This conference proceedings volume contains 94 papers. The following topics are dealt with: hierarchical intelligent control;perception-representation-action triad;nonconventional cost functions;team decision making;s...
详细信息
ISBN:
(纸本)0818621087
This conference proceedings volume contains 94 papers. The following topics are dealt with: hierarchical intelligent control;perception-representation-action triad;nonconventional cost functions;team decision making;swarm intelligence;perceptual robotics;shape representation;shape extraction and analysis;active perception;acoustic perception;intelligent computing systems;knowledge representation for learning control;neurocontroller design;neural network applications;fault-tolerant control systems;noise identification in linear systems;evidential and fuzzy reasoning in intelligent control.
A program of research in robotics that seeks to encode abstract tasks in a form that simultaneously affords a control scheme for the torque-actuated dynamical systems, as well as a proof that the resulting closed-loop...
详细信息
ISBN:
(纸本)0818621087
A program of research in robotics that seeks to encode abstract tasks in a form that simultaneously affords a control scheme for the torque-actuated dynamical systems, as well as a proof that the resulting closed-loop behavior will correctly achieve the desired goals, is reviewed. Two different behaviors that require dexterity and might plausibly connote 'intelligence' -- navigating in a cluttered environment and juggling a number of otherwise freely falling objects -- are examined with regard to similarities in problem representation, method of solution, and causes of success. The central theme concerns the virtue of global stability mechanisms. At the planning level they lend autonomy, that is, freedom from dependence upon some 'higher' intelligence. They encourage the design of canonical procedures for model problems, which may then be instantiated in particular settings by a change of coordinates. The procedures developed result in provably autonomous behavior. Simulation results and physical experimental studies suggest the practicability of these methods.
A categorical model of problem solving is introduced. The concept is that domain-dependent knowledge can also take the form of structural knowledge about the domain and, more specifically, that the decomposition metho...
详细信息
ISBN:
(纸本)0818621087
A categorical model of problem solving is introduced. The concept is that domain-dependent knowledge can also take the form of structural knowledge about the domain and, more specifically, that the decomposition methods that have proved to be so effective in mathematical reasoning can also be applied in the case of artificial intelligence systems. The fact that such knowledge is superficially more arcane because of its abstract nature does not automatically indict it as being necessarily weak. It is shown that a number of algebraic approaches to problem solving can be incorporated into the viewpoint.
This volume of the proceedings contains 213 papers. The topics covered are mixed analog/digital design automation, high performance circuit layout, sigma delta conversion, computational methods for nonlinear circuits,...
详细信息
This volume of the proceedings contains 213 papers. The topics covered are mixed analog/digital design automation, high performance circuit layout, sigma delta conversion, computational methods for nonlinear circuits, chaos in nonlinear circuits, parallel signal processing on VLSI arrays, multidimensional systems and signal processing, neural networks, synthesis and logic minimization, continuous time integrated filters, mathematics of circuits and systems, digital filters, power system analysis, high definition TV, adaptive signal processing, analog digital integrated circuits, algebraic questions in circuits and systems, digital processing, nonlinear circuits and systems, robotics, microwave networks, and VLSI design.
Research activities in artificial intelligence at Saint Joseph's University are described. There has been significant progress in both basic research and system implementation in the last few years. The software d...
详细信息
ISBN:
(纸本)0818621087
Research activities in artificial intelligence at Saint Joseph's University are described. There has been significant progress in both basic research and system implementation in the last few years. The software developed pertains to search pruning for problem solving, learning from examples (similarity-based learning as it is often called), and explanation-based generalization and self-improving game-playing programs. The work on similarity-based learning can support the automatic formation of expert rules. All of this work is based on the basic research. Activities in the areas of the theory of problem solving, learning algorithms, and software development are described.
Sinhalese is the major language of Sri Lanka, spoken by 15 million people. A Sinhalese syntactic and semantic analysis system has been developed. Grammar rules for Sinhalese phrases, clauses and sentences are formaliz...
详细信息
ISBN:
(纸本)0818621087
Sinhalese is the major language of Sri Lanka, spoken by 15 million people. A Sinhalese syntactic and semantic analysis system has been developed. Grammar rules for Sinhalese phrases, clauses and sentences are formalized, and a Sinhalese dictionary with morphological, syntactic, and semantic features has been developed. The entries to the Sinhalese dictionary are connected to concepts in a conceptual dictionary based on English, Japanese, and Sinhalese.
The architectural features of digital signal processors (DSPs) that make them applicable to intelligent control are discussed. The impact of parallel features on numeric processing capabilities and efficient capabilit...
详细信息
ISBN:
(纸本)0818621087
The architectural features of digital signal processors (DSPs) that make them applicable to intelligent control are discussed. The impact of parallel features on numeric processing capabilities and efficient capabilities and efficient program execution is described. I/O and real-time features of DSPs are examined. The role of numerical computations in preprocessing vocal, visual and written input data in real-time AI systems is considered. The parallels between neural and DSP computations are illustrated. A node configuration for a virtually implemented neural network, based on commercially available DSP chip, is proposed.
The authors deal with the principal patch representation of visible surfaces in a scene, an algorithm for creating a stable surface model in this representation, and an algorithm for extending this model into subseque...
详细信息
ISBN:
(纸本)0818620617
The authors deal with the principal patch representation of visible surfaces in a scene, an algorithm for creating a stable surface model in this representation, and an algorithm for extending this model into subsequent views. The representation is based on the fact that the lines of minimum and maximum curvature on a generic smooth surface are orthogonal at almost every point. The mathematical literature provides a theorem that says that the principal patches can be created locally. An engineering solution is presented for creating global principal patch networks. By computing the lines of curvature from a range image, it will be possible to construct a mesh data structure and repatch the surface with tensor product surfaces that are virtually free of tensor product artifacts and allow application of intersurface continuity algorithms. The authors focus on the computational difficulties encountered in building a quadrilateral mesh based on integrated lines of curvature. Hyperbolic (negative Gaussian curvature) surfaces present few problems, but elliptic (positive Gaussian curvature) surfaces possess isolated umbilic points, i.e., singularities in their principal direction vector fields, which have presented some problems for the mesh growing algorithm. These are dealt with on a special case basis. After creating a mesh in one range image from one viewpoint, it is necessary to continue growing the mesh in range images obtained from adjacent viewpoints, sometimes called the scene merging or multiview integration problem. An algorithm for accomplishing this task is also described.
The author discusses the minimal entailment relation proposed by E. Sandewall (1989). It is argued that Sandewall's notion of entailment is well suited for prediction but is incapable of accounting for evidence co...
详细信息
ISBN:
(纸本)0818621087
The author discusses the minimal entailment relation proposed by E. Sandewall (1989). It is argued that Sandewall's notion of entailment is well suited for prediction but is incapable of accounting for evidence contradicting the predicted 'normal' course of events. The author does not describe a complete solution to this problem. However it is suggested that a solution has to be based on distinguishing between different purposes of the reasoning process, such as prediction or explanation. A problem solver must then make the assumptions underlying a particular mode of reasoning explicit in order to be able to reason about them and to retract them in the light of conflicting evidence. Sandewall's combination of logic and differential equations and its relevance to the area of intelligent control are described. The minimal entailment relation is introduced, and a problem with the logic when it comes to multiple modes of reasoning is presented. A solution based on mode assumptions is suggested.
The authors deal with the principal patch representation of visible surfaces in a scene, an algorithm for creating a stable surface model in this representation, and an algorithm for extending this model into subseque...
详细信息
The authors deal with the principal patch representation of visible surfaces in a scene, an algorithm for creating a stable surface model in this representation, and an algorithm for extending this model into subsequent views. The representation is based on the fact that the lines of minimum and maximum curvature on a generic smooth surface are orthogonal at almost every point. An engineering solution is presented for creating global principal patch networks. By computing the lines of curvature from a range image, it will be possible to construct a mesh data structure and repatch the surface with tensor product surfaces that are virtually free of tensor product artifacts and allow application of intersurface continuity algorithms. The authors focus on the computational difficulties encountered in building a quadrilateral mesh based on integrated lines of curvature.< >
暂无评论