Physical Sciences and Mathematics Commons^™

Seaway: A Multi-Agent Decision-Support System For Naval Expeditionary Logistic Operations, Anthony Wood, Kym Jason Pohl, Justin Crawford, Mark Lai, John Fanshier, Ken Cudworth, Tom Tate, Hisham Assal, Shawn Pan, Jens G. Pohl

Collaborative Agent Design (CAD) Research Center

This report describes work performed by CDM Technologies Inc. in conjunction with the Collaborative Agent Design (CAD) Research Center of California Polytechnic State University (Cal Poly), San Luis Obispo, for the Office of Naval Research (ONR), on the SEAWAY experimental system for planning, gaming and executing maritime logistic operations from a sea base. SEAWAY incorporates three fundamental concepts that distinguish it from existing (i.e., legacy) command and control applications. First, it is a collaborative system in which computer-based agents assist human operators by monitoring, analyzing and reasoning about events in near real-time. Second, SEAWAY includes an ontological model of the …

Immaccs: An Experimental Multi-Agent C2 System, Jens G. Pohl, Anthony A. Wood, Kym Jason Pohl

Collaborative Agent Design (CAD) Research Center

The Integrated Marine Multi-Agent Command and Control System (IMMACCS) is a multi-agent, distributed software system, designed to provide a Common Tactical Picture (CTP) with integrated and meaningful decision-support facilities to authorized operators at any access node. IMMACCS has been implemented as a three-tier architecture that distinguishes between information, logic and presentation. It utilizes an object-serving communication facility with subscription and multi-casting capabilities that is based on the Common Object Request Broker Architecture (CORBA). With an emphasis on application, IMMACCS was designed and implemented in concert with its military users as an integral component of experiments conceived by the Marine Corps …

Semi-Regular Mesh Extraction From Volumes, Z. J. Wood, M. Desbrun, P. Schroder, D. Breen

Computer Science and Software Engineering

We present a novel method to extract iso-surfaces from distance volumes. It generates high quality semi-regular multiresolution meshes of arbitrary topology. Our technique proceeds in two stages. First, a very coarse mesh with guaranteed topology is extracted. Subsequently an iterative multi-scale force-based solver refines the initial mesh into a semi-regular mesh with geometrically adaptive sampling rate and good aspect ratio triangles. The coarse mesh extraction is performed using a new approach we call surface wavefront propagation. A set of discrete iso-distance ribbons are rapidly built and connected while respecting the topology of the iso-surface implied by the data. Subsequent multi-scale …

Robotic System Sensitivity To Neural Network Learning Rate: Theory, Simulation, And Experiments, Christopher M. Clark, James K. Mills

Computer Science and Software Engineering

Selection of neural network learning rates to obtain satisfactory performance from neural network controllers is a challenging problem. To assist in the selection of learning rates, this paper investigates robotic system sensitivity to neural network (NN) learning rate. The work reported here consists of experimental and simulation results. A neural network controller module, developed for the purpose of experimental evaluation of neural network controller performance of a CRS Robotics Corporation A460 robot, allows testing of NN controllers using real-time iterative learning. The A460 is equipped with a joint position proportional, integral, and derivative (PID) controller. The neural network module supplies …

Adapting To The Information Age, Jens G. Pohl

Collaborative Agent Design (CAD) Research Center

This paper draws attention to the profound changes that human civilization is experiencing as it moves from an industrial environment into an information environment, in which unprecedented emphasis is placed on the knowledge and capabilities of the individual. A clear distinction is drawn between data and information in relationship to computer-based facilities, and the transition of data-processing to the higher levels of information and knowledge representation in quasi intelligent decision-support systems. It is argued that the cultivation of its human capital becomes a foundational requirement for the success of a knowledge-based organization. In such an organization traditional practices of hierarchical, …

An Inference Engine-Based Subscription Service, Kym J. Pohl, Jens G. Pohl

Collaborative Agent Design (CAD) Research Center

A Distributed Network Architecture (DNA) forms the basis of many decision-support systems available today. Such architecture excels at providing an application environment rich in transparency, performance, and expandability (Gray and Lievano 1997). However, efforts at the Collaborative Agent Design (CAD) Research Center in San Luis Obispo, California have found that for this architecture to be successfully applied to agent-based, decision-support systems two additional ingredients must be present, namely a query service and a subscription service. These two mechanisms support the extensive collaboration inherent in agent-based, decision-support systems. Although primarily utilized as a means of agent-to-agent interaction these two services can …

Hybrid Probabilistic Programs, Alex Dekhtyar, V. S. Subrahmanian

Computer Science and Software Engineering

The precise probability of a compound event (e.g. e1 V e2,e1 Ʌ e2) depends upon the known relationships (e.g. independence, mutual exclusion, ignorance of any relationship, etc.) between the primitive events that constitute the compound event. To date, most research on probabilistic logic programming has assumed that we are ignorant of the relationship between primitive events. Likewise, most research in AI (e.g. Bayesian approaches) has assumed that primitive events are independent. In this paper, we propose a hybrid probabilistic logic programming language in which the user can explicitly associate, with any given probabilistic strategy, a conjunction and disjunction operator, and …

Proceedings Of The 2000 Onr Decision-Support Workshop Series: The Human-Computer Partnership In Decision-Support, Collaborative Agent Design Research Center

Collaborative Agent Design (CAD) Research Center

The Decision Support Workshop of May 2-4, 2000 held in San Luis Obispo, Cal., was the second in a series that was started one year earlier as a joint project of the Office of Naval Research and the Collaborative Agent Design Research Center of Cal Poly.

The goal of this series of Workshops is to provide a forum where connections can be established on one hand between developers and proponents of decision support tools, with potential users such as managers of large, complex organizations/systems on the other. Clearly, the military belong to this class of users and it is therefore …

Monitoring Of Distributed Processes With Mobile Agents, Ryan P. Kennedy, Franz J. Kurfess

Computer Science and Software Engineering

The proliferation of networked and distributed systems presents a need for more tool development with regard to the monitoring and maintenance of distributed processes. The goal of this paper is to present a mechanism used to collect detailed process information from various remote Unix hosts on a network. The interface to this mechanism, a GUI applet, is accessible through a Java enabled browser such as Netscape Navigator. It presents the user with a menu of choices such as which host to view, and what process information to retrieve (I/O-bound processes, numbers of processes, individual/total process usage, etc.). The requested information …

Branch Transition Rate: A New Metric For Improved Branch Classification Analysis, Michael Haungs, Phil Sallee, Matthew Farrens

Computer Science and Software Engineering

Recent studies have shown significantly improved branch prediction through the use of branch classification. By separating static branches into groups, or classes, with similar dynamic behavior, predictors may be selected that are best suited for each class. Previous methods have classified branches according to taken rate (or bias). We propose a new metric for branch classification: branch transition rate, which is defined as the number of times a branch changes direction between taken and not taken during execution. We show that transition rate is a more appropriate indicator of branch behavior than taken rate for determining predictor performance. When both …

Neural Networks And Structured Knowledge: Rule Extraction And Applications, Franz J. Kurfess

Computer Science and Software Engineering

As the second part of a special issue on "Neural Networks and Structured Knowledge," the contributions collected here concentrate on the extraction of knowledge, particularly in the form of rules, from neural networks, and on applications relying on the representation and processing of structured knowledge by neural networks. The transformation of the low-level internal representation in a neural network into higher-level knowledge or information that can be interpreted more easily by humans and integrated with symbol-oriented mechanisms is the subject of the first group of papers. The second group of papers uses specific applications as starting point, and describes approaches …

Instructional Design Agents – An Integration Of Artificial Intelligence And Educational Technology, Erika Rogers, Carol Scheftic, Emilio Passi, Sharon Lanaghan

Computer Science and Software Engineering

The purpose of this paper is to introduce a project whose goal is to design and develop a productivity tool which helps academic instructors in their course preparation. This tool will be composed of a number of “instructional design agents”, which combine techniques in human-computer interaction, artificial intelligence and educational theory. The first of these agents is based on Bloom’s Taxonomy, and a brief overview of this work in progress is presented.