Banner National Institute of Standards and Technology
ISD Research Area Banner
ISD home About ISD ISD Research Areas ISD's Products and Services What's New in ISD Search ISD

Research in Knowledge Representation for Autonomous Systems

a workshop in the

ACM Fourteenth Conference on Information and Knowledge Management (CIKM) 2005

November 5, 2005
Hilton Bremen
Bremen, Germany

Agenda
Background:

For an autonomous system to behave appropriately in an uncertain environment, many researchers and practitioners feel that the system must have an internal representation (world model) of what it feels and experiences as it perceives entities, events, and situations in the world. It must have an internal model that captures the richness of what it knows and learns, and a mechanism for computing values and priorities that enables it to decide what it wishes to do.

Autonomous systems in this context refer to embodied intelligent systems that can operate fairly independently from human supervision. A major challenge in autonomous systems is the ability to maintain an accurate internal representation of pertinent information about the environment in which it operates. The inability to do this well hinders effective task planning and execution.

A large body of work exists in various knowledge representation and ontology areas, yet relatively little has been applied to the area of world modeling in autonomous systems. The field of autonomous systems has reached a level of maturity such that it could greatly benefit from leveraging the work that has been on-going in these areas. World modeling in autonomous systems can also serve as a prime problem domain in which to apply theoretical and practical knowledge representation, ontological, and data fusion techniques.

For the purpose of this workshop, we are treating knowledge representation in a very all-encompassing manner to include the representation of parametric knowledge, spatial, temporal and iconic knowledge (including images and maps), symbolic knowledge (including ontologies), a priori and in situ knowledge, risk knowledge, value judgments, task knowledge, system knowledge, etc.

Return to top

Motivation and Objectives:

This workshop builds off of a highly successful symposium that was held as part of the 2004 AAAI Spring Symposium Series entitled “Knowledge Representation and Ontologies for Autonomous Systems.” This symposium was successful in bringing together colleagues in the autonomous systems, knowledge representation, ontology, and data fusion communities to jointly address the challenge of how to best leverage existing knowledge representation technologies to aid in the advancement of autonomous systems’ capabilities. There was much agreement among the symposium’s participants that this is a prime area for exploration and that the symposium should be the first in a series of related workshops.

The objective of this workshop is to bring together colleagues in the autonomous systems, knowledge representations, ontology, and data fusion communities to find ways of leveraging existing knowledge technologies to benefit autonomous systems. This workshop will be unique in that is will be driven by the needs of the robotics community, namely, presentations will focus on the knowledge representation needs of robotic researchers and practitioners along with approaches that have been both successful and unsuccessful at addressing those needs.

Return to top

List of Major Topics Covered:

This workshop aims to bring together colleagues in the autonomous systems and knowledge technology communities in order to:

  • Understanding what work is currently ongoing in developing knowledge representations and ontologies for autonomous systems
  • Applying knowledge representations to autonomous systems for representing parametric, spatial, temporal, dynamic and symbolic knowledge
  • Exploring the usefulness of different types of ontologies for autonomous systems
  • Understanding and formalizing the interaction between disparate knowledge representations (e.g., images, maps, classes, and relationships) that provide complementary information about the same object or event (including establishing real-time links between symbolic and iconic knowledge).
  • Exploring the issue of symbol grounding, where symbols in the world model are grounded to the physical reality of the external world.
  • Representing a priori and in situ knowledge, risk knowledge, value judgments, state information, history, plans, entities, events, situations, intent, task knowledge, and self-knowledge
  • Exploring which knowledge technologies work best for different challenges in autonomous systems, including corresponding performance measures
  • Exploring the requirements that subsystems (e.g., sensors, learning modules, planners, and operator control units) place on knowledge
  • Understanding the role of knowledge in model-based perception and control
  • Exploring approaches to formalize the autonomous system’s internal representation
  • Exploring means to measure of the quality of knowledge within autonomous systems
  • Exploring the reusability of knowledge among disparate autonomous systems
  • Determining how data fusion technologies (which support autonomous system sensing capabilities) can be assisted by using knowledge technologies
  • Understanding the interplay between quantitative knowledge originating from sensors and qualitative knowledge used at higher knowledge levels
Organizer:

Craig Schlenoff
National Institute of Standards and Technology
100 Bureau Drive, Stop 8230
Gaithersburg, MD 20899-8230
craig.schlenoff@nist.gov

Stephen Balakirsky, NIST
National Institute of Standards and Technology
100 Bureau Drive, Stop 8230
Gaithersburg, MD 20899-8230
stephen@nist.gov

Return to top

Submission Information:

The workshop will consist of paper presentations describing current research or visionary approaches, as well as discussion sessions. Those interested in participating should submit a full paper (5000 words maximum) outlining their relevant research activities in PDF format to kr@cme.nist.gov.

Return to top

Important Dates:

Deadline for Paper Submission: July 15, 2005
Acceptance Notification: July 31, 2005
Camera-Ready Copies Due: August 24, 2005
Workshop: November 5, 2005

Return to top

Important Links:

Get Adobe Acrobat Reader

isd-webmaster@cme.nist.gov
Date Created: May 17, 2005
Last updated: May 24, 2005

 

 
Manufacturing Engineering Laboratory Skip navigation