Robot Waiters Serving Dinner in Thailand
Uploaded on Jun 14, 2010
At Thailand's most original Japanese restaurant, the service is fast, friendly and extremely efficient - that's because two high-tech robots do most of the work. (June 14)
Cookie Perfection Machine
Published on Jan 11, 2014
This machine allows me to mix a single cookie and vary the recipe for each cookie on the sheet. Hence, I can test many different recipe variations with one batch of ingredients in one afternoon.
A1 concepts Let's Pizza
Published on May 2, 2012
A1 concepts is proud to introduce an innovative pizza machine which makes it possible to create an authentic pizza, made with only fresh ingredients from scratch into a delicious pizza. 24/7 And in less than 2,5 minutes.
PR2 robot clears dinner table - Stanford University
Uploaded on Dec 13, 2011
This project was done by Abhishek Sharma, Bharath Bhat and Rohan Kamath at the AI Lab, Stanford University in Autumn 2011.
In this project we use a Microsoft Kinect sensor mounted on top of the PR2 robot (Willow Garage Inc.) to obtain RGB and depth images of table top objects. Further, the algorithm
attempts to recognize general dining table objects and locate their positions. Finally, we make the robot pick up the objects and place them in separate boxes based on their type.
We would like to express our gratitude to Ellen Klingbeil and Samir Menon from the Stanford AI Lab for their help and guidance during the project.
Robot Learns to Flip Pancakes
Uploaded on Jul 26, 2010
Pancake day special!
The video shows a Barrett WAM robot learning to flip pancakes by reinforcement learning. The motion is encoded in a mixture of basis force fields through an extension of Dynamic Movement Primitives (DMP) that represents the synergies across the different variables through stiffness matrices. An Inverse Dynamics controller with variable stiffness is used for reproduction.
For pancake day special, the skill is first demonstrated via kinesthetic teaching, and then refined by Policy learning by Weighting Exploration with the Returns (PoWER) algorithm. After 50 trials, the robot learns that the first part of the task requires a stiff behavior to throw the pancake in the air, while the second part requires the hand to be compliant in order to catch the pancake without having it bounced off the pan.
Социальные закладки