Search

This paper proposes a method for mobile robot self-localization by the use of a passive RFID system and Support Vector Machines (SVMs). The use of the SVM eliminates the need for laborious measurement of the geometric position of each RFID tag. Furthermore, the method works even when several malfunctioning tags are included. The ability of the method is confirmed in tests, and we conclude that the method performs well. © 2010 Wiley Periodicals, Inc. Electr Eng Jpn, 172(4): 19–30, 2010; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20967

This paper describes the on-demand patient service system which uses RFID tags and a wheelchair robot in medical facilities. In this system, the robot can identify a patient and obtain his/her diagnosis schedule by the RFID tag in his/her registration card. According to the schedule, the robot can carry the patient to his/her target examination room. To construct this system, we employ the idea of the intelligent environment, called “Robot Town”. Many sensors are distributed in Robot Town, and robots can easily move and work by using the sensors. We executed a proving experiment with our system under the scenario that assumed an outpatient came to the unfamiliar and large medical facility. In addition, to evaluate our system, we executed the questionnaire survey to nurses. As the result of survey, we know that their expected points are an improvement of the daily work efficiency, safe transportation of patients and an improvement of an amenity level in a hospital. And, we also know that their worried points are safety of the robots, the abilities of detection to the unexpected emergency situations, costs and difficulties of maintenance of systems, and responsibilities in case of accidents.

To structure environment in informative way through the sensor network with distributed RFID tags is a promissing approach to an autonomous intelligent robot working in an ordinary environment for daily human life. This paper proposes methods to integrate the data from sensors into online database of the environment and to provide a robot with realtime information of the dynamically changing situation of its surroundings. Based on the analysis of sensor functions and data requirement from the robot, we have designed and implemented a data management system. In the experiments, decision and action of the robots in a task context have been successfully achieved by using the data provided through the data management system.

Self-localization of the mobile robot using RFID system generally requires a lookup table which relates the ID of each tag with its position. However, it is tedious for a human worker to manually build the table. This paper proposes a method to automatically build the lookup table by a simple mobile robot without global position measurement function. Given the small number of RFID tags with their accurate position data, the method successfully build the lookup table for many other RFID tags whose position is unknown in advance.

We propose continuous-time system identification using discrete data and continuous curves of the data obtained by curve fitting. We describe a method for fitting a finite Fourier series to discrete data and show that the fitted curve can be created as the output from a bilinear neural network system. By using this method for fitting, we propose a method for determining the optimal values for coefficients in the differential equation which expresses a continuous-time system.

This paper presents a method for the analysis of bilinear neural networks (BNNs) with time delay. A BNN system was proposed to analyze a weak nonlinear model. To analyze this system, we need to solve the equations for the system. In this paper, we propose a method that determines whether it is possible to solve the equations analytically. If this is possible, we propose a concrete method for solving them. This paper also presents new optimum curve fitting for data sampled at discrete times, such as data outputted from a sensor in a mobile phone, and a new BNN system for curve fitting. Moreover, this paper presents one example where the BNN system for curve fitting and other BNN systems are applied to the analysis of human motion.

This paper describes a method for Event handling on Robot Town platform and its application by using a wheelchair robot. To enable a sharable personal mobility robot system by using a motorized wheelchair on the market, vision sensors and RFID tags are distributed and are connected to a network. Sensor data are used by the robot for not only the event to perform self-localization but also the event of on-demand calling from the user. Experiments confirmed that wheelchair robots made decisions and completed tasks successfully by use of the method for event handling on Robot Town platform.

This paper proposes a method for the self-localization of a mobile robot using a passive radio frequency identification (RFID) system and support vector machines (SVMs). Using the SVM, we do not need to perform any complicated tasks for measuring the geometric position of each RFID tags to produce a look-up table as used by conventional self-localization methods. Moreover, the method works even when several malfunctioning tags are included. The performance and accuracy of the method are confirmed by our simulation test, and we conclude that the method shows almost the same performance as that of a look-up table.

The layout design for the wire harnesses cannot be performed until a mechanical prototype is completed because of the necessity to determine the route and length in consideration of deformation. This paper proposes a real-time wire harness deformation simulation method that works together with a mechanism, and a design support system that allows virtual verification of wire harness layout using a 3-D product model. Real-time deformation simulation includes mechanical simulation calculating kinematics and harness shape simulation using a Bezier curve. The design support system allows interactive verification of exact length, maximum curvature and collision by simulating the behavior of a mechanism and a wire harness.Copyright © 2006 by ASME

In mechanical systems development, it is well known that verification tests covering all aspects of mechanics, software, and hardware cannot be performed until a working prototype of the product is completed. As a result, serious flaws may be not discovered until the final stages of development, resulting in delays and extra work, mainly on the embedded software (known as firmware). We propose a new design and manufacturing methodology for mechanical systems that is based on a 3D real-time simulator, called “VPS” (Virtual Product Simulator). This simulator enables the development of virtual mechanical models on computers, allowing engineers to work on the model without seeing the actual device. It provides more time to thoroughly test the whole system, thereby, making the development process more efficient.Copyright © 2002 by ASME