We May Have Lost At Go, But We Still Stack Stones Better
Written by David Conrad   
Saturday, 03 June 2017

AI may have become the world's best placers of black and white stones on a grid, but when it comes to the art of stone stacking humans are still way ahead and there's the art to consider.

This year's ICRA IEEE International Conference on Robotics and Automation is a place to find the best demonstrations of robots doing intelligent things. 

Researchers from ETH Zurich have a particularly zen task for their robot arm - to stack stones. Given a few small stones, all the robot has to do is place one on top of the other to create a balanced pile. The stones provided are a little bit of a cheat in that they have been 3D scanned before the robot gets started and this allows it to make use of a physics model to see if a placement can balance. It is still a fairly tough assignment, however, as the robot has to pick a suitable stone and then place it on top of the previous one so that it balances. As the pile gets higher the task becomes increasingly difficult and errors of placement accumulate. Now watch the video:

 

 

Notice that the video is speeded up in most of the clips from x4 to x15. At its real speed it would be even more zen garden-like.

Now to move on to the human efforts in the same area.  To quote Wikipedia:

Rock balancing (or "stone stacking") is an art, discipline, or hobby in which rocks are naturally balanced on top of one another in various positions. Adhesives, wires, supports, or rings are not permitted.

 That is the literal definition, but now take a look at what it actually is:

 

 

It isn't really credible is it?

I would say that Michael Grab, the stone balancing artist in the video,  is in no danger of having his job taken by robots any time soon.

So AlphaGo you may have beaten the world's best Go players and be the champion of moving little black and white pebbles, but if the humans had changed the game to making the tallest stack, not to mention the most artistic, it would be game over for robots and a win for the humans.

 

rockstack

 

More Information

Autonomous Robotic Stone Stacking with Online next Best Object Target Pose Planning (pdf)

https://en.wikipedia.org/wiki/Rock_balancing

Related Articles

AlphaGo Triumphs In China

AlphaGo Revealed As Mystery Player On Winning Streak

Why AlphaGo Changes Everything

Robots Learn To Navigate Pedestrians 

 

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

 

 

Banner


Looking Forward To NAO 7
03/11/2024

Introduced to the world in 2004 by its creator Bruno Maisonnier the kid-sized, autonomous humanoid robot NAO, turns 20 this year. At less than 2 ft tall, it is small in stature, but plays a big r [ ... ]



JetBrains Improves Kubernetes Support In IDE Upgrades
12/11/2024

JetBrains has improved its IDEs with features to suggest the logical structure of code, to streamline the debugging experience for Kubernetes applications, and provide comprehensive cluster-wide Kuber [ ... ]


More News

 

espbook

 

Comments




or email your comment to: comments@i-programmer.info

 

Last Updated ( Saturday, 03 June 2017 )