Researchers Teach Robots How To Fall Gracefully

Posted: Oct 15 2015, 7:54am CDT | by , Updated: Oct 15 2015, 10:33pm CDT, in News | Latest Science News


Researchers Teach Robots How to Fall Gracefully
Credit: DARPA Robotics Challenge

An algorithm has been developed to minimize the serious damage caused by falling.

When humans stumble and fall, they get into a ‘damage control’ kind of mode, meaning they have an ability to twist their arms or legs in such a manner that can prevent vulnerable parts of body from injuries as much as possible.

But robots lack this instinct or reflexes and they usually fall flat on their face. This kind of awkward fall can damage their components and disrupt mechanism as well.

To reduce this blunt impact, researchers from Georgia Institute of Technology have developed an algorithm, which will help robots in responding to falls and to control their movements.

“A fall can potentially cause detrimental damage to the robot and enormous cost to repair,” said Sehoon Ha, a PhD graduate, who developed the algorithm alongside Professor Karen Liu.

"We believe robots can learn how to fall safely. Our work unified existing research about how to teach robots to fall by giving them a tool to automatically determine the total number of contacts (how many hands shoved it, for example), the order of contacts, and the position and timing of those contacts. All of that impacts the potential of a fall and changes the robot's response."

The researchers tested the tool on robot called BioloidGP humanoid. The tool instructs robot how to react to different types of falls, produced by slight push to heavier push to extremely hard push.

The latest algorithm is based on the previous research which showed how cats modify their bodies while falling and land safely on their feet. The biggest challenge in here was that robots have stiffer bodies than cats and it was difficult to determine the angle which can result in desired softer landing.

"From previous work, we knew a robot had the computational know-how to achieve a softer landing, but it didn't have the hardware to move quickly enough like a cat," said professor Liu."Our new planning algorithm takes into account the hardware constraints and the capabilities of the robot, and suggests a sequence of contacts so the robot gradually can slow itself down."

Though, results are not up to the mark as of yet and falls are not as graceful as researchers probably would have liked but they are certainly heading towards a right direction.

Source: Georgia Tech

You May Like


The Author

Hira Bashir covers daily affairs around the world.




Leave a Comment

Share this Story

Follow Us
Follow I4U News on Twitter
Follow I4U News on Facebook

Read the Latest from I4U News