~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The Raelian Movement
for those who are not afraid of the future : http://www.rael.org
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Deceptive robots hint at machine self-awareness
http://www.newscientist.com/article/mg20727794.800-deceptive-robots-hint-at-machine-selfawareness.html?full=true
22 September 2010 by Celeste Biever
Video: Robot deception
A robot that tricks its opponent in a game of hide and seek is a step
towards machines that can intuit our thoughts, intentions and feelings
ROVIO the robotic car is creating a decoy. It trundles forward and
knocks over a marker pen stood on its end. The pen is positioned along
the path to a hiding place - but Rovio doesn't hide there. It sneaks
away and conceals itself elsewhere.
When a second Rovio arrives, it sees the felled pen and assumes that
its prey must have passed this way. It rolls onwards, but is soon
disappointed.
The behaviour of the deceptive Rovio represents something much more
significant than a crude game of robot hide-and-seek. It is a
demonstration of an aspect of social intelligence known as theory of
mind, which humans only develop around the age of 4 or 5. If robots
can be made to display theory of mind in other situations, it could
endow them with a sophisticated intelligence. They might then be able
to reason the thoughts, intentions and even feelings of people and
other robots.
"It was definitely exciting to see it work," says Alan Wagner of the
Georgia Institute of Technology in Atlanta, who programmed Rovio with
colleague Ron Arkin. "We have expanded the boundary of understanding
deception and how deception relates to artificial systems."
The defining feature of theory of mind is the ability to model the
beliefs and intentions of others as distinct to one's own. Robots have
previously hinted at this ability by performing a variety of mental
tricks (see "Becoming aware").
Deception, though, is definite progress. It requires not only the
modelling of a distinct mind but also the ability to anticipate and
manipulate the actions of others. "A deceiving agent knows what the
other agent knows and intends to change what the other agent knows,"
says Liane Young, a cognitive scientist at the Massachusetts Institute
of Technology.
To demonstrate artificial deception, Wagner and Arkin recruited two
Rovio robots, made by WowWee in Hong Kong, for a game of
hide-and-seek. Before the game, the robots were released to learn
about the game environment and the effect of their own actions on it.
The environment featured three adjacent hiding places. On the path
leading towards each of these hidey-holes, the researchers placed a
marker pen stood on its end (see diagram).
Programmed to learn, the first thing seeker Rovio did was move into
one of the caches, knocking the pen over on its way. The pen was reset
and the robot repeated the process, 10 times in all. Using a
combination of its camera and probabilistic software, it learned to
associate fallen pen and hiding place.
Hider Rovio came to the same conclusions as it explored the
environment, but crucially, it had been given the ability to learn how
to send a false signal.
The game then began. Hider Rovio's learned knowledge allowed it to
predict what seeker Rovio would do in the same situation. It
calculated that knocking over a pen and sneaking elsewhere would fool
its seeker. "It uses its own model of itself to determine how best to
deceive the other individual," says Wagner.
In 15 of the 20 times the game was played, the seeker chose the wrong
corridor (International Journal of Social Robotics, DOI:
10.1007/s12369-010-0073-8).
However, many researchers point out that it is unsurprising that the
deceiving robot should succeed, given the extent of its
pre-programming. "It seems to me the theory of mind is in the
experimenter, not the robot," says Sara Mitri, a roboticist and
evolutionary biologist at Harvard University. "It's like it's staged;
[the robot] is like a puppet rather than a child."
In 2009, Mitri was part of a team at the Swiss Federal Institute of
Technology in Lausanne (EPFL) which created basic robots that evolved
the ability to discourage other robots from accessing a common, finite
"food" source, without being programmed to do so (Proceedings of the
National Academy of Sciences, DOI: 10.1073/pnas.0903152106).
Wagner acknowledges that the robots are pre-programmed, but emphasises
that each one learns on its own. "It would learn how its movement
affected the markers, which told it basically how to deceive," he
says.
Raúl Arrabales, who researches machine consciousness at the Carlos III
University of Madrid in Spain, agrees. "It is actually an
implementation of theory of mind, because it is using the learning
mechanism to update the model of the [opponent] or its own model." He
notes, however, that the robot can't transfer the knowledge
autonomously to another situation. "It is not like a human, it is
something in between," he says.
Humans have a generalised concept of deception, which wasn't
demonstrated by these robots. "It was implemented on a very specific
task, for a very particular interaction," says Kevin Gold, an AI
researcher at the Rochester Institute of Technology in New York state.
"It's a far cry from human theory of mind because it is so specific to
the task."
Yet Gold acknowledges that it is a step in the right direction. "It
provides a kind of outline for things that would be fleshed out in a
more general system," he says. "There is real stuff under the hood
going on here."
Already, Wagner and Arkin have implemented a more complicated version
of the hide-and-seek game in a software-only simulation. In this
version, the software deceiver can tailor how it deceives its opponent
depending on what particular sensors it discovers its opponent has -
some have audio, others vision, others infrared. This extends the
degree to which the deceiver reasons about its opponent's abilities.
By introducing games where cooperation brings benefits or penalties,
the deceiver can also be programmed to decide whether or not it is
worthwhile to fool its opponent, by judging what kind of task it is.
Wagner hopes to develop the deception software to help robots become
more human-like in their interactions with us, for example, by
enhancing a machine's ability to reason about a person's likes,
dislikes or other emotions. "It's a springboard to reasoning about all
kinds of other things," he says. "We want a robot that could interact
with people in any kind of situation."
Using deception is a springboard to robots reasoning about all kinds
of other things
Could such a robot ever make moral decisions? "I think moral judgement
is reserved for conscious agents," says Young. "However, if robots are
able to compute intentions, actions and outcomes, then in a sense
robots may be able to deliver the moral judgements of others."
Exploring robot theory of mind in these ways could even tell us
something about ourselves, Young says. "Any computational code that
supports the external behavioural properties of theory of mind and
deception can help us understand what's going on in the human mind."
"Ethics" is simply a last-gasp attempt by deist conservatives and
orthodox dogmatics to keep humanity in ignorance and obscurantism,
through the well tried fermentation of fear, the fear of science and
new technologies.
There is nothing glorious about what our ancestors call history,
it is simply a succession of mistakes, intolerances and violations.
On the contrary, let us embrace Science and the new technologies
unfettered, for it is these which will liberate mankind from the
myth of god, and free us from our age old fears, from disease,
death and the sweat of labour.
Rael
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-----------------------------------------------------------------
Tell your friends who love scientific news that they can
subscribe to this list !!
They can do it by sending a blank email to:
rael-science-select-subscribe@yahoogroups.com
It's free !
-----------------------------------------------------------------
To unsubscribe, send an email to:
rael-science-select-unsubscribe@yahoogroups.com
-----------------------------------------------------------------
To change your e-mail address, unsubscribe from the old address and subscribe from the new address (see above).
-----------------------------------------------------------------
No comments:
Post a Comment