Robot, heal thyself

A paper on the website The Engineer describes an algorithm that allows robots to adapt to damage. It's titled, "Robots that can adapt like natural animals," by Antoine Cully, Jeff Clune and Jean-Baptiste Mouret.

The website: http://www.theengineer.co.uk

The article: http://www.theengineer.co.uk/Journals/2014/07/31/y/w/m/Adaptive_robotics.pdf

There is also a video on the site that shows an example of a robot adapting to damage, and continuing to walk afterward.

Video (3:48): http://www.theengineer.co.uk/video/robot-adapts-to-injury-and-continues-to-walk/1019019.article

There is no speaking and no sound, but there are words on the screen describing what is being shown - short and simple. This is certainly useful for lower-level students, since it is so clear and easy to understand. But it can also be used with higher-level students who can describe what is being shown (either in speaking or writing).

The article itself is not very useful for my students, since it is 23 pages long and written in an academic style. But the abstract can be useful for language work, and the innovation is very interesting.

The abstract:

"While animals can quickly adapt to a wide variety of injuries, current robots cannot 'think outside the box' to find a compensatory behavior when damaged: they are either limited to the contingency plans provided by their designers, or need many hours to search for suitable compensatory behaviors. We introduce an intelligent trial and error algorithm that allows robots to adapt to damage in less than 2 minutes, thanks to intuitions that they develop before their mission and experiments that they conduct to validate or invalidate them after damage. The result is a creative process that adapts to a variety of injuries, including damaged, broken, and missing legs.This new technique will enable more robust, effective, autonomous robots and suggests principles that animals may use to adapt to injury."

Although my students understood this text, they recognized that it was written in a rather formal, academic style. Students can identify these features of the text: vocabulary such as compensatory behavior, contingency plans, validate, invalidate, and enable; and grammar features such as passive voice and the use of compound and complex sentences (which my students refer to as "long sentences").

They can then work together to develop a simpler, more conversational version by imagining how they would describe this project to a non-technical friend.

One example that my students came up with:

"While animals can adapt when they get hurt or injured, robots can't figure out what to do when they're damaged. They have to either rely on their software programming or need a lot of time to figure out what to do. This algorithm lets robots adapt to damage in less than 2 minutes. They use a creative process to develop intuition before they have to do something and then they try out experiments to see what works after they're damaged. This algorithm can be used even when the robot's legs are damaged or broken. This will let robots be more independent, strong, and effective, just like animals that adjust to their injuries."

In addition to language work, my students enjoyed discussing this innovation and talking about features shown on the video.