|
|
Background:
People do not experience the world solely as an ordered sequence of events. The timing of our perceptions and behaviors has as much of an impact on our experiences as the nature of the events themselves. Yet many of the representations currently used to model human behavior do not incorporate explicit models of the temporal expression of these stimuli or actions. Dynamic behavior is often modeled sequentially in such a way that its temporal resolution is reduced and potential non-stationarity is ignored for the sake of computational efficiency (as in Markov state-based models of behavior), and/or causal mappings between observations and behavior are simplified to mitigate the sparseness of available datasets. Given that any artificial agent designed to interact with people will be dealing with intelligent partners with rich mental representations of time, are we using the appropriate representations?
The issue of timing can be even more critical when designing natural interactive social behaviors for robots or other synthetic characters. Human social behaviors are extremely dependent on a close feedback loop of simultaneous and coordinated activity between multiple interactors. Yet how to best represent these interdependencies and temporal relationships in order to produce interactive behaviors is just beginning to be explored and understood from a computational perspective. Speed, acceleration, tempo, and delay are concepts that AI and robotics researchers recognize as important in everything from motor control to verbal communication, but we do not yet possess a well-motivated framework for how these temporal considerations should be designed into our systems.
This workshop is oriented towards several different groups of researchers, including, but not limited to: computer scientists who use machine learning techniques to model human behavior, psychologists and neuroscientists who study social behavior, and designers of robots or computational artifacts that interact naturally with humans in real time. By bringing together members of these communities through a shared interest in temporal representations, our goal is to identify critical areas of study and promising techniques. Some of the central questions to be addressed are:
 | As researchers who study human interactive behavior, where do the common representations fall short? In what cases are they sufficient? |
| What representations should be developed or borrowed to better represent human behavior or deal with the challenges of interacting naturally with a person? |
| What do we know (e.g. from the social, cognitive, and behavioral sciences) about the timing of human behavior that we are not currently using? Which aspects of human behavior or social interaction are likely to be highly dependent on time? |
| What kinds of experiments in human-machine interaction could serve as testbeds (or eventually benchmarks) for the study of the role of timing? |
Submissions:
Papers on any aspect of modeling or studying the temporal aspects of human or human-machine social interaction are welcome. Interested participants may submit either full length papers (up to 6 pages in AAAI format) or short papers/extended abstracts (2 pages). Reports on experimental results, descriptions of implemented systems, and position papers are all welcome. Please email submissions to aaai10sstime@googlemail.com.
Schedule:
The symposium will take place over two and a half days from Monday through Wednesday, March 22-24, 2010 at Stanford University, California
Check back later for a detailed schedule.
Format:
This symposium will feature presentations (for long papers) and posters (for short papers) from accepted participants. Pending speaker availability, there will be invited talks or a panel discussion by experts from a variety of relevant fields.
Additionally, there will be break-out discussion sessions where members of special interest areas can discuss issues in greater depth and report their shared conclusions back to the symposium as a whole. Some potential breakout session topics are:
|
Nonverbal communication
|
|
Rhythmic or musical interaction
|
|
Spoken dialogue
|
|
Social decision-making
|
|
User state modeling
|
|
Interaction kinesics
|
If you would like to suggest a topic for a breakout discussion or express interest in one of the listed topics, please include this information with your submission or mail it separately to the official symposium email address, aaai10sstime@googlemail.com.
Timeline:
June 26
Submissions open
October 12
Submissions closed
November 6
Notification of acceptance/rejection
December 7
Registration open
February 5
Invited participant registration deadline
February 26
Final (open) registration deadline
Organizing Committee:
Frank Broz (University of Hertfordshire)
Marek Michalowski (Carnegie Mellon University)
Emily Mower (University of Southern California)
|
