{"title":"Image following using the feature-based optical flow approach","authors":"C. Cheng, Kun-Hsin Ho, Huimin Li, Gwo-Long Lin","doi":"10.1109/ISIC.2002.1157788","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157788","url":null,"abstract":"Visual servo can be achieved by extracting motion information from the optical flow, defined as the apparent motion of brightness patterns of an image. Since the optical-flow-based approach does not require knowledge of targets in advance, it is suitable for versatile tracking and positioning purposes. For most robotic tasks, steady position of the end-effector with respect to its working environment is essential to successful and efficient operations. In this paper, application of the optical flow technique to following of a moving image is presented. In addition, more accurate values of the optical flow are usually observed along image features. In order to achieve better estimation of the optical flow, feature-based optical flow computation approaches are also proposed. Image following tasks are demonstrated by 3D tracking experiments driven by stepping motors.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115591112","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pee Suat Hoon, Yang Rong Huan, J. Berge, Barnaby Sim
{"title":"Foundation/spl trade/ Fieldbus high speed Ethernet (HSE) implementation","authors":"Pee Suat Hoon, Yang Rong Huan, J. Berge, Barnaby Sim","doi":"10.1109/ISIC.2002.1157860","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157860","url":null,"abstract":"With the introduction of fast speed Ethernet and more reliable switches, end users are now more eager than ever to implement Ethernet solutions at the plant floor for real-time control applications. This paper illustrates some intelligent control functions that can be achieved by using Foundation/spl trade/ Fieldbus high speed Ethernet (HSE). This report is based on the recent experience gained from a field trial carried out between Singapore Polytechnic and Lee College located in Houston, Texas over the Internet.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124730470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Objects' combination based simple computation of attribute core","authors":"Zheng Zheng, Guo-Yin Wang, Yuehua Wu","doi":"10.1109/ISIC.2002.1157816","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157816","url":null,"abstract":"Rough set theory is emerging as a new tool for dealing with fuzzy and uncertain data. Attribute reduction is one of the most important parts in rough set theory. The attribute core of a decision table is often the start point and key of many information reduction procedures. Hu's method (1995) for computing the attribute core based on the discernibility matrix was wrong because of the neglect of some factors. The error was corrected by Dongyi Ye, but the complexity of his algorithm was too high. In this paper, we present a new algorithm based on object combination. The algorithm corrects Hu's error and has less complexity than Ye's and Hu's methods.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129157693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Motion dynamics and path tracking control problem of a dual-unit articulated vehicle","authors":"A. Hemami","doi":"10.1109/ISIC.2002.1157761","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157761","url":null,"abstract":"A particular class of vehicles, consisting of two units of single axle half vehicles (or two-wheeled trailer) pivoted together in the middle, is used for ore transportation in underground mines. Steering of this vehicle is performed by changing the angle between the two units through an actuator. Automated motion of this relatively low-speed vehicle is of interest. In this paper, the dynamics of motion of this type of vehicle are studied and the equations governing the motion and the tracking error dynamics are formulated. The objective is to see how the dynamic forces can affect the vehicle behaviour in path tracking. The system inputs are the traction forces on the front and rear wheels and the articulation actuator effort. These equations can be used for formulation of the path tracking control problem and synthesis of a control policy for automated guidance of the vehicle.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126946505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Controllability and stabilizability of a class of hybrid dynamic systems","authors":"G. Xie, Long Wang","doi":"10.1109/ISIC.2002.1157880","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157880","url":null,"abstract":"Many practical engineering problems can be modelled as such a class of hybrid dynamic systems (HDSs), where N plants are controlled by a central controller in sharing time manner. These plants are described by differential equations and the controller works according to the mechanism of discrete event. This paper discuss the controllability and stabilizability of this class of hybrid dynamic systems. First, we define the controllability of this class of HDSs and establish the necessary and sufficient condition for controllability. Furthermore, we define the stabilizability of this class of HDSs and establish the necessary and sufficient condition for stabilizability as well.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125589985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stabilization of stochastic recurrent neural networks","authors":"E. Sánchez, J. Perez","doi":"10.1109/ISIC.2002.1157804","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157804","url":null,"abstract":"The paper presents the stabilization of a dynamic neural network disturbed by additive Gaussian noise. This stabilization is achieved using a quadratic Lyapunov function. A control law is derived, which ensures that the neural network state becomes globally uniform ultimately bounded (GUUB) in probability. The applicability of the proposed control law is illustrated by an example.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122553253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Claudio Ambra, K. Oldknow, Guiseppe Migliorini, I. Yellowley
{"title":"The design of a high performance modular CNC system architecture","authors":"Claudio Ambra, K. Oldknow, Guiseppe Migliorini, I. Yellowley","doi":"10.1109/ISIC.2002.1157777","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157777","url":null,"abstract":"The authors review various design options available for open architecture CNC systems. The current trend towards software only motion control is contrasted with the more traditional approach using a separate processor. A rather different approach integrating the real time activities, including interpolation and position measurement, within an FPGA is the focus of the paper. The system approach described is based upon the integration of the stateline architecture developed over the past 12 years in the Manufacturing Engineering Laboratory at the University of British Columbia with Theseus, a new innovative modular design for industrial electronics developed by Sitek SPA.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121169377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A neural-fuzzy logic approach for modeling and control of nonlinear systems","authors":"O. M. Ahtiwash, M. Z. Abdulmuin, S. F. Siraj","doi":"10.1109/ISIC.2002.1157774","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157774","url":null,"abstract":"Neural networks and fuzzy logic systems are two of the most important results of the research in the area of soft computing. While neural networks and fuzzy logic have added a new dimension to many engineering fields of study, their weaknesses have not been overlooked, in many applications the training of a neural network requires a large amount of iterative calculations. The technique used in this work replaces the rule-base of a traditional fuzzy logic system with backpropagation neural network. We propose an adaptive neuro-fuzzy logic control scheme (ANFLC) based on the neural network learning capability and the fuzzy logic modeling ability. The development of this system is carried out in two phases: the first phase involves training a multilayer neuro-emulator (NE) for the forward dynamics of the plant to be controlled; and the second phase involves online learning of the neuro-fuzzy logic controller (NFLC). Extensive simulation studies of nonlinear dynamic systems are carried out to illustrate the effectiveness and applicability of the proposed scheme.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123838873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reference governor control of constrained feedback systems using neural networks","authors":"Harshad Jahagirdar, S. Keerthi, M. Ang","doi":"10.1109/ISIC.2002.1157766","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157766","url":null,"abstract":"A neural network approach to reference governor control of systems with constraints on state and control variables is discussed. A feed-forward neural network architecture is used to define safety sets in a constrained system state-space. Results presented here include the description of a neural reference governor algorithm and its application to linear and nonlinear control systems. The objective is to demonstrate the feasibility of such a design as an alternative to the Lyapunov function approach to the control of constrained systems.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"201 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124930629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Real-time torque control of nonholonomic mobile robots with obstacle avoidance","authors":"Tiemin Hu, Simon X. Yang","doi":"10.1109/ISIC.2002.1157742","DOIUrl":"https://doi.org/10.1109/ISIC.2002.1157742","url":null,"abstract":"In this paper, a novel torque controller is presented for nonholonomic mobile robots with obstacle avoidance. In the proposed controller, based on the artificial potential fields technique, an obstacle torque is introduced in the controller, which acts locally to push the robot away from the obstacles. The environment is initially assumed to be completely unknown, except the target location. Environment information is obtained from onboard robot sensors that have limited visibility range only. The neural network assumes a single layer structure, by taking advantage of the robot regressor dynamics that express the highly nonlinear robot dynamics in a linear form in terms of the known and unknown robot dynamic parameters. System stability and convergence are rigorously proved using a Lyapunov theory, subject to unmodeled disturbance and bounded unstructured dynamics. The real-time fine control of mobile robots is achieved through on-line learning of the neural network without any off-line learning procedures. A series of simulation results show that the proposed controller can be successfully applied to both static and dynamic environments, as well as a multi-robot system.","PeriodicalId":228502,"journal":{"name":"Proceedings of the IEEE Internatinal Symposium on Intelligent Control","volume":"639 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132789565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}