putting out forest fires to grabbing you a cup of coffee, robots have the
potential to be hugely beneficial to humans. The problem, however, is that they
seem to fall apart when they’re injured.
people or animals get hurt, they can usually compensate for minor injuries and
keep limping along, but for robots, even slight damage can make them stumble
and fall. Now a robot scarcely larger than a human hand has demonstrated a
novel ability: It can recover from damage an innovation that could make robots
on Wednesday said they had created a small robot that can recover from damage,
in a step toward machines that mimic the remarkable adaptive powers of humans
and animals. The feat could one day lead to first-responder robots which can
cope with dangers that today would put them out of operation, they said.
idea is to have robots that can survive in hostile environments such as a
Fukushima-type nuclear disaster,” said Jean-Baptiste Mouret of the Pierre and
Marie Curie University in Paris. “If we send in robots, they have to be able to
pursue their mission even if they are damaged, and not just come to a halt in
the middle of a reactor.”
robot can automatically learn to keep walking even when it is damaged.
credit: UPMC/Antoine Cully)
research, published in the journal Nature, is inspired by the learning
abilities of the natural world. If a dog hurts its paw, for instance, it will
seek to move differently to avoid putting pressure on the painful wound. The
adaptive skill comes from experience — from knowing how the body moves and
exploring the options that are available.
is what Mouret’s team sought to replicate in a powerful computer program to
guide a six-legged 50-centimeter (20-inch) walking robot. The core of the
program is to build a knowledge base for the robot of how it moves, and to
assign to each of these movements a “value” as to how useful they could be in a
crisis. The “values” are rather like intuition. In the case of the injured dog,
the animal knows that to walk again, it has to learn how to shift its weight
around. Behaviors such as sniffing or wagging its tail are rejected at this
time because they will not help.
“values” are then used to guide a learning algorithm, called Intelligent Trial
and Error, which conducts experiments to see if compensatory behavior will help
the robot to continue its mission even when damaged. Using it, the prototype
robot found a way to keep walking after just a couple of minutes, even when two
of its legs had been broken. “If one behavior doesn’t work, the robot is smart
enough to rule out that entire type of behavior and try a new type,” said
Mouret’s colleague, Antoine Cully.
example, if walking mostly on its hind legs does not work well, it will next
try walking mostly on its front legs. “What’s surprising is how quickly it can
learn a new way to walk. It’s amazing to watch a robot go from crippled and
flailing around to efficiently limping away in about two minutes.” The team
also used the program on a flexible robotic arm which was tasked with dropping
a ball into a bin. The limb swiftly learned ways of carrying on with its
mission, even when several of its “joints” were broken. (Credit: AFP)