Willow Garage Blog

I just want to point out that the robot's operating system is open-source and runs on heaps of different robot platforms: http://www.ros.org/ The software is primary developed by Willow Garage, a start-up created by an ex-Googler that also has Larry Page on its board: http://www.willowgarage.com/ You can actually simulate this specific robot and even write algorithms (in Python and C++ AFIAK) without having one: http://www.ros.org/wiki/pr2_simulator As you can probably tell, I really love how they're lowering the entry barrier for robotics programming!

That article had no real info at all! They haven't even confirmed with the company yet. The site (http://www.willowgarage.com) lists nothing relevant to this and nothing's on their blog. Did someone at ieee even confirm any of this before publishing? Edit... Just read again to try and find some more and this "multiple sources" business sounds an awful lot like that X-Surface debacle. I expected more.

I think Hackers will have the last laugh after all. When hackers finally build an AI, it will also be the first soul. An intelligent mind decoupled from a body and thus capable of being immortal. The first step in this direction was the stored program concept itself which was best articulated by Von Neumann (http://qss.stanford.edu/~godfrey/vonNeumann/vnedvac.pdf) and realized in the EDVAC. This allowed programs to be decoupled from hardware. Dennis Ritchie, whose loss we all mourn, made what I consider the second big step. Decoupling large software systems from hardware, via a portable operating system. It will take a while (10-20 years?), but maybe something like ROS (http://www.willowgarage.com/pages/software/ros-platform) will someday become a full mind that is still decoupled from any particular hardware...a soul!!!

Willow Garage (http://www.willowgarage.com/) has been doing tons of work with the kinect for all sorts of robotics use via their ROS platform, all BSD licensed. That'll provide the software/algorithms needed to get the camera integrated into neat robotics work. As for whether or not we'll see the kinect on Jarvis's next bung dropper, well, we may want slightly more hardened technology directing roboknives than the camera you set next to your TV so you can pet virtual kittens (this statement excludes anyone involved in Survival Research Labs). But the idea is there, sure.

FTA: "Buzzing you in when you get locked out, signing for a package, taking that frozen chicken out of the freezer while you’re at work, feeding your pet, and of course the veritable classic of robo-problems: getting you a beer." - imho these are terrible examples of what a robot could do... there are much simpler solutions for most of these problems than buying this: http://www.willowgarage.com/pages/pr2/overview

Reminds me of my own experience doing research in mobile robotics. It basically followed a cycle described pretty well by the the comic here: http://www.willowgarage.com/sites/default/files/blog/201004/willow_p1_…

Sure. There are quite a few. Here is a non-comprehensive list: http://www.bnrobotics.com/ http://www.resquared.com/ http://www.aethon.com/ http://www.redzone.com/ http://www.seegrid.com/ http://www.bostondynamics.com/ http://www.irobot.com/ http://www.cyphyworks.com/ <-- started by some of the original iRobot folks http://www.mobilerobots.com/ http://www.willowgarage.com/ http://www.evolution.com/ http://www.sensiblemachines.com/ http://astrobotictechnology.com/ ... etc ... NOTE: Some of the companies are further along than others but all of them (to the best of my knowledge) started as startups and/or university spin-outs (which is a subset of startups). You can normally find startup robotics companies near/around the schools with the best robotics programs (i.e. CMU, UPenn, Stanford, MIT, etc.)

Have you heard about Willow Garage? http://www.willowgarage.com/

Some smart robotics startups: MekaRobotics (by Aaron Edsinger, MIT star behind Domo) http://mekabot.com/ http://people.csail.mit.edu/edsinger/domo.htm Willow Garage (former early Google employee founder) http://www.willowgarage.com/ AnyBots (Trevor of YC's company) http://anybots.com/ Q Robotics (early stars from iRobot that liked startups so much, they needed to leave and start another once iRobot went public) http://qrobotics.com/ You don't really need to know anything about robots to work on them. The best groups are made up of specialists that understand a bit of everything, but are essentially software|hardware|electrical|systems engineers at their core.

I don't see how this will work in 3 years time. Cheap robots today (<100K) suck at manual dexterity tasks. It took quite a lot of work to get a PR2 to fold laundry (and some of the best robotics people in the world worked on this). The kinds of tasks I imagined Foxconn workers performed all require significant manual dexterity. For an amazing use of robots in a factory environment, I would suggest a tour of BMW's Munich factory. They have a whole bunch of specialized robotic arms that do things like welding, lifting, painting, etc. Their factory still employs humans (albeit fewer humans). In BMW's case, their use of robotics makes sense. Foxconn, not so much. Finally, there are some completely automated car factories. I thought Hyundai's US factory manufactured cars solely with robots. However, I believe they have a higher defect rate (partially due to this process). Edit: Link to the PR2 laundry folding robot - http://www.willowgarage.com/blog/2010/04/02/towels-uc-berkeley

This is a weak article. First, it ignores the existence of commodity robots. Something like 4 million Roombas have been sold. They are easy to use commodity robots that sell in volume from Best Buy. Second, many people, going back to the early 20th century, have imagined buying cheap general purpose robots, just as they have imagined buying jet packs and holidaying on space stations. Just because I imagine it doesn't make it feasible. The reason there aren't many autonomous-robot startups is that no one knows how to do the AI. It may make sense to you that you ought to be able to put together robots like you put together a spreadsheet, but that's not how it turned out to be. The article admits this, describing day to day tasks as "incredibly complex". Yet then asks us to imagine the cheap, capable robot. Third, the "mysterious" capital behind Willow Garage is Scott Hassan, an early and thus very rich Googler. It says so on the WG web page [http://www.willowgarage.com/pages/about-us/history]. Fourth, Microsoft has Robotics Studio, a package that competes with ROS in many respects. It is exactly a "robot operating system" on top of Windows. Researchers pretty much ignore Robot Studio, but why does this journalist do so when he says that "what we need Microsoft [...] to do is build an operating system....". It has been trying for years. Thanks for the advice, though. A low-quality piece for Spectrum, picked up from a blog.

It's not exactly encouraging to see, on the Willow Garage ROS website, that the page seems to have been last updated in 2013 (http://www.willowgarage.com/pages/software/ros-platform). You'll instead want to try http://www.ros.org/ or go directly to the installers, located at: http://wiki.ros.org/lunar/Installation However, the latest version (Lunar) on OSX is described "This is a work in progress! It really won't work right now... " and I've verified their instructions don't work. Instead, you'll want to use this shim: https://github.com/mikepurvis/ros-install-osx Hope this saves some folks time.

West Coast point of comparison: http://www.willowgarage.com/pages/about-us/history

Clothes sorting is being worked on and is fairly far along IMO. http://www.willowgarage.com/blog/2011/06/06/solving-laundry-uc-berkele…

This doesn't seem like it will do much to advance robotics in the private sector (wheels are fine). I'm more excited to see more results from the DARPA arm program (http://www.gizmag.com/irobot-darpa-autonomous-robotic-manipulation-pro… and the Velo gripper (https://willowgarage.com/velo2g).

Tully Foote has posted this on Willow Garage's blog: "Willow Garage has decided to enter the world of commercial opportunities with an eye to becoming a self-sustaining company. This is an important change to our funding model." http://www.willowgarage.com/blog/2013/02/11/willow-garage-changing

The one in Big Bang Theory is Texai from Willow Garage I think, http://www.willowgarage.com/pages/texai/overview and has been around from quite some time.

They used this one: http://www.willowgarage.com/pages/texai/overview (Competition coming soon https://www.suitabletech.com/ )

Solar airplane: http://solarimpulse.com/en/timestop/job-offer/ Space ship: http://www.spacex.com/careers.php Robots: http://www.willowgarage.com/pages/jobs We are hiring also: http://bu.mp/company/jobs

The people at Willow Garage think there is a market for this [1]. http://www.willowgarage.com/blog/2010/04/27/reinventing-wheel

There are also government and commercial jobs for research engineers that don't require a PhD. You play as second fiddle but you still get time to work on improving algorithms or coming up with your own. Willow Garage has a job opening that you might look at: http://www.willowgarage.com/jobs/research-engineer

I'd rather build one than become one. http://www.willowgarage.com/blog/2010/10/21/tum-rosie-and-pr2-james-ma…

Today Willow Garage announced that eleven (rather than the original ten anticipated) PR2 Beta robots, with a total value of over $4.4M, will be loaned out to academic and research institutions worldwide to develop a slew of impressive capabilities over the next two years. The recipients include 7 US-based institutions, 3 European, and 1 Asian. The final list is a panoply of robotics specialists: University of Freiburg (Germany), Bosch, Georgia Tech, KU Leuven (Belgium), MIT, Stanford, TU Munich (Germany), UC Berkeley, U Penn, USC, and University of Tokyo (Japan) -- full details can be found in the Willow Garage press release: http://www.willowgarage.com/blog/2010/05/04/pr2-beta-program-recipient…

As someone trying to convert/integrate Robotics research results into production code, I found this spot on. There is no real incentive for researchers to write decently structured/reusable code. There is another cartoon laying out WillowGarage's strategy to counter this effect (http://www.willowgarage.com/sites/default/files/blog/201004/willow_p2_… ) I am not entirely convinced, but an interesting read nonetheless.