{"title":"Locating a mobile robot using local observations and a global satellite map","authors":"A. Hayashi, T. Dean","doi":"10.1109/ISIC.1988.65419","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65419","url":null,"abstract":"A method for locating an autonomous mobile robot using local observations and a global satellite map is described. The satellite map provides approximate elevation data for an area within which the robot is known to be located. The map consists of a coarse grid of rectangular regions annotated with upper and lower bounds on the elevation within the region. In exploring its environment, the robot makes measurements to extract information about the relative position and orientation of local landmarks. These landmarks are integrated into a stochastic map, which is then matched with the satellite map to obtain an estimate of the robot's current location. The landmarks are not explicitly represented in the satellite map. The results of the proposed matching algorithm correspond to a probabilistic assessment of whether or not the robot is located within a given region of the satellite map. By assigning a probabilistic interpretation to the information stored in the satellite map, it is possible to provide a precise characterization of the results computed by the matching algorithm.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130168173","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":"Learning for the adaptive control of large flexible structures","authors":"Z. Gao, M. Peek, P. Antsaklis","doi":"10.1109/ISIC.1988.65483","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65483","url":null,"abstract":"An important problem in the adaptive control of large flexible structures is to select the adaptive controller parameters appropriately so that good performance is obtained. A method, based on machine learning, for solving this problem is introduced and discussed. It is shown that learning by observation and discovery can be effectively used in the adaptive control design, and in particular in optimizing the system performance. The search for the optimal performance is formulated as an unconstrained nonlinear optimization problem where the variables are the parameters in the adaptive controller and the cost function is the performance index which is defined as a weighted sum of the root-square-error, the maximum error, and the settling time. The learning system is built on top of the adaptive controller, and it employs a knowledge-based system which consists of a rulebase and a database. The results obtained are used to propose an intelligent adaptive control system where the parameters in the adaptive controller are to be tuned online without human supervision. Results of simulations are performed on the model of a large space antenna are given.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130819482","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":"Intelligent navigation for an autonomous mobile robot","authors":"E. Rodin, S. M. Amin","doi":"10.1109/ISIC.1988.65458","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65458","url":null,"abstract":"The authors present a navigational algorithm for solving the problem of collision-free path planning and real-time control of an autonomous mobile robot in an environment cluttered with moving obstacles. The proposed approach is based on geometric representation/multiobjective A* search and the path smoothing/steering control techniques. An attempt was made to introduce a geometric structure into a paradigm that lacked any previous structure, as well as a multiobject search technique. The proposed navigational system has the following three-level structure: identifier, goal selector, and adapter. The authors are currently implementing the algorithm on a Sun 4 artificial intelligence workstation.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130957238","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":"Integrating multiple sensors and industrial robots: system architecture and control aspects","authors":"J. Wahrburg","doi":"10.1109/ISIC.1988.65424","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65424","url":null,"abstract":"To improve the integration of sensors and robots, a system architecture that defines information processing in closed-loop sensor applications is proposed. The bandwidth of the control loop is increased by introducing additional underlying signal paths. This flexible system architecture reduces the deadtime problem by establishing additional underlying signal paths and allows the use of standard industrial robot controls with minor modifications. To be compatible to existing industrial robot controls, all sensor related tasks are transferred to the corresponding sensor computers. A separate sensor control unit is introduced as the main interface between the different sensors and the robot control. It performs the specific operations which are necessary for the adaptation to a given application, including data fusion in multiple sensor systems.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115549099","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":"Neural architectures for smart memories in analog VLSI","authors":"A. Andreou","doi":"10.1109/ISIC.1988.65511","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65511","url":null,"abstract":"Some basic issues related to the engineering of smart memory systems for intelligent control are discussed. In particular, it is noted that neurally inspired architectures for MOS analog VLSI implementation of smart memories yield highly regular and dense designs with improved performance and low power consumption. These architectures use MOS transistors in the subthreshold region and current-mode circuits. The neural paradigm not only offers insight into the architectures, but also into the actual implementation details. The bidirectional associative memory, the simplest nonlinear two-layer neural network model with feedback, has been implemented on silicon and tested functionally. Associative recall rates of 100000 vectors/s have been obtained with power consumption of a few milliwatts.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114574052","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":"Robotic deburring of two dimensional parts with unknown geometry","authors":"H. Kazerooni, M. Her","doi":"10.1109/ISIC.1988.65475","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65475","url":null,"abstract":"Two of the problems in robotic deburring are addressed: tracking the planar two-dimensional part contour and control of the metal removal process. The tracking mechanism is a roller bearing mounted on a force sensor at the robot endpoint. The tracking controller utilizes the force measured by this force sensor to find the normal vector to the part surface. Using the part contour information the robot travels along the edge of the part. The metal removal algorithm uses another set of contact forces, cutting forces generated by the cutter, to develop a stable metal removal. This algorithm generates electronic compliancy for the robot along the edge of the part. This electronic compliancy causes the robot to slow down when the cutter encounters a burr. A set of experimental results is given to verify the effectiveness of the approach.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116169396","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":"Linear robust control of mechanical manipulators","authors":"W.-s. Lu","doi":"10.1109/ISIC.1988.65470","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65470","url":null,"abstract":"A linear feedback control scheme for trajectory tracking is presented. It is shown to be robust against model uncertainties. The scheme is based on an eigen-analysis of the inertia matrix of the mechanical manipulator considered and a least-squares-type approximation of the Coriolis, centrifugal, and gravity terms in the manipulator's dynamics. The eigen-analysis and least-squares approximation lead to a simple yet reasonable model which in turn defines a structure of the constant feedback control. To determine the parameters of this controller, an analysis of the tracking-error dynamics is carried out using a Lyapunov approach. It turns out that, by properly choosing a set of feedback gains, the tracking error can be kept to a prescribed range during the task in the presence of the gravity effect and model uncertainties.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128258587","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":"Low data rate remote vehicle driving","authors":"M. Herman, K. Chaconas, M. Nashman, T. Hong","doi":"10.1109/ISIC.1988.65460","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65460","url":null,"abstract":"Several algorithms that have been implemented as possible candidates for a hybrid video compression system to be used for remote driving of a ground vehicle are described. The algorithms have been implemented on the pipelined image processing engine (PIPE) real-time image processing machine. The PIPE has been integrated with a remote control vehicle system, and the algorithms were evaluated by means of real-world remote driving experiments. These experiments have shown that remote vehicle driving is difficult enough without degrading the imagery through compression algorithms. The degraded imagery makes driving even more difficult. The following difficulties were found in driving in cross country terrain using either the full video or the compressed video: global relative vehicle location is very difficult for the driver to obtain; the orientation of the local ground surface is very difficult to obtain; ditches, gullies, and other obstacles are difficult to distinguish; and the range of objects from the vehicle is difficult to determine. It appears that performing compression by transmitting images at a rate of, at most, a few per second and then providing a realistic video simulation to the operator may be one of the most effective ways of performing video compression.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129740599","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":"Diagnosing multiple faults in intelligent controls and automated systems","authors":"M. Arjunan","doi":"10.1109/ISIC.1988.65411","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65411","url":null,"abstract":"The discipline of mathematical statistics has developed techniques of handling multiple events or what are called distributions of multivariate nature. An attempt is made to show how these traditional techniques can be applied to the problem of multiple failures in an expert system context. Generally, in a expert system, a set of hypotheses is proposed on the basis of the symptoms and, through a backward chaining or forward chaining technique, the set of causes is determined for the symptoms. It is in this process that the use of multivariate statistical techniques can be useful. One of the techniques, called principal components analysis, in which a set of symptoms and the covariance matrix of causes can be analyzed, is shown as an example. This yields a set of principal components that can be used to represent a large number of possible values of symptoms in a diagnostic application. An application to intelligent controls is discussed.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127453259","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":"Mathematical analysis of neural networks used in the solution of set selection problems","authors":"C. Jeffries","doi":"10.1109/ISIC.1988.65512","DOIUrl":"https://doi.org/10.1109/ISIC.1988.65512","url":null,"abstract":"The generalized neural network model of M. Cohen and S. Grossberg (1983) has been studied by many authors using Lyapunov-type functions. As an alternative, the author treats closely related dynamical systems (the gain functions are piecewise linear) with other dynamical-systems-theory machinery. It is shown that, by using a certain perturbation scheme, one can use such models with piecewise linear gain functions to solve a variety of set selection problems.<<ETX>>","PeriodicalId":155616,"journal":{"name":"Proceedings IEEE International Symposium on Intelligent Control 1988","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1988-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129075850","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}