|
| |
DR. JOSH BONGARD
The Scientific American article
Resilient Robot Hobbles Along, Even if Injured:
New four-legged machine can assess damage to its body and adapt its
gait accordingly said
When a person stubs his toe, he compensates by favoring his other leg.
More dramatically, if he loses use of both his legs, he can still crawl
to get from point A to point B. Now a robot shaped like a four-legged
starfish can do the same. Designed at Cornell University, the
nine-piece device can advance toward a goal even after incurring
damage. In a paper published in this week's Science, the researchers
describe the algorithm by which this mechanical beast can assess its
own condition.
"The main advance here was not just the diagnosis and recovery, but how
the robot does that, which is to build a model of itself," explains
Josh Bongard, a computer scientist now at the University of Vermont. In
the past, robots attempting to recover from damage would have attempted
upward of hundreds of thousands of movements in an inefficient
trial-and-error process designed to overcome injury. But if these
robots are to become "the next generation of planetary rovers," Bongard
points out, "you can't assume that this robot can perform hundreds of
thousands of trials. It may damage itself further or fall off a cliff."
So, Bongard, along with his colleagues Victor Zykov and Hod Lipson,
programmed their robot to carefully select its actions so that it makes
as few movements as possible.
Dr.
Josh Bongard
is
Assistant Professor,
Department of Computer Science,
University of Vermont.
He was co-organizer:
"The 50th Anniversary Summit of Artificial
Intelligence:
Trends and Challenges in the 21st
Century", Monte Verita, Switzerland.
He is a reviewer for
Artificial Life,
Adaptive Behavior,
IEEE Transactions on Evolutionary Computation, and
IEEE Transactions on Systems, Man, and Cybernetics.
How could the body influence our thinking when it
seems obvious that
the brain controls the body?
In
How the Body Shapes the Way We Think: A New View of
Intelligence, coauthored by Josh,
with a foreword by Rodney Brooks,
he
demonstrates that thought
is not
independent of the body but is tightly constrained, and at the same
time enabled, by it. He shows that the kinds of thoughts we are
capable of have their foundation in our embodiment in our
morphology
and the material properties of our bodies.
Josh authored
Evolving Modular Genetic Regulatory Networks and
Evolved Sensor Fusion and Dissociation in an Embodied Agent
and
coauthored
Coevolutionary strategy for structural damage identification using
minimal physical testing,
New Robotics: Design Principles for Intelligent Systems,
Evolving Complete Agents Using Artificial Ontogeny,
Reinventing the Wheel: Experiments in Evolutionary Geometry,
The Road Less Travelled: Morphology in the Optimization of Biped
Robot
Locomotion,
and
"Managed Challenge" Alleviates Disengagement in Co-evolutionary
System
Identification.
Read a
full list of his publications!
He earned a BSc Honors, Computer Science Summa Cum Laude from
McMaster University, Hamilton, Canada in 1997. He earned a MSc,
Evolutionary and Adaptive Systems Graduated with Distinction,
University of Sussex, Brighton, United Kingdom,
Cognitive and Computing Sciences Graduate Research Centre in 1999.
He earned a PhD for "Incremental Approaches to the Combined Evolution
of a Robot's Body and
Brain", University of Zürich, Zürich, Switzerland,
Department of Information Technology,
Artificial Intelligence Laboratory,
Software Engineering Group,
Combined Doctoral appointment in 2003.
Watch the
Windows Media Player or
Quicktime video of his resilient robot in action!
Watch
videos related to his
Automated Damage Diagnosis and Recovery for Remote Robotics
paper.
Read
"Self-aware" space rovers would be speedy explorers.
Josh is looking for people interested in helping to explore the nature
of
aesthetic preference: how and why do people like one object more than
another? If you are interested, please download the
ZIP file
(Windows version only), unzip it to a directory, double-click on
instructions.txt in that directory, and get involved in scientific
discovery!
Print bio!
|
|