Under development at Willow Garage is a new ROS stack for PR2 that will allow it to completely calibrate itself. According to the Willow Garage blog, “you can start the process before lunch, and by the time you get back, there’s a nicely calibrated robot ready to go.” Robots, for all their charms, tend to rely fairly heavily on being well calibrated… If you’ve ever programmed a humanoid hobby robot, you’re probably familiar with the necessity to “zero” out the servos just about every time you use the thing lest it immediately throw itself to the ground in protest when you try to get it to walk.

It’s not just that calibration is relatively tedious and time consuming, it’s that you need to repeat it over and over again, which is a waste of time in that you’re not actively improving the functionality of the bot. What’s that you say? Something is inefficient and needs to be repeated over and over? That’s just the type of thing that screams “automate me!” to programmers, which is why a calibration stack will be included in a future ROS release. Eventually, the calibration stack will hopefully mature to the point where self calibration can be applied to just about any type of robot running ROS.

[ Willow Garage ]

When we first saw PR2 Alpha plugging itself into a standard wall socket last year, it was a sort of hit and miss behavior where the robot would stab at the outlet a bunch of times until it actually made a connection. As they say in the video, this is a “sub-optimal” behavior. I commented at the time that:

This is one of those situations where developing a robot that’s able to plug into a socket 20% of the time (but try over and over) is (I imagine) much more efficient than developing a robot that’s able to plug into a socket 100% of the time.

Now, I’m not sure whether I’m exactly wrong about my assertion… There are many significant hardware differences between PR2 Alpha and the PR2 in the above video, and undoubtedly a lot of programming was necessary for the one-shot plug-in. This stuff is a big investment of time and money. As a programmer myself, I totally understand how when something is sub-optimal, you want to optimize, and the improved behavior is certainly beneficial to PR2. However, my question is (still) whether the amount of resources invested in getting PR2 to hit that outlet 100% of the time is really worth it when a much lower percentage of success is still perfectly adequate when it comes to getting the robot to charge itself.

Either way, optimal is optimal, and the same library of behaviors that allow PR2 to plug itself in which such accuracy and precision will certainly come in handy when it tries to do other stuff, like tying my shoelaces for me ’cause I’m too lazy to bend over.

[ Willow Garage ]

Willow Garage has been putting together a whole assemblage of PR2 robots, and they want to give you one to play with. For free. All you have to do is convince them that you (and your institution) will be using the PR2 to accelerate robotics research and drive open source robotics development. It’s that simple!

If you want to get your brand new PR2 to do much of anything, a good way to go about that might be ROS, or Robot Operating System. ROS 1.0, aka Box Turtle (cute!), is the very first non-beta release of Willow Garage’s open source Robot Operating System. ROS has the potential to be huge, if it becomes what it’s trying to become, which is a way for people to share code between different robot platforms. So, instead of having to write your own code to control (say) a gripper, you can just download a ROS package that will do it for you, which will integrate with other robotics software frameworks. On the other side of things, if you write some totally awesome code to control a gripper, other people can use your totally awesome code on their robots too. Basically, the idea behind ROS is to keep people from having to reinvent the wheel over and over again for each new robot, so that people can spend their time improving the wheel and inventing the hoverpad, as it were.

If it catches on, this could be great. I’m not saying MS-DOS great, but still great.

[ PR2 ]
[ ROS Introduction ]

If we ever find ourselves with our own household robots, they’re going to need to be able to learn from us, because there will be all kinds of wild and crazy stuff that we want our robots to be able to do that the robot designers won’t have thought of. So, the ability to teach robots new tasks is rather important. But even more important is teaching robots to generalize one thing or task and apply it to many different variations on that thing or task. Back in September, we wrote about an ASIMO that learned to generalize different types of objects: show it a chair, and ASIMO could figure out what other objects were chair-like.

PR2 has taken this concept of generalization a step further by applying it to actions, not just things. When you teach PR2 an action (by providing an example of the action), PR2 can understand the fundamental components of the action and apply them to different variations of the action. So like, if you teach PR2 to pour a beverage out of a can into a cup, it then doesn’t matter what kind of can or what kind of cup or where they are relative to each other or if you move them around in the middle. This is hugely, hugely important for robots to be able to do, because having to teach a robot an action for “pour from can into cup on counter” and then a separate action for “pour from can into cup on low table” isn’t just tedious, it’s one of those things that is going to keep anyone from wanting to be involved with the robot at all.

There are a lot of major obstacles to surmount when it comes to creating a robot that can be practical and useful around people who know nothing about robots… From stuff like plugging into a normal outlet to recharge to not squeezing things too hard. It’s awesome to see Willow Garage and PR2 tackling these critical objectives and finding solutions that work.

[ Willow Garage ]

Remember this cute little “need power” animation of Willow Garage’s PR2? It’s part of a series of simulations that Willow Garage has put together to try and figure out which behaviors work best (i.e. are most intuitively understandable) when it comes to interacting with humans, and they need you to help them do the figuring. There are a series of eight different concept animations of PR2 interacting with people that they’d like you to watch and describe, and the data will be used to help make PR2 more human-readable… It’s online, it only takes 10 or 20 minutes, and it’s kinda fun. Click here to participate in the study.

[ Willow Garage ]

This is Intel’s research robot, named Marvin. Marvin has just learned how to plug himself into a standard wall outlet, a feat that duplicates the skills of Willow Garage’s PR2. What’s interesting to me is how these two robots use substantially different techniques to complete the same task. After Marvin locates a power socket, his arm makes a series of passes along the wall with a sensor to locate the exact location of the outlet and then plugs himself in in one shot. Now that this proof of concept has been tested successfully, Intel plans to add more sensors to allow the robot to plug itself in without having to go through the whole raster scanning routine.

PR2, on the other hand, uses a brute force approach. It locates the general location of an outlet, and then stabs blindly (sort of blindly) until it gets lucky and makes a connection. Now, it’s easy to say that the Marvin is better at connecting to outlets than PR2 is because, well, that’s true. But arguably, PR2 is more efficient than Marvin. It doesn’t need a single dedicated plug sensor, let alone an entire array. That’s less upfront expense, less integration, less programming, and fewer things to break. Yeah, it takes a little longer, but the robot isn’t in a rush, and it’s not like you’re waiting around… It’s an autonomous system, and hypothetically, you’ll just never have to worry about it.

[ Intel Labs Seattle ] VIA [ Gizmodo ]

Willow Garage has Jorge Cham of PhD Comics doing a series of panels for them entitled simply “R.O.B.O.T. Comics.” Your guess is as good as mine as to what R.O.B.O.T. stands for, but each one features PR2. Another, after the jump. (Read more…)

I don’t know exactly how, but Willow Garage has programmed a gripper to be able to tell whether or not a bottle is full, empty, open, or closed just by squeezing. I’m not sure I could do this with 93% accuracy, could you? If I had to guess, I’d say that with a fine enough measurement of back pressure from the bottle, you might be able to get a pretty good idea of what its state i… For example, the bottle that resists gripping pressure the most is probably full and closed. After that would come (probably) empty and closed or (maybe) full and open, followed by empty and open.

As cool as this is, if it’s how it works, it’s a fairly restrictive method, relying on a compliant bottle and with a binary lid that doesn’t exhibit states like “closed but not sealed.” But still… That’s a heck of a lot of information out of a little squeeze.

Speaking of grippers, the PR2 robot has also been outfitted with a new quick-change end effector, i.e. a system to quickly and easily swap out “hands” to adapt to different tasks, something that pretty much every single sci-fi robot has but has been somewhat elusive on real robots. Video of that, after the jump. (Read more…)

Now that Willow Garage’s PR2 robot has learned to plug itself in, you may be worried that it’s lost all dependency on humans, leading inevitably to a robot uprising and the eventual extermination of the entire human race. It’s a valid concern. With this in mind, Willow Garage has put together this handy list of ways in which you can personally defeat an uprising of PR2 robots with simple household items:

1. Lay 2×4s across the ground. The PR2 is highly maneuverable on inclines up to 5 degrees, but it cannot drive over sharp obstacles like a 2×4. The PR2 can also be turned away by anything that’s at least 3cm tall.

2. Always keep a supply of liquid nearby to toss on any advancing robot. We have Naked and Odwalla fruit juice fridges in a central location and restock them frequently.

3. Stairs are the enemy of cows, Daleks, and wheeled robots.

4. Black power outlets are like Ninjas: invisible to the PR2.

5. Use round door knobs. The PR2 can only enter homes that are ADA-compliant

Stairs. Door knobs. Fruit juice. Looks like we’ll be pretty safe from rampaging assemblages of household robots for the near future… Or will we.

[ Willow Garage ]
Comic from PHD Comics

Picking up an object is one of those things that humans do without thought, but it’s a complicated task for robots, involving all kinds of pressure sensors and dynamic grip adjustment. Willow Garage, while working on the gripper for their PR2 robot, discovered that it’s not so much pressure that causes damage to gripped objects (like eggs), but rather momentum, so if you get the gripper to slow down as soon as it makes contact with an object, you can hold it more securely without breaking it. This may not seem like a big deal at all, and I guess it’s not, but it’s another one of those little pieces that robotics researchers are gradually getting figured out on the way to making robots just as capable as humans.

And +2 to whoever had the idea of putting the egg in a bag first.

[ Willow Garage ]