I'm now on Twitter @ KellyCommaRoy This originated on 4chan.

Jimmy Wales Wikipedia mickymebia pickamebia bickiebeebia bickabebia personal appeal from jimmy wales preathe weed

Project was led by UC Berkeley Ph.D. student Jeremy Maitin-Shepard working with Professor Pieter Abbeel. The video is shown at 50X speed. More details can be found in the paper at www.cs.berkeley.edu

robot autonomous deformable object manipulation towel folding laundry university california berkeley aritifical intelligence AI machine learning uc pr2 willow garage maitin-shepard abbeel

Project was led by UC Berkeley Ph.D. student Jeremy Maitin-Shepard working with Professor Pieter Abbeel. The video is shown at 30X speed. More details can be found in the paper at www.cs.berkeley.edu

robot autonomous deformable object manipulation towel folding laundry university california berkeley aritifical intelligence AI machine learning pr2 willow garage maitin-shepard abbeel

Footage of some preliminary results obtained at UC Berkeley which were compiled for Willow Garage's One-Minute PR2 Quick Start Video Contest. The PR2 is presented with two socks. It then classifies each sock as either "inside" or "outside" and flips accordingly. Once both socks are in the proper orientation, it pairs them. Team: Ping Chuan (Ted) Wang, Stephen Miller, Mario Fritz, Trevor Darrell, Pieter Abbeel.

pr2 willow garage folding robot robotics socks abbeel berkeley

The Berkeley PR2 autonomously pairs socks. This includes: identifying inside-out socks, folding, matching, and bunching them together. This work was done by Ping Chuan Wang, Stephen Miller, Mario Fritz, Trevor Darrell, and Pieter Abbeel, at the University of California, Berkeley. Video shown at 15x speed. Details may be found in the paper at www.cs.berkeley.edu

pr2 folding deformable object manipulation laundry pairing socks university california berkeley willow garage ping chuan wang stephen miller mario fritz pieter abbeel trevor darrell

Professor Abbeel steps through the elimination of a single variable in variable elimination.

UC Berkeley cs188 variable elimination intro to AI Pieter Abbeel

Professor Abbeel steps through a couple of examples of maximum likelihood estimation.

UC Berkeley cs188 Intro to AI Pieter Abbeel maximum likelihood

Footage of some preliminary results obtained at UC Berkeley which were compiled for Willow Garage's One-Minute PR2 Quick Start Video Contest. The PR2 picks up a towel from an unknown configuration and proceeds to fold it. When it is unsure which corner would be best to grasp, it polls Twitter for advice. In return, once it has finished the procedure, it posts a photo of the folded towel. To interact with the PR2 and assist it in future demos, follow now at twitter.com Team: Stephen Miller, Mario Fritz, Marco Cusumano-Towner, Pieter Abbeel.

pr2 folding robot autonomous towel willow garage twitter berkeley abbeel

Professor Pieter Abbeel leads a team of researchers exploring artificial intelligence in pursuit of eliminating tedious tasks.

ashley morgan mari rosas reena flores robot robots pieter abbeel pr2 willow garage steve cousins rosie the robot the jetsons research cal brett eecs computer science artificial intelligence surgery uc berkeley caltv cal tv

Professor Abbeel steps through a couple of examples on Laplace smoothing.

UC Berkeley cs188 Intro to AI Pieter Abbeel Laplace smoothing

Need a little extra help getting the laundry done? Robotics engineers at University of California at Berkeley have developed a robot that can fold towels and socks. SmartPlanet talks to Berkeley Professor Pieter Abbeel and his student Stephen Miller about the technology behind their laundry-folding robot.

11s0110 domesticrobots 264 CNET 18 11

A team of UC-Berkeley researchers has programmed a robot to do something brand new -- fold towels! They've overcome a major challenge in robotics, which is programming robots to manipulate flexible objects that change shape. Professor Pieter Abbeel and his team developed novel computer vision and manipulation algorithms that enable their robot, PR2, to reliably find the corners of the towels so it can fold them. See how they did it in this episode of Innovation Nation with Miles O'Brien.

NSF National Science Foundation Innovation nation Science technology innovation robots Berkeley research robotics laundry UC-Berkeley Science Channel

Pieter Abbeel has programmed robots to learn how to perform tasks without detailed instructions. One robot can fold laundry, while others can fly model helicopters or tie sutures.

youtube

Prof. Abbeel steps through two examples of variable elimination.

Bayes nets variable elimination cs188 uc berkeley

Perception for the Manipulation of Socks - Ping Chuan Wang, Stephen Miller, Mario Fritz, Trevor Darrell, Pieter Abbeel. Presented at IROS 2011 More information can be found at rll.berkeley.edu

manipulation socks PR2 robots sockification

EG-RRT: Environment-Guided Random Trees for Kinodynamic Motion Planning with Uncertainty and Obstacles - Leonard Jaillet, Judy Hoffman, Jur van den Berg, Pieter Abbeel, Josep M. Porta, Ken Golberg. Presented at IROS 2011

robots motion planning rrt random forest environment uncertainty dynamics constraints obstacles

Prof. Abbeel steps through the execution of d-separation for a few example Bayes' nets.

cs188 UC Berkeley D-separation Bayes' nets conditional independence

Prof. Abbeel steps through sampling examples. Apologies for the weird background beat caused by some microphone issues.

bayes nets sampling cs188 uc berkeley

In this episode we report back on all the shred/alcohol fuelled mayhem from the WBB BBQ shred, we had in our back garden last weekend. a long edit but enjoyable. Stay tuned for more episode from Angus, Scotty and the rest of the WBB crew. (main song UNKLE- Hold my Hand)

Angus Leith Scott Penman Helen Fox Connor Carey Dom Harington Joe Power Dec Power Simon Cudlip Katie Blundell Cody Hierons Will Radula-Scott Richie Logan Charlie Rowland Karlien Abbeel Emilia Vanni wbb wee breck bastards bbq shred fun silly drunk party snowboard stunts tricks

[ICRA2010: Berg, Miller, Duckworth, Hu, Wan, Fu, Goldberg and Abbeel] Learning knot-tying from demonstrations.

robot surgical learning demonstrations knot knot-tie knot-tying tying UC Berkeley Berkeley robotics

Prof. Abbeel steps through the execution of value iteration. This is the first question of assignment 5.

Screencast-O-Matic.com

UC Berkeley PR2 Robot Folds Laundry In 2010, the Berkeley PR2 (unofficially named Brett, for "Berkeley Robot for the Elimination of Tedious Tasks") showed us that it could pick a towel out of a pile of clean laundry one by one and neatly fold and stack them, which was an impressive demo. Somewhat less impressive was the fact that the robot would take between 20 and 25 minutes to neatly fold one single towel, which, let's face it, isn't entirely practical. That time has now been cut down to under six minutes, with the potential for as little as two minutes per towel if they really crank the robot up. The key to robots is in advances in Artificial Intelligence (AI). A limiting factor in developing a useful and practical robot is that current robots can only do what their programming tells them. You can program a robot to fold a shirt, but if you throw in a shirt with buttons on the opposite side, the robot may not be able to fold the shirt. If you program a robot to bake a cake, there is little chance the robot can make lasagna without specific programming. The PR2 doesn't rely on such discreet programming. Rather, it reduces the dependence on a complex vision system and instead relying on gravity and the properties of cloth. The PR2 now just picks up a towel wherever is convenient and then drags it across a folding table, knowing that as it does, the piece of the towel furthest away from the gripping point must necessarily be a corner. What do you all think? Is this a big <b>...</b>

Robot AI Artificial intelligence Laundry

can this hits 10 likes ? :D

ul

todos contra el gobierno yeah by submarco

00064632651

Simple hover visualization using flightgear and the R22 model of a RC helicopter using LQR control as part of 16-899 class at CMU. Model by Peter Abbeel. Check out heli.stanford.edu for a real helicopter doing similar tricks.

helicopter simulation RC LQR control flightgear matlab