Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525108
C. Richards, C.E. Smith, N. Papanikolopoulos
In response to the overcrowding of transportation systems, there has been an increase in the emphasis placed upon intelligent vehicle/highway systems (IVHS). Whether the application is keeping a safe distance between vehicles on highways or allowing a pedestrian to safely cross a street, environmental sensing and control play a crucial role in IVHS applications. In this paper we present robust visual detection and tracking techniques for IVHS applications, where computer vision may be the only sensor used or a part of a larger multi-sensor system. We have selected the application of pedestrian detection and tracking to demonstrate that the controlled active vision framework can provide precisely the type of information required to effectively manage traffic situations.
{"title":"Vision-based intelligent control of transportation systems","authors":"C. Richards, C.E. Smith, N. Papanikolopoulos","doi":"10.1109/ISIC.1995.525108","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525108","url":null,"abstract":"In response to the overcrowding of transportation systems, there has been an increase in the emphasis placed upon intelligent vehicle/highway systems (IVHS). Whether the application is keeping a safe distance between vehicles on highways or allowing a pedestrian to safely cross a street, environmental sensing and control play a crucial role in IVHS applications. In this paper we present robust visual detection and tracking techniques for IVHS applications, where computer vision may be the only sensor used or a part of a larger multi-sensor system. We have selected the application of pedestrian detection and tracking to demonstrate that the controlled active vision framework can provide precisely the type of information required to effectively manage traffic situations.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"8 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123547311","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525057
B. Carse, T. Fogarty
We propose an architecture and representation, based on the learning classifier system, for the learning of temporal behaviour in intelligent agents operating in environments where reasoning about time, as well as space, plays an important part in the success of a learning agent. We draw our inspiration from two main biological sources: first, the Darwinian model of evolution, embraced by the genetic algorithm (GA) and second, the proposed existence of internal clocks in organisms for learning of period and interval timing. Biological evidence for internal clocks and their use in living organisms are briefly summarised. We describe two versions, discrete and fuzzy, of a novel learning classifier system which incorporates internal clocks for the express purpose of learning temporal behaviour. Several possible application areas of the proposed classifier system can be envisaged. These include intelligent control, using the classifier system either for direct control or as a temporal model; artificial life in environments with temporal as well as spatial characteristics; and temporal pattern recognition.
{"title":"Evolutionary learning of temporal behaviour using discrete and fuzzy classifier systems","authors":"B. Carse, T. Fogarty","doi":"10.1109/ISIC.1995.525057","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525057","url":null,"abstract":"We propose an architecture and representation, based on the learning classifier system, for the learning of temporal behaviour in intelligent agents operating in environments where reasoning about time, as well as space, plays an important part in the success of a learning agent. We draw our inspiration from two main biological sources: first, the Darwinian model of evolution, embraced by the genetic algorithm (GA) and second, the proposed existence of internal clocks in organisms for learning of period and interval timing. Biological evidence for internal clocks and their use in living organisms are briefly summarised. We describe two versions, discrete and fuzzy, of a novel learning classifier system which incorporates internal clocks for the express purpose of learning temporal behaviour. Several possible application areas of the proposed classifier system can be envisaged. These include intelligent control, using the classifier system either for direct control or as a temporal model; artificial life in environments with temporal as well as spatial characteristics; and temporal pattern recognition.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130124502","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525111
Tianzhen Wang, Jie Yang
Reviews the certainty grids method, developed in CMU, MIT, and Stanford, and introduces how to use the method in the central program in robot perception and navigation. The authors also describe the sensor model in detail. Then the authors explain a simulation result.
{"title":"Certainty grids method in robot perception and navigation","authors":"Tianzhen Wang, Jie Yang","doi":"10.1109/ISIC.1995.525111","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525111","url":null,"abstract":"Reviews the certainty grids method, developed in CMU, MIT, and Stanford, and introduces how to use the method in the central program in robot perception and navigation. The authors also describe the sensor model in detail. Then the authors explain a simulation result.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127985533","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525030
T. Long, E.L. Hanzevack, S. Caggiano
We have previously successfully developed collocated neurocontrollers for vibration suppression. The objective of this research is to develop neural network controllers for vibration suppression under the constraint of noncollocated control. Noncollocated control may be necessary under at least two scenarios: physical constraints of sensor/actuator placement, or reconfiguration due to damaged elements. The neural controller is based on forward dynamics and decentralized control. This controller has been demonstrated to be effective in vibration suppression for two different systems.
{"title":"Noncolocated vibration control using neural networks","authors":"T. Long, E.L. Hanzevack, S. Caggiano","doi":"10.1109/ISIC.1995.525030","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525030","url":null,"abstract":"We have previously successfully developed collocated neurocontrollers for vibration suppression. The objective of this research is to develop neural network controllers for vibration suppression under the constraint of noncollocated control. Noncollocated control may be necessary under at least two scenarios: physical constraints of sensor/actuator placement, or reconfiguration due to damaged elements. The neural controller is based on forward dynamics and decentralized control. This controller has been demonstrated to be effective in vibration suppression for two different systems.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126611296","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525096
Y. Kwon, J.S. Lee
An obstacle avoidance algorithm, the weighted safety vector field (WSVF) method, is presented. In determining the orientation of the mobile robot, the algorithm first computes the primary steering angle for normal manuevering which is derived based on the fuzzy inference rule. To cope with the constrained environments such as corner and hallway, the algorithm then computes the secondary steering angle which is derived based on the fuzzy inference rule. The primary steering angle is used for the normal manuevering whereas the secondary steering angle compensates for the wiggling motion of the mobile robot that occurs frequently at the corner or at the hallway. The presented algorithm has been successfully tested on the simulation example.
{"title":"An obstacle avoidance algorithm for mobile robot: the improved weighted safety vector field method","authors":"Y. Kwon, J.S. Lee","doi":"10.1109/ISIC.1995.525096","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525096","url":null,"abstract":"An obstacle avoidance algorithm, the weighted safety vector field (WSVF) method, is presented. In determining the orientation of the mobile robot, the algorithm first computes the primary steering angle for normal manuevering which is derived based on the fuzzy inference rule. To cope with the constrained environments such as corner and hallway, the algorithm then computes the secondary steering angle which is derived based on the fuzzy inference rule. The primary steering angle is used for the normal manuevering whereas the secondary steering angle compensates for the wiggling motion of the mobile robot that occurs frequently at the corner or at the hallway. The presented algorithm has been successfully tested on the simulation example.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116554571","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525088
Z. Kovačić, S. Bogdan, P. Crnosija
The paper describes a model reference-based self-organizing fuzzy control scheme which is suitable for high-order systems of well-known structure. The conditions for stability of the learning process, which may be used for determination of the learning coefficient values, have been worked out. The way of improving the system response in the initial stage of learning by using the referent model-based method of presetting a fuzzy control surface is described. The proposed fuzzy control method has been tested in the angular speed control loop of a DCM servo drive. The results obtained have shown the feasibility and marked effectiveness of the self-organizing fuzzy control scheme indicating a better performance of the system with the preset fuzzy controller than with a blank fuzzy rule-table in the initial stage of learning.
{"title":"Design and stability of self-organizing fuzzy control of high-order systems","authors":"Z. Kovačić, S. Bogdan, P. Crnosija","doi":"10.1109/ISIC.1995.525088","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525088","url":null,"abstract":"The paper describes a model reference-based self-organizing fuzzy control scheme which is suitable for high-order systems of well-known structure. The conditions for stability of the learning process, which may be used for determination of the learning coefficient values, have been worked out. The way of improving the system response in the initial stage of learning by using the referent model-based method of presetting a fuzzy control surface is described. The proposed fuzzy control method has been tested in the angular speed control loop of a DCM servo drive. The results obtained have shown the feasibility and marked effectiveness of the self-organizing fuzzy control scheme indicating a better performance of the system with the preset fuzzy controller than with a blank fuzzy rule-table in the initial stage of learning.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116757235","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525049
R. Hooper, D. Tesar
This paper describes a method of redundancy resolution that combines closed form inverse kinematics with multicriteria optimization to form a method able to coordinate the motion of a hyper-redundant serial robot at deterministic speeds greater than 100 cycles per second on a personal computer. The work includes a listing of over 30 task-based performance criteria derived from physical models of the robot and presents formulations for several of them. It discusses a motion coordination method that explicitly generates motion options and evaluates them based on any number of performance criteria. The highest-ranking option becomes the next motion command for the robot's servo controllers. Finally, the paper presents a simulation of motion coordination for a hyper-redundant serial robot with 21 degrees of freedom.
{"title":"Motion coordination based on multiple performance criteria with a hyper-redundant serial robot example","authors":"R. Hooper, D. Tesar","doi":"10.1109/ISIC.1995.525049","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525049","url":null,"abstract":"This paper describes a method of redundancy resolution that combines closed form inverse kinematics with multicriteria optimization to form a method able to coordinate the motion of a hyper-redundant serial robot at deterministic speeds greater than 100 cycles per second on a personal computer. The work includes a listing of over 30 task-based performance criteria derived from physical models of the robot and presents formulations for several of them. It discusses a motion coordination method that explicitly generates motion options and evaluates them based on any number of performance criteria. The highest-ranking option becomes the next motion command for the robot's servo controllers. Finally, the paper presents a simulation of motion coordination for a hyper-redundant serial robot with 21 degrees of freedom.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131616005","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525054
B. Porter, N. Zadeh
In this paper, a new class of computed-torque/fuzzy-logic controllers is introduced and designed using genetic algorithms. It is demonstrated that these computed-torque/fuzzy-logic controllers are more robust than computed-torque/proportional-plus-derivative controllers.
{"title":"Genetic design of computed torque/fuzzy-logic controllers for robotic manipulators","authors":"B. Porter, N. Zadeh","doi":"10.1109/ISIC.1995.525054","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525054","url":null,"abstract":"In this paper, a new class of computed-torque/fuzzy-logic controllers is introduced and designed using genetic algorithms. It is demonstrated that these computed-torque/fuzzy-logic controllers are more robust than computed-torque/proportional-plus-derivative controllers.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132738412","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525099
K. Kyriakopoulos, P. Kakambouras, N. J. Krikelis
The problem of motion planing of a wheeled nonholonic vehicle is treated by decomposing the problem to the subproblems: 1) find a collision free path; and 2) approximate this path with a nonholonomic collision free path. This is treated, in real time, by solving the first subproblem using a potential fields strategy and the second one with nonholonomic tracking. Thus, collision avoidance of a nonholonomic wheeled vehicle in a feedback formulation is achieved.
{"title":"Potential fields for nonholonomic vehicles","authors":"K. Kyriakopoulos, P. Kakambouras, N. J. Krikelis","doi":"10.1109/ISIC.1995.525099","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525099","url":null,"abstract":"The problem of motion planing of a wheeled nonholonic vehicle is treated by decomposing the problem to the subproblems: 1) find a collision free path; and 2) approximate this path with a nonholonomic collision free path. This is treated, in real time, by solving the first subproblem using a potential fields strategy and the second one with nonholonomic tracking. Thus, collision avoidance of a nonholonomic wheeled vehicle in a feedback formulation is achieved.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131798524","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}
Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525077
George Paschos, K. Valavanis
Texture has been widely accepted as a feature of primary importance in computer vision. However, the majority of the research has focused on methods applied to grey-level images, where only the luminance component of the input signal is utilized. A method for describing the chromatic aspects of textures is proposed, that can be used for scene segmentation as well as classification. Experiments with synthesized and natural images justify the use of chromaticity-based measures.
{"title":"Chromatic measures for color texture description and analysis","authors":"George Paschos, K. Valavanis","doi":"10.1109/ISIC.1995.525077","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525077","url":null,"abstract":"Texture has been widely accepted as a feature of primary importance in computer vision. However, the majority of the research has focused on methods applied to grey-level images, where only the luminance component of the input signal is utilized. A method for describing the chromatic aspects of textures is proposed, that can be used for scene segmentation as well as classification. Experiments with synthesized and natural images justify the use of chromaticity-based measures.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134314320","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：