Unconstrained spoken language is an intuitive and flexible way for
humans to command robots to perform spatial tasks such as navigation or
manipulation. Dialog (i.e., conversational) interfaces offer a rich way
to establish common ground between a person and a robot, and hence
facilitate natural and flexible interaction. This workshop specifically
aims to bring together communities studying robotics, natural language
understanding, spatial cognition, and perception to build powerful
spatial dialog systems for robots. We aim to bridge the gap between the
theoretical understanding and practical application of spatial language
understanding, create and discuss shared datasets and problems, and
define key research problems and challenges.
- Dialog interfaces for spatial reasoning tasks, such as navigation,
object finding, object manipulation and delivery.
- Challenges inherent to multi-modal interaction for commanding robots
with spatial semantics including speech, gesture and sketch.
- Interpreting and generating route instructions for spatial tasks.
- Learning meanings for spatial words such as “past, “on," “right," etc.
- Vision and other sensing modalities for grounding linguistic elements
such as places, objects, spatial relations, and verbs.
- Knowledge representations that support spatial reasoning.
- Descriptions of publicly available corpora that focuses on spatial tasks.
Submit your manuscript by email to [hidden email] with
“[RSS 2011 WORKSHOP]” in the subject line.
-- Important Dates --
Submit manuscripts by: May 16, 2011
Notification of acceptance/rejection: May 30, 2011
Final camera-ready papers deadline: June 6, 2011
The workshop: Friday, July 1, 2011
-- Organizers --
Thomas Kollar (Massachusetts Institute of Technology)
Stefanie Tellex (Massachusetts Institute of Technology)
Antoine Raux (Honda Research Institute)
Robert Ross (Dublin Institute of Technology)
Matthew Marge (Carnegie Mellon University)
robotics-worldwide mailing list
[hidden email] http://duerer.usc.edu/mailman/listinfo/robotics-worldwide