Computing Reviews
Today's Issue Hot Topics Search Browse Recommended My Account Log In
Review Help
Search
Autonomous human-robot proxemics: socially aware navigation based on interaction potential
Mead R., Matarić M. Autonomous Robots41 (5):1189-1201,2017.Type:Article
Date Reviewed: Jun 21 2017

When humans interact, the interaction partners are expected to respect culture-defined interaction spaces, ranging from intimate over personal and social to public space. Social robots that interact with humans should be aware of these spaces by maintaining suitable physical distances and by engaging in appropriate behavior.

Proxemics examines human spatial behavior in social encounters; the authors employ it to create computational models of human-robot interaction (HRI). In addition to physical representations, based on inter-agent distance and orientation, and psychological representations, based on the inter-agent relationship, they focus on psychophysical representations concerned with social stimuli and develop a computational framework for psychophysical proxemics. Two main components are a reactive proxemic controller that minimizes the error for the distance and angle between the intended goal pose and the actual goal pose, and a proxemic trajectory planner to determine a path from the current to the target pose.

In an interaction scenario involving a human and a social robot, the model estimates the inter-agent pose (position and orientation of the agent), speech input and output levels, and gesture input and output levels. The parameters for this model are captured in a Bayesian network derived from data-driven models of human communication. The authors validate their model by calculating trajectories for the transitions involved in achieving a goal pose from a number of different starting poses. This allows social robots to engage in social interactions with humans that balance appropriate physical distance while maximizing the probability to recognize spoken language and body gestures. In experiments with a small set of human participants, a PR2 robot performed well in situations typical for interactions, but poorly when too far away, or when the human is out of the field of view. No unwanted robot hugs were reported.

Reviewer:  Franz Kurfess Review #: CR145363 (1708-0562)
Bookmark and Share
  Featured Reviewer  
 
Robotics (I.2.9 )
 
Would you recommend this review?
yes
no
Other reviews under "Robotics": Date
Movement problems for 2-dimensional linkages
Hopcroft J. (ed), Joseph D., Whitesides S. SIAM Journal on Computing 13(3): 610-629, 1984. Type: Article
Feb 1 1985
Robot motion planning with uncertainty in control and sensing
Latombe J. (ed), Lazanas A., Shekhar S. Artificial Intelligence 52(1): 1-47, 1991. Type: Article
Oct 1 1992
Dictionary of robot technology in four languages: English, German, French, Russian
Bürger E., Korzak G., Elsevier North-Holland, Inc., New York, NY, 1986. Type: Book (9789780444995193)
Mar 1 1988
more...

E-Mail This Printer-Friendly
Send Your Comments
Contact Us
Reproduction in whole or in part without permission is prohibited.   Copyright 1999-2024 ThinkLoud®
Terms of Use
| Privacy Policy