IEEE Robotics & Automation Magazine - December 2010 - 23

F R O M T H E

G U E S T E D I T O R S

State-of-the-Art in Robot Authentication
Marina L. Gavrilova (marina@cpsc.ucalgary.ca), University of Calgary, and Roman V. Yampolskiy (roman.yampolskiy@louisville.edu)

T

his special issue on robot authentication presents a collection of state-of-the-art articles reporting on the
unique aspects of secure authentication in robotics.
The issue concentrates specifically on automatic identification of artificial entities (robots, bots, and avatars) and the
complementary problem of human recognition by such
artificial agents.
There are numerous recent advancements in all aspects of
the development and deployment of advanced domestic and
industrial robots as well as artificial entities, such as intelligent
software agents and avatars. These developments have in turn
led to advanced research on program recognition, robot
behavior recognition, robot behavior prediction, robot detection, and robot self-recognition, as well as attempts to use biometric research for avatar and robot synthesis. This special
issue addresses a natural question of an automatic, fast, secure,
and accurate identification of artificial entities via contributions from robotics, as well as from biometrics, security, artificial intelligence, pattern recognition, cognitive science, and
virtual reality fields.
Domestic and industrial robots, intelligent software agents,
virtual world avatars, and other artificial entities are quickly
becoming a part of our everyday life. Just like it is necessary to
be able to accurately authenticate identity of human beings, it
is becoming essential to be able to determine the identity of
the nonbiological entities rapidly infiltrating all aspects of
modern society. Robotic museum guides, software office assistants, humanlike biped robots, office robots, domestic and
industrial androids, bots, virtual-world avatars, military robots,
and thousands of other man-made entities all have something
in common: a pressing need for a decentralized, affordable,
automatic, fast, secure, reliable, and accurate means of identity
authentication.
To address these concerns, the concept of artimetrics-a
field of study that will allow identification, classification, and
authentication of robots, software, and virtual reality agents-
was recently introduced by the editors of this special issue. As
research progresses, there is increasing evidence that the developed prototypes of the robots of tomorrow tend to resemble
humans and possess abilities of a human being, including
capacity to walk, speak, type, make decisions, and interact in
the real and virtual world. It is also likely that robot owners
might choose to customize their robot's appearance, just like
people frequently elect to customize their cell phones or computers, resulting in robots to be truly unique in appearance.
The feature that naturally lends itself to customization is the

face of a robot; in fact, celebrity look-alike and model robots
have already appeared. Thus, the need arises to ensure that
there is no security threat to people, property, and cyberinfrastructure-a goal achievable through a variety of newly introduced methodologies and techniques.
A promising new direction of research is to extend current
cognitive informatics and biometrics research focusing on
humans to a new generation of research algorithms for recognition of software and hardware robots. Recently, there have
been significant increases in a variety of biometric methods-
utilizing learning approaches (i.e., AdaBoost), advanced image
analysis [principal component analysis (PCA) and derivatives],
geometric pattern recognition (Voronoi diagram-based matching), and information fusion (rank, decision, and match score
level)-that can fairly successfully recognize human identities.
New research in the area of robots recognizing humans uses the

Digital Object Identifier 10.1109/MRA.2010.938838

DECEMBER 2010

IEEE Robotics & Automation Magazine

23
Table of Contents for the Digital Edition of IEEE Robotics & Automation Magazine - December 2010
