Path: EDN Asia >> News Centre >> Industrial/Mil/Aero >> Smart algorithm allows robot to adapt to damage
Industrial/Mil/Aero Share print

Smart algorithm allows robot to adapt to damage

24 Aug 2015  | Amy Norcross

Share this page with your friends

Scientists from Pierre and Marie Curie University (PMCU) in Paris and from the University of Wyoming (UW) have developed a new type of robot that quickly adapts to injury or damage.

Researchers Antoine Cully, Danesh Tarapore and Jean-Baptiste Mouret, from PMCU, and Jeff Clune, from UW, describe an "intelligent trial-and-error algorithm that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans."

They claim experiments with robots employing this algorithm have been successful in determining adaptations for a robot with legs injured in five different ways, including damaged, broken and missing legs, and for a robotic arm with joints broken in 14 different ways.

The study was published in the journal Nature.

Quickly adapting robot

(Source: Antoine Cully/Pierre and Marie Curie University)

"When injured, animals do not start learning from scratch," senior author Jean-Baptiste Mouret said in a statement. "Instead, they have intuitions about different ways to behave. These intuitions allow them to intelligently select a few different behaviours to try out and, after these tests, they choose one that works in spite of the injury. We made robots that can do the same."

Before the robot is deployed, it uses a computer simulation of itself to create a detailed map of the space of high-performing behaviours. This map represents the robot's "intuitions" about different behaviours it can perform and their predicted value.

According to the study's lead author, Antoine Cully, "These maps can be quite large. In our experiments with the six-legged robot, the map contained over 13,000 gaits." If the robot becomes damaged, although it does not do any diagnosis or repair itself, it can use these intuitions to guide a learning algorithm that conducts experiments to quickly find a way to compensate.

"Once damaged, the robot becomes like a scientist," explained Cully. "It has prior expectations about different behaviours that might work and begins testing them. However, these predictions come from the simulated, undamaged robot. It has to find out which of them work, not only in reality but also given the damage.

"What's surprising," he added, "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 video below shows a hexapod robot that adapts and is able to keep walking even with two broken legs, and a robotic arm that "learns" how to correctly place an object even with several damaged motors.

Additional applications for the algorithm in "healthy" robots include adapting to different terrain or developing new behaviours for unforeseen situations.

"It could enable the creation of robots that can help rescuers without requiring their continuous attention," said study co-author Danesh Tarapore. "It also makes easier the creation of personal robotic assistants that can continue to be helpful even when a part is broken."

Want to more of this to be delivered to you for FREE?

Subscribe to EDN Asia alerts and receive the latest design ideas and product news in your inbox.

Got to make sure you're not a robot. Please enter the code displayed on the right.

Time to activate your subscription - it's easy!

We have sent an activate request to your registerd e-email. Simply click on the link to activate your subscription.

We're doing this to protect your privacy and ensure you successfully receive your e-mail alerts.

Add New Comment
Visitor (To avoid code verification, simply login or register with us. It is fast and free!)
*Verify code:
Tech Impact

Regional Roundup
Control this smart glass with the blink of an eye
K-Glass 2 detects users' eye movements to point the cursor to recognise computer icons or objects in the Internet, and uses winks for commands. The researchers call this interface the "i-Mouse."

GlobalFoundries extends grants to Singapore students
ARM, Tencent Games team up to improve mobile gaming

News | Products | Design Features | Regional Roundup | Tech Impact