PARC-HRI 2013 - Probabilistic Approaches for Robot Control in HRI

Sociable robots "in the wild" must quickly and accurately make decisions to produce appropriate social behaviors in human-robot interactions (HRI). To do this, a robot must reason over natural human communication mechanisms, such as speech, gesture, attention, and other body language. These multimodal data are inherently noisy and complex. Probabilistic techniques have been successfully applied to the modeling of these types of data. Such approaches have also demonstrated their utility in traditional robotics applications, including mapping, localization, navigation, manipulation, and higher-level planning.
The objective of this half day workshop is to discuss the application of probabilistic approaches to further enable robot autonomy in HRI, as well as address the shortcomings and necessary improvements in current techniques needed for robust socially intelligent behavior. This workshop will investigate the use of probabilistic approaches, such as Bayesian networks and Markov models, for robust robot control and decision-making under uncertainty. Target applications range from social behavior primitives?such as gesture, eye gaze, and spacing?to higher-level interaction planning and management systems.
Topics
Under the focus of probabilistic approaches to sociable robot control, the workshop invites submissions describing original work, either completed or still in progress, related to one or more of the following topics:
Social content and behavior planning
Behavior realization and control for sociable robots
Models for natural communication dynamics
Knowledge-based and data-driven approaches to social behavior understanding
Numeric representations of human state
Online learning and user adaptation
Situatedness within social/environmental contexts
Interaction frameworks and architectures for human-robot interaction
Submissions
Workshop contributions should be submitted via e-mail to hri2013ws.parc-AT-gmail.com .
If a submission exceeds 10MB, the file should be made available online and a URL for download should be provided.
Submitted papers should be 4-6 pages in length in PDF format, and should conform to the IEEE publication guidelines. For templates and examples, follow the link:
http://www.ieee.org/conferences_events/conferences....