Abstract
Mobile robots, if they are to perform useful tasks and become accepted in open environments, must interact with humans. Robot response to humans at the most basic level means not injuring them directly or indirectly, e.g., treating humans as obstacles to be avoided in the performance of a task. Robots will be more useful if they can interact in more sophisticated ways. Here we identify a set of useful robot/human interaction modes: attending, taking advice, and tasking. All three involve complex sensing and planning operations on the part of the robot, including the use of visual tracking of humans, gesture recognition, and speech recognition and understanding. We show how these capabilities are integrated in the Saphira architecture on Flakey, a mobile robot testbed. We demonstrate a scenario in which an untrained supervisor is able to introduce Flakey to an office environment, and command it to perform delivery tasks.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
R. A. Brooks, A layered intelligent control system for a mobile robot, in: Proceedings of the IEEE Conference on Robotics and Automation (1986) 14–23.
M. Drumheller, Mobile robot localization using sonar, A. I. Memo 826, Massachusetts Institute of Technology (1985).
C. C. et. al., CARMEL versus FLAKEY: A comparision of two winners, AI Magazine 14 (1) (1993) 49–57.
M. P. Georgeff and F. F. Ingrand, Decision-making in an embedded reasoning system, in: Proceedings of the Conference of the American Association of Artificial Intelligence, Detroit, MI (1989) 972–978.
J. R. Hobbs, M. Stickel, D. Appelt, and P. Martin, Interpretation as abduction”, Artificial Intelligence 63 (1–2) (1993) 69–142.
J. Leonard, H. Durrant-Whyte, and I. J. Cox, Dynamic map building for an autonomous mobile robot, in: IROS (1990) 89–95.
Y. Lespérance and H. J. Levesque, Indexical knowledge and robot action — a logical account, Artificial Intelligence 73 (1–2) (February 1995).
R. C. Moore, Reasoning about knowledge and action, PhD thesis, Massachusetts Institute of Technology, Cambridge, MA (1980).
H. P. Moravec and A. E. Elfes, High resolution maps from wide angle sonar, in: Proceedings of the 1985 IEEE International Conference on Robotics and Automation, Washington, D. C. (1985) 116–121.
K. Myers and K. Konolige, Reasoning with analogical representations, in: B. Nebel, C. Rich, and W. Swartout, eds., Principles of Knowledge Representation and Reasoning: Proceedings of the Third International Conference (KR92), San Mateo, CA (Morgan Kaufmann, 1992).
S. J. Rosenschein, The synthesis of digital machines with provable epistemic properties, Technical Note 412, SRI Artificial Intelligence Center, Menlo Park, California (1987).
A. Saffiotti, E. H. Ruspini, and K. Konolige, Integrating reactivity and goal-directedness in a fuzzy controller, in: Procs. of the 2nd Fuzzy-IEEE Conference, San Francisco, CA (1993).
A. Saffiotti, E. H. Ruspini, and K. Konolige, A multivalued logic approach to integrating planning and control, SRI Tech Report 533, SRI International (1993).
R. Zabih and J. Woodfill, Non-parametric local transforms for computing visual correspondence, in: 3rd European Conf. Computer Vision, Stockholm (1994).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag London Limited
About this paper
Cite this paper
Konolige, K. (1997). Robots that take advice. In: Khatib, O., Salisbury, J.K. (eds) Experimental Robotics IV. Lecture Notes in Control and Information Sciences, vol 223. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035228
Download citation
DOI: https://doi.org/10.1007/BFb0035228
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76133-4
Online ISBN: 978-3-540-40942-7
eBook Packages: Springer Book Archive