The problem of designing intelligent machines operating in uncertain environments with minimum supervision or interaction with a human operator is examined. The structure of an intelligent machine is defined to De the...
详细信息
The problem of designing intelligent machines operating in uncertain environments with minimum supervision or interaction with a human operator is examined. The structure of an intelligent machine is defined to De the structure of a Hierarchically Intelligent Control System, composed of three levels hierarchically ordered according to the principle of "increasing intelligence with decreasing precision," namely: the organization, the coordination and the hardware control levels. The behavior of such a machine may be managed by controls with special considerations and its "intelligence" is directly related to the derivation or a compatible measure that associates the intelligence of the higher levels with the precision of execution of the lower levels. It is shown that the concept of entropy as defined in Information Theory and Theoretical Thermodynamics is a sufficient analytic measure that unifies the treatment of all the levels of an intelligent machine as the mathematical problem of finding the right sequence of internal decisions and controls for a system structured in the order of intelligence and inverse order of precision (constraint) such that it minimizes its total entropy
The Ada Research Group of the robotics Research laboratory at The University of Michigan is currently developing a real-time distributed computing capability based upon the premises that real-time distributed language...
详细信息
Fundamental factors limiting the widespread application of current robotic systems are the requirements for precise control of the robot task environment, custom-designed fixtures and end-effectors, and on-site contro...
详细信息
Fundamental factors limiting the widespread application of current robotic systems are the requirements for precise control of the robot task environment, custom-designed fixtures and end-effectors, and on-site control program development. These requirements arise because current robotic systems do not have an understanding of the robot task environment. Further, these systems are not able to react intelligently to non-deterministic events which occur during task execution. This paper examines the nature of understanding and its use to resolve uncertainty as it relates to robot task execution. Then a research plan which is aimed at the systematic incorporation of understanding into the robot task environment is outlined.
computer-aided design (CAD) has found a hew home in the control systems theory. Many control system's related problems such as analysis, design, estimation, filtering and simulation are now handled through CAD pac...
详细信息
computer-aided design (CAD) has found a hew home in the control systems theory. Many control system's related problems such as analysis, design, estimation, filtering and simulation are now handled through CAD packages and languages. Through these software tools, even a novice computer programmer can take advantage of powerful computational and numerical algorithms for control systems problems. In this paper a CAD language for control and Kalman filtering will be presented. The language, called CONTROL. lab is written in FORTRAN/77 and can run under UNIX or VMS on a DEC 11/780 VAX computer system.
The dynamic performance of computer-controlled manipulators is directly linked to the formulation of the dynamic model of manipulators and its corresponding control law. Several approaches are available in formulating...
详细信息
The dynamic performance of computer-controlled manipulators is directly linked to the formulation of the dynamic model of manipulators and its corresponding control law. Several approaches are available in formulating the dynamic models of mechanical manipulators and most notably of these are the Lagrange-Euler and the Newton-Euler formulations. This paper describes an efficient position plus derivative control in joint space for a PUMA robot arm whose dynamic equations of motion are formulated by the Newton-Euler method. The controller compensates the inertia loading, the nonlinear coupling reaction forces between joints and the gravity loading effects. Using a PDP 11-/45 computer the controller equation can be computed in 3 ms which is sufficient for real-time control. computer simulation of the performance of the control law is included for discussion.
The four-volume set LNCS 7724--7727 constitutes the thoroughly refereed post-conference proceedings of the 11th Asian Conference on computer Vision, ACCV 2012, held in Daejeon, Korea, in November 2012. The total of 22...
详细信息
ISBN:
(数字)9783642373312
ISBN:
(纸本)9783642373305
The four-volume set LNCS 7724--7727 constitutes the thoroughly refereed post-conference proceedings of the 11th Asian Conference on computer Vision, ACCV 2012, held in Daejeon, Korea, in November 2012.
The total of 226 contributions presented in these volumes was carefully reviewed and selected from 869 submissions. The papers are organized in topical sections on object detection, learning and matching; object recognition; feature, representation, and recognition; segmentation, grouping, and classification; image representation; image and video retrieval and medical image analysis; face and gesture analysis and recognition; optical flow and tracking; motion, tracking, and computational photography; video analysis and action recognition; shape reconstruction and optimization; shape from X and photometry; applications of computer vision; low-level vision and applications of computer vision.
This book and its sister volumes constitute the Proceedings of the Third International Symposium on Neural Networks (ISNN 2006) held in Chengdu in southwestern China during May 28–31, 2006. After a successful ISNN 20...
详细信息
ISBN:
(数字)9783540344407
ISBN:
(纸本)9783540344391
This book and its sister volumes constitute the Proceedings of the Third International Symposium on Neural Networks (ISNN 2006) held in Chengdu in southwestern China during May 28–31, 2006. After a successful ISNN 2004 in Dalian and ISNN 2005 in Chongqing, ISNN became a well-established series of conferences on neural computation in the region with growing popularity and improving quality. ISNN 2006 received 2472 submissions from authors in 43 countries and regions (mainland China, Hong Kong, Macao, Taiwan, South Korea, Japan, Singapore, Thailand, Malaysia, India, Pakistan, Iran, Qatar, Turkey, Greece, Romania, Lithuania, Slovakia, Poland, Finland, Norway, Sweden, Demark, Germany, France, Spain, Portugal, Belgium, Netherlands, UK, Ireland, Canada, USA, Mexico, Cuba, Venezuela, Brazil, Chile, Australia, New Zealand, South Africa, Nigeria, and Tunisia) across six continents (Asia, Europe, North America, South America, Africa, and Oceania). Based on rigorous reviews, 616 high-quality papers were selected for publication in the proceedings with the acceptance rate being less than 25%. The papers are organized in 27 cohesive sections covering all major topics of neural network research and development. In addition to the numerous contributed papers, ten distinguished scholars gave plenary speeches (Robert J. Marks II, Erkki Oja, Marios M. Polycarpou, Donald C. Wunsch II, Zongben Xu, and Bo Zhang) and tutorials (Walter J. Freeman, Derong Liu, Paul J. Werbos, and Jacek M. Zurada).
暂无评论