[robocup-worldwide] CFP: Special session on Knowledge Representation and Reasoning in Robotics @ ICSR 2014

[Subramanian Ramamoorthy]

Special session on Knowledge Representation and Reasoning in Robotics
The International Conference on Social Robotics
October 27-29, 2014
Sydney, Australia



MOTIVATION:

Robots and agents deployed to interact and collaborate with humans in
homes, offices, and other domains, have to represent knowledge and
reason at both the sensorimotor level and the cognitive/semantic (or
social) level. This objective maps to the fundamental challenge of
representing, revising, and reasoning with qualitative and
quantitative descriptions of uncertainty and incomplete domain
knowledge obtained from sensors, humans, and other sources.  Although
many algorithms and architectures have been developed for knowledge
representation and reasoning, the research community is fragmented,
making it difficult for researchers with complementary expertise to
collaborate with each other. For instance, the rich body of research
in logical reasoning paradigms and qualitative representations
supports commonsense reasoning, encodes semantics such that they are
accessible to humans, and provides smaller state spaces for learning
and reasoning.  However such representations may not support
probabilistic analysis, whereas a lot of information available to
robots at the sensorimotor level is represented probabilistically to
quantitatively model the uncertainty in sensor input processing and
actuation.  On the other hand, the sophisticated algorithms based on
probabilistic graphical models that support quantitative modeling of
uncertainty, make it difficult to represent and reason with
commonsense knowledge.  Furthermore, algorithms developed to combine
logical and probabilistic reasoning do not provide the desired
expressiveness for commonsense reasoning and/or do not fully support
the uncertainty modeling capabilities required in robotics.

This special session seeks to bring together researchers from these
disparate communities, fostering an open discussion to promote a
deeper understanding and appreciation of recent breakthroughs and
tough challenges in the individual communities. We will build on the
workshops that have been organized on this theme, and on the broader
theme of bringing AI and robotics closer together. We hope that this
special session will encourage collaborative efforts towards
addressing the knowledge representation and reasoning challenges faced
by robots interacting and collaborating with humans.


TOPICS:

Topics of interest include (but are not limited to):
* Knowledge acquisition and representation.
* Combining symbolic and probabilistic representations.
* Reasoning about uncertainty.
* Reasoning with incomplete knowledge.
* Interactive and cooperative decision-making.
* Learning and symbol grounding.
* Planning and Robotics. 
* Commonsense reasoning.
* Cognitive architectures.

We are especially interested in papers describing efforts to integrate
different approaches for knowledge representation, reasoning and/or
learning on robots and agents. We also encourage papers that clearly
identify the need for such an integration in different application
domains such as health care, search and rescue, surveillance, and
smart homes.


FORMAT & SUBMISSIONS:

Papers submitted to this special session must follow the author
guidelines for ICSR. Please select the appropriate special session
during paper submission.

For more information, please see:
http://icsr2014.org/special-session.html


Paper submission: June 18, 2014
Notification: July 16, 2014


CHAIRS:

Mohan Sridharan, Texas Tech University
Subramanian Ramamoorthy, The University of Edinburgh
Vaishak Belle, University of Toronto


-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.