Impromptu teams

Download Report

Transcript Impromptu teams

Impromptu Teams of
Heterogeneous
Mobile Robots
Ross Mead
Dr. Jerry B. Weinberg
Introduction

Following the World Trade Center attacks,
teams of mobile robots were called to
Ground Zero to aid in finding victims.

This marks the first time in history that
robots were used in a real search and
rescue environment.
Introduction

The small size of these machines
granted them the ability to
investigate places where workers
could not go.

Rescuers were able to perceive
and communicate with victims…
 using
visual and audio sensors
Introduction

Participating teams came
from different organizations
across the country…
 had

not previously met
Robots were heterogeneous
 varied
in shape, size, and
functionality
Introduction

Based on their abilities, robot teams were
assigned particular objectives…
 Hazardous
materials
 Medical
 Logistics
 Planning
 Search-and-rescue
Introduction

Despite this delegation, did not demonstrate teamwork.

The overall goal was the same…


The robots were only aware of their own assigned tasks.
Missions were carried out individually, and were limited
solely to the abilities of that robot…

A failure of a single unit would greatly hinder the completion of
the overall search and rescue operation.
Introduction

How can these robots, which have never interacted,
collaborate to accomplish a joint objective?

How can abilities, internal knowledge, perceptual
experiences, and tasks be uniformly represented and
understood by all members of an impromptu robot team?


composed of independent agents each unknown to the others
Once this information is obtained, how can robots
reorganize and delegate individual and joint objectives,
based on individual abilities and limitations?
Background

A homogeneous team of robots
has been used in a search and
rescue environment.
 Tejada

et al. (2003)
Impromptu teams have been
applied to the RoboCup robotic
soccer league.
 Bowling
et al. (2005)
Background

A theoretical foundation for teamwork
among mobile robots has been provided.
 Cohen

et al. (1991)
A multi-layered approach to
heterogeneous teams has been discussed
and implemented.
 Balch
et al. (2002)
Background

symbol grounding problem
 in
artificial intelligence (AI), the representation of
internal knowledge and how it is meaningfully
interpreted as concepts in the physical world

Three levels of knowledge representation:
– physically similar to what it represents
 indexical – links between icons
 symbolic – provides a relationship between icons,
indices, and other symbols
 iconic
Goals/Objectives

If heterogeneous robots are to organize and
work together as an impromptu team, a
language must be developed that allows them to
share knowledge in a meaningful way.

For consistent interpretation of communicated
knowledge within a team, symbols representing
the knowledge must be grounded in concepts...
 refer
to categories of entities in an environment
Goals/Objectives

Symbolic communication protocol based
upon the Semantic Web…
 extension
of World Wide Web
 gives information well-defined meaning

relates to the corresponding entity in the real world
Goals/Objectives
Goals/Objectives

Information is presented in a structured form…


similar to a descriptive sentence
<subject> <predicate> <object>

By enforcing this strict syntax, robot attributes can be
broken down and related to the traits of others.

This structure can easily be interpreted by both
computers and people…

simple to edit, search, and communicate
Goals/Objectives

Based on the characteristics of XML…
 language

used to program the Semantic Web
XML is able to encode metadata…
 information

about the information
XML is extensible.
Goals/Objectives

XML is designed so that new tags can be
defined that describe new concepts and
categories of information…
 can

be shared with others searching for information
The communication protocol would be layered
beneath a robot’s own independent program…
 provide
meaning to symbols relating to itself and
other robots in its immediate area.
Goals/Objectives

A task management system is needed to
complete individual and joint goals.

The team must consider the individual abilities,
limitations, costs, and rewards of each robot to
delegate tasks and coordinate activities
appropriately…
 must
be tolerant of communication failure and
dysfunctional teammates
Procedures

The robot coordination system will initially be
implemented and tested in simulation in PyRo.
 programming
environment for different types of robots
 specifics of actuators and sensors are abstracted


program can be shared across different platforms
ultimate tool for heterogeneous robot code portability
Procedures

This project will be developed within the
framework of the Department of Computer
Science (CS) Senior Assignment.
 The
target task will be the American
Association for Artificial Intelligence (AAAI)
Robot Scavenger Hunt Challenge.
Procedures

A robotic system to search the
Engineering Building for a list of
objects will be developed…
 working

with senior CS students
Code must be portable and list of
objectives must be easy to modify
 working
with three ActivMedia robots
Elmer,
Taz, Marvin
Procedures

Working alongside the scavenger hunt project, I
will be developing the robot coordination system.

The scavenger hunt is, in many ways, analogous
to urban search and rescue…
a
successful implementation of the system will show
proof-of-concept of impromptu teams in a search and
rescue environment
References

S. Westphal (2001). “Robots join search and rescue
teams”, New Scientist (Online) 19 September 2001.
09 March 2006.
http://www.newscientist.com/article.ns?id=dn1321

P. Cohen & H. Levesque (1991) “Teamwork,” Nous
25:11—24

R. Murphy (2004) “Human-Robot Interaction in
Rescue Robotics,” IEEE Systems, Man and
Cybernetics Part C: Applications and Reviews,
special issue on Human-Robot Interaction, Vol. 34,
No. 2, May 2004.

T. Balch & L. Parker (2002) Robot Teams: From
Diversity to Polymorphism, A K Peters, Ltd., Natick,
Massachusetts.

M. Bowling & P. McCracken (2005) “Coordination
and Adaptation in Impromptu Teams,” In the
Proceedings of AAAI-05.

Harnad, S. (2003) The Symbol Grounding Problem,
Encyclopedia of Cognitive Science, Nature
Publishing Group/Macmillan.

S. Tejada, A. Cristina, P. Goodwyne, E. Normand,
R. O’Hara, & S. Tarapore (2003) “Virtual Synergy: A
Human-Robot Interface for Urban Search and
Rescue”. In the Proceedings of the AAAI 2003
Robot Competition, Acapulco, Mexico.

R. Daviddson (1993) “A Framework for Organization
and Representation of Concept Knowledge in
Autonomous Agents,” In Scandinavian Conference
of Artificial Intelligence—93, IOS Press.

Semantic Web. Ed. Eric Miller, et al. 8 March 2006.
W3C. 11 March 2006. http://www.w3.org/2001/sw/
Questions?