on deterministic perturbations of the input such as step, pulse and sinusoidal changes have not always been successful because the response of the system may be masked by uncontrollable disturbances, collectively referred to as noise. Particularly in multisensor-integrated systems, the effect of noise from the sensors is not negligible and so the information on the system model and noise model is important for the accurate control of the integrated systems. In this paper, a statistical method for estimating the transfer function models with superimposed noise is presented. Similarity between the auto-correlation function of linear filter system driven by white noise and the impulse response function of dynamic system enables us to develop a method of identifying the order of dynamic systems. In order to identify the systems with superimposed noise, this paper derives R-, S-, and GPAC array which provide us with pretty clear information on the identification of dynamic systems with noise. From the derived arrays, we can obtain the order of transfer function model and also the order of noise model represented by an ARMA process. Finally, an example of order identification of transfer function model and noise model is presented to show effectiveness of the proposed algorithm View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiplicative inhibitory velocity detector (MIVD) and multi-velocity motion detection neural network model

    Publication Year: 1996 , Page(s): 476 - 483
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (504 KB)  

    Motion perception is one of the most important aspects of the biological visual system, from which we get a lot of information of the natural world. In this paper, trying to simulate the neurons in MT (motion area in visual cortex) who respond selectively both in direction and speed, we propose a novel multiplicative inhibitory velocity detector (MIVD) model, whose spatiotemporal joint parameter K determines its optimal velocity. Based on the response amplitude disparity (RAD) property of MIVD, we build two multi-velocity fusion neural networks (a simple one and an active one) to detect the velocity of 1-D motion. The experiments show that the active MIVD neural network with a feedback fusion method has a relative better result View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Failure detection using optimal parity vector sensitive to special sensor failure

    Publication Year: 1996 , Page(s): 55 - 61
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB)  

    Based on the parity space construction and the orthogonal constraint condition of parity vector, the approach of failure detection and isolation using optimal parity vector is presented in this paper. Its main idea is to design a performance criterion which is similar to the one proposed by Zhang and Patton (1993), but most sensitive to designated sensor's failure and least sensitive to other sensor's failure and unknown inputs such as noises. Through the Monte-Carlo simulation, it is shown that the approach of choosing optimal parity vector greatly increases the ability of failure detection and the effectiveness of failure isolation is better than the generalised likelihood test approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Grouping corresponding parts in vision and audition using perceptual grouping among different sensations

    Publication Year: 1996 , Page(s): 713 - 718
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (460 KB)  

    In sensor fusion, output from various sensors is fused to obtain better information. In those systems, it is implicitly assumed that output from various sensors has originated from the same object. However, if sensors are mounted on a system without intension, the assumption is not feasible. In many sensor fusion systems, designers set up sensors to obtain output originated from the same object. In the present paper, in order to automatically find relationship among sensors, we propose laws for perceptual organization among different sensations referring to the laws for organization in one sensation in the Gestalt psychology. Then the foundation of the laws is examined in simple experiments. The experimental system consists of vision and audition. It extracts corresponding parts of the two sensation referring to changes of output from each sensation View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An active microphone method for speech recognition systems

    Publication Year: 1996 , Page(s): 446 - 453
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (516 KB)  

    We propose a method to recognize human speech without the restriction that the speaker should be close to the microphone for the multiple modal interface. This method has the following features: 1) to control the microphone directivity for improvement of S/N ratio by using the speaker's position estimated by the result of gesture recognition, 2) to compose the impulse response of the transfer characteristic between speakers and microphones into reference data of the recognition system. We describe the active microphone method in detail, and show its effectivity through several experiments. Then, we discuss the results View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Intuitive control of a multi-robot-system by means of projective virtual reality

    Publication Year: 1996 , Page(s): 273 - 280
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1156 KB)  

    Experiences in controlling a multi-robot-system which is capable of performing different experiment handling and service tasks in a space laboratory environment, showed that the realization of a man machine interface based on modern virtual reality (VR) techniques is a promising approach for a new command and supervision interface that is intuitively operable. The general aim of the development described here was to provide the general framework for “projective virtual reality” which allows to “project” actions that are carried out by users in the virtual world into the real world with the help of robots. This framework is based on a new approach which relies on the “task deduction” capabilities of the virtual-reality-system and the task planning component of the multi-robot-control View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recovery of dynamic scene structure from multiple image sequences

    Publication Year: 1996 , Page(s): 305 - 312
    Cited by:  Papers (7)  |  Patents (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1000 KB)  

    Despite significant progress in automatic recovery of static scene structure from range images, little effort has been made toward extending these approaches to dynamic scenes. This disparity is in large part due to the lack of range sensors with the high sampling rates needed to accurately capture dynamic scenes. We have developed a system that overcomes this problem by exploiting video cameras, which easily capture images of dynamic scenes, and image-based stereo, which estimates scene structure based on correspondences among the images from different cameras. Our system uses a synchronized multi-camera recording system to capture live video of the scene and a software implementation of image-based stereo to compute range images off-line. By combining this system with multi-image fusion, we created a novel system for dynamic structure recovery, with many applications including telepresence, training, and entertainment. Development of this system has also revealed the potential use effusion as both a multi-view and multi-resolution integration process for stereo View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimal design of distributed signal detection systems

    Publication Year: 1996 , Page(s): 719 - 725
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (444 KB)  

    A distributed signal detection problem is considered in such a manner that a number of local detectors transmit their individual decisions, based on their own observations, to a global decision maker (data fusion center), which combine the local (preliminary) decisions to make the final decision. A DBT formulation of the binary DDF problem is described and the necessary conditions for the person-by-person optimal decision rule of overall system (local detectors) are derived. The special case of identical detectors with independent observation is investigated with an illustrative example View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of a distributed IMM algorithm for multi-platform multi-sensor tracking

    Publication Year: 1996 , Page(s): 455 - 461
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (476 KB)  

    In this paper, a distributed interacting multiple model (DIMM) algorithm for multi-platform multi-sensor tracking is presented, where the overall target model space is decomposed into all platforms. Each platform contains only a model subset, and interacting multiple model filtering is performed on all platforms. By exchanging some moderate filtering results through a platform communication datalink, a distributed interacting multiple model algorithm can be obtained. Since the DIMM has the advantages of distributed models and distributed measurements as well, significant computation can be saved and good performance can be achieved View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Synchronous-homogeneous concurrent propagation mechanism of competitive-waves for hyper-distributed hyper-parallel AI processing

    Publication Year: 1996 , Page(s): 806 - 813
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (680 KB)  

    This paper presents a new approach based on the synchronous homogeneous concurrent propagation of competitive waves and it is used for hyper-distributed hyper-parallel heuristic AI processing. The approach is featured by the knowledge-based problem-solving in the distributed parallel environment, the cellular array-based hardware architecture, and the various applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hole position and inclination sensor with 2 dimensional PSD, and its application to automatic shaft inserting

    Publication Year: 1996 , Page(s): 78 - 85
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (428 KB)  

    Shaft inserting is a frequent and important operation for automatic parts assembly. We have developed a sensor that can detect in real time the position of hole center and its inclination using a 2D position sensitive device (PSD). The sensor can detect the hole position by using the signals for the center of the light part. When the hole is inclined, a black ellipse image is focused on the PSD, the total current of one pair of PSD electrode differs from that of another pair. Therefore the sensor can detect the hole inclination by this current difference. We have developed an automatic shaft inserting system by applying the position and inclination sensor to a parallel joint robot with four freedom View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of optical proximity sensor: ORANGES system-optical range sensor with circular scanning

    Publication Year: 1996 , Page(s): 509 - 516
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (812 KB)  

    In this paper, we describe a method of range finding to an attentive local area of an object by a novel optical proximity sensor; ORANGES system, which is an abbreviation of an Optical RANGE Sensor system. ORANGES system is provided with a function of optical range sensing sequentially at each point along a circular path which is a locus of circular scanning of a laser beam projection. The prototype of the ORANGES system uses both circular scanning and the range sensing mechanisms View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of contact position between a grasped object and the environment based on sensor fusion of vision and force

    Publication Year: 1996 , Page(s): 116 - 123
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (732 KB)  

    Robots require various techniques of sensor fusion to achieve effectively manipulation tasks. This paper presents a sensor fusion method of vision and force information to estimate contact position between a grasped object and the other objects in the environment. The technique will be useful especially for assembly tasks since manipulation of an object by using visual information only often falls into difficulties because of the occlusions caused by the grasped object, surrounding objects, and the manipulator itself. In such situations, force sensor information helps to estimate the contact position even when the exact contact position is invisible. Consequently, sensor fusion of vision and force permits to improve adaptability of robot systems to changing situations in the task. Experiments using a robot system demonstrate usefulness of the proposed method. In addition, we address problems of sensor planning to automatically select sensor information taking the fusion of vision and force into account View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A direct interpretation of dynamic images and camera motion for vision guided robotics

    Publication Year: 1996 , Page(s): 313 - 320
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (720 KB)  

    A general scheme to represent the relation between dynamic images and camera motion is presented. Then, its application to visual servoing is proposed. For a specific object, the possible combination of the camera pose and the obtained image should be constrained on a lover dimensional hyper surface within the product space of whole combination of image data and camera position. The visual servoing, for example, is interpreted as to find a path on this surface leading to a given goal image. Our approach is to analyze the properties of this surface, and utilize its differential or tangential property for visual servoing. For this approach, the dimension of the image information becomes key problem. We propose to use the principal component analysis and to represent images with a composition of small number of “eigenimages” by using K-L (Karhunen-Loeve) expansion. In this paper, we describe, first, that a normal vector of this surface is related to the so-called interaction matrix, and confirm the feasibility of our basic idea for visual servoing with a preliminary experiment. Then, we present a dynamical estimation of the normal vectors to move robot arm mounting a camera to a goal position where a given goal image will be obtained. We also consider the construction of the eigenspace (the eigenimage space) to represent images efficiently and to speedup convergence in the control. Experimental results of visual servoing with proposed method show the feasibility and applicability of our newly proposed approach View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A fuzzy modeling approach to decision fusion under uncertainty

    Publication Year: 1996 , Page(s): 788 - 795
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (628 KB)  

    A multisensor decision fusion scheme is presented in which the probabilities associated with the local sensor decisions are known to vary in a nonrandom fashion around their design values. The uncertainties associated with the local decisions are modeled by means of fuzzy sets. A Bayesian approach is used to design the optimum fusion rule for the case where the local sensor decisions are statistically independent across the sensors. In order to reach a crisp decision, the global Bayesian risk is defuzzified using a criterion for mapping fuzzy sets on to the real line. The performance of the optimum fusion rule obtained is illustrated by means of a numerical example View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An onboard measurement system of gravity gradients using inertial accelerometers

    Publication Year: 1996 , Page(s): 108 - 115
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (568 KB)  

    A method of making possible the onboard measurement of gravity gradients is proposed in this paper. First, analytical solutions of gravity gradients are derived as the second order spatial gradients of the gravitational potential in the conservative field. Next, it is shown that the gravity gradients can be obtained from the outputs of inertial accelerometers placed some distance away from each other, and a concept of measurement system is clarified. Third, it is analytically shown that a gravity gradiometer system can be continued using twelve single-degree-of-freedom accelerometers or six two-degree-of-freedom accelerometers or four three-degree-of freedom accelerometers. Finally, it is concluded that a new type of inertial navigation system using gravity gradiometers will be configured when it becomes possible to precisely measure gravity gradients View full abstract»

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