Go back to Table of Contents.
Maria Gini
We would like to solicit nominations for the following SIGMAN positions (current position holders are listed in parentheses):
Officers must be members of AAAI during their terms of office.
INDUSTRIAL CO-CHAIR (normally a full-time employee of a commercial
corporation): duties shall include organizing and conducting the
yearly business meeting, representing SIGMAN to the AAAI parent
(the senior current CO-CHAIRPERSON shall be designated as the
"AAAI Liaison"), promoting interaction between SIGMAN and other
bodies, supporting the organization and execution of workshops,
and assuring interaction between the sub-areas of SIGMAN.
MEMBER-AT-LARGE; duties shall include actively identifying
problems of interest to the members, organizing workshops and
other activities, and promoting cooperation among experts and
practitioners in AI and Manufacturing.
BENCHMARK SECRETARY: duties shall include actively promoting the
definition of problems, description of solutions, and evaluation of
implementations by the SIGMAN membership, and maintaining these
definitions, descriptions, and evaluations, in machine readable and
transmittable form when possible. (NOTE: These activities should
in no way be construed as involving "standardization" of any kind,
and no member is required to use the benchmarks.)
Please send nominations by October 31, 2000.
You should include contact information (e-mail and phone number)
and a few lines of credentials for each nominee. The elections
will be conducted by email or (snail) mail in November/December.
More information about SIGMAN can be found on the SIGMAN Web page
at http://sigman.cs.umn.edu/.
You can subscribe to the SIGMAN
mailing list by sending a message to
sigman-request@cs.umn.edu
with the word "subscribe" in the body.
Thank you for your cooperation. We are looking forward to another
year of exciting activities.
Maria Gini
Newsletter Secretary, SIGMAN
The AAAI SIGMAN organization represents a wide array of researchers addressing fundamental scientific problems that arise in engineering design and manufacturing. The human endeavor that is design and manufacturing is rich in basic problems for researchers in Artificial Intelligence. From process planning researchers who aim to augment the abilities of human process engineers, to those who employ agents and distributed AI to model and control the factory floor---AI has found one of its most fertile and challenging proving grounds in the manufacture of products.
The idea for this AAAI SIGMAN-sponsored Special Issue of the Journal of Artificial Intelligence in Engineering Design, Analysis and Manufacturing grew out of SIGMAN's "AI in Manufacturing" workshops held in Albuquerque, New Mexico 1996 and 1998. The goal of the issue was to identify a representative selection of papers from the academic and industrial AI research community providing a cross-section of the recent advances in the integration of AI and manufacturing. The selection of papers in this issue includes contributions in core areas of AI and Manufacturing: Knowledge Representation (Schlenoff et al.), Computer-Aided Design and Analysis (Yang and Marefat), Process Planning (Nau et al, Gaines et al., Sticklen et al), Agents and Shop-Floor Control (Barber et al.). This collection of papers is representative of the highly interdisciplinary nature of research on AI in Manufacturing. Manufacturing continues to be a premiere proving ground for AI, with real-world problems that hard to represent and combinatorially brutal on our best algorithms. Researchers in these areas often find they produce deep research insights that advance both AI and manufacturing sciences. I, and SIGMAN, are proud to provide a representative sample of recent results in this special issue.
Special thanks for making this issue possible goes to Leslie Cumiford (Chair of the 1996 and 1998 workshops), as well as to the rest of the AAAI SIGMAN executive committee (Maria Gini, Dana Nau, Steve Smith). AAAI SIGMAN also thanks its membership as well as its financial sponsors: the National Science Foundation, National Institute of Standards and Technology, Defense Advanced Research Projects Agency and the United States Department of Energy. We also extend our thanks to Bill Birmingham and the AI-EDAM editorial board for their vigorous support of this issue and AAAI SIGMAN.
List of Papers:
Go back to Table of Contents.
Modern enterprise systems support highly specialized, concurrent task
planning and decision making,
integrating enterprise-wide business functions with
flexible manufacturing systems. They are
implemented on automated systems with
(often world-wide) distributed architectures on heterogeneous
operating systems and hardware platforms from different vendors. To ensure
coherence in problem solving and decision making, enterprise systems
require new concepts for integrating geographically dispersed activities.
Object Orientation has shown to be an effective paradigm capable of
managing the development complexity of modern automation systems.
This special issue is intended to publish contributions on models, methods,
tools, and results in the design of software architectures for distributed
control systems with their applications to robotics and factory
automation. The emphasis will be on new advanced techniques and
methodologies grown in the realm of the object-oriented paradigm:
Object-Oriented enterprise application frameworks (Enterprise Framework for
short), design patterns and pattern languages, distributed objects, mobile
objects and intelligent agents.
Deadline for submission: 1 February 2001
For additional information, look at the
Call for Papers.
Special Issue on Multi-Robot Systems
of the Transactions on Robotics and Automation.
Guest Editors: Tamio Arai, Enrico Pagello, Lynne Parker
Several new robotics application areas, such as underwater and space
exploration, hazardous environments, service robotics in both public and
private domains, the entertainment field, etc., can benefit from the use
of multi-robot systems. In these challenging application domains, multi-robot
systems can often deal with tasks that are difficult, if not impossible, to
be accomplished by an individual robot. A team of robots may provide
redundancy and contribute cooperatively to solve the assigned
task, or they may perform the assigned task in a more reliable, faster, or
cheaper way beyond what is possible with single robots.
Research work in multi-robot systems has progressed significantly in
recent years. Issues that have
been studied are diverse, and include cooperative motion
planning, formation-keeping, cooperation
among two or more mobile manipulators,
architectures for distributed control,
influence of both differentiating and integrating animal societies on
cooperating robot teams, decisional aspects for execution control,
learning techniques for collective robotics, and so on.
Deadline for submission: 15 March 2001
For additional information, look at the
Call for Papers.
Data Mining for Design and Manufacturing: Methods and Applications will be
published by Kluwer Academic Publishers. The book is a volume in a series
called "Massive Computing" that is organized by James Abello (AT&T Labs
Research), Panos Pardalos (Univ. of Florida) and Mauricio Resende (AT&T
Labs Research). The book is especially important since it will bring
together the latest research and practice on the relationship between data
mining and design and manufacturing environments.
Data Mining for Design and Manufacturing: Methods and Applications will
bring together the latest research and practice on the relationship
between data mining and design and manufacturing environments. Topics
include data warehouses, marts, process, tasks, (e.g., association,
clustering, classification, forecast), methods (e.g., statistics, decision
trees and rules, neural networks, fuzzy learning, and case-based
reasoning); machine learning in design (e.g., knowledge acquisition,
learning in analogical design, conceptual design, and learning for design
reuse); data mining for product development and concurrent
engineering; design and manufacturing warehousing; computer-integrated
manufacturing (CIM) and data mining; data mining for Material Requirements
Planning (MRP); Enterprise Resource Planning (ERP) and Workflow
Management; process and quality control; process analysis; data
representation/visualization; fault diagnosis; adaptive schedulers; and
learning in robotics. The contributors will include leading researchers
and practitioners from academia and industry.
Data Mining is defined as the process of extracting valid, previously
unknown, comprehensible information from large databases in order to
improve and optimize business decisions. Data mining methods have been
used in various industrial fields, and have led to a broad range of
research efforts. Powerful computerized integrated design and
manufacturing tools (such as CAD, CAM, MRP and ERP) for collecting and
managing data are in use in virtually all mid-range and large
manufacturing companies. Over time, more and more product development,
design, operation, and performance data are accumulated and computerized
during product design and manufacturing processes. The abundance of data
generated and collected during daily operations has impeded the ability to
extract useful knowledge. In design and manufacturing environments, this
situation calls for new techniques and tools that can intelligently and
(semi)automatically turn low-level data into high-level and useful
knowledge.
The first of its kind, the objective of this book is to demonstrate the
potential of data mining in design and manufacturing environments. The
book provides an explanation of how data mining technology can be employed
beyond prediction and modeling, and how to overcome several central
problems in design and manufacturing environments. Practitioners can gain
insight on how data mining is integrated with standard CAD/CAM, MRP, and
ERP Systems. The book also presents the formal tools required to extract
valuable information from design and manufacturing data (e.g., patterns,
trends, associations, and dependencies), and thus facilitates
interdisciplinary problem solving and optimizes design and manufacturing
decisions.
Go back to Table of Contents.
Go back to Table of Contents.