Robocar Oriented Development and the New City

Brad Templeton has done more work on the implications and impacts of robocars/self-driving cars than anyone I know. There are dozens of thoughtful essays on his site, and he is now a consultant to Google’s self-driving car team (can’t talk about that of course – too bad). This longish essay speculates on the impacts of robocars on patterns of city development. 

This essay examines the potential future big changes to cities as a result of robocars. Most of these changes will be inspired by one key element of robocars: because they can drop passengers off, and then go do other work or park themselves densely in more remote lots, the need for large amounts of parking surrounding commercial buildings should diminish greatly, particularly in suburbs and non-central urban areas. If the land devoted to parking can be repurposed, what does that mean for the city?

See Brad’s main robocar page: Where Robot Cars (Robocars) Can Really Take Us. I learn something every time I visit.

Breakthrough With Towel-Folding Robot

What’s really striking about this project is that it was inexpensive and was completed fairly quickly, Eric Berger, director of the personal robotics program at Willow Garage, told TechNewsWorld.

“The thing that’s exciting about this towel-folding project isn’t the fact that we can fold bath towels, it’s that developing that new capability was faster and less expensive than it would have been before,” he explained. “It only required a graduate student with limited equipment instead of a multibillion dollar program.”

The Willow Garage general purpose prototype robot PR2 offered the UC Berkeley team the low-cost research tool they needed. For robotics folks PR2 is very roughly like Amazon EC2 is for innovative website startups (the $1 million startup of 1998 can now be done for $50k or less). What they did with the PR2 platform is very impressive — the generalized towel-folding task is not nearly as simple as it might look.

Excerpt from the Aaron Saenz blog post at Singularity Hub:

Robots just got roped into doing some light housework. Researchers at UC Berkeley used Willow Garage’s PR2 robot to fold towels. The UCB programming used some innovative visual scanning allowing the PR2 to pick up a towel, find its corners, and fold it on a table perfectly. According to the paper presented at the 2010 ICRA, the robot successfully completed 50 out of 50 attempts to fold a single towel, and also folded 5 out of 5 towels when they were presented in a group. Is watching a robot do laundry really that exciting? Hell yes. We have a personal robot actually performing personal and useful tasks. It’s not dancing. It’s not welcoming you to an expo. It’s doing real work. That’s amazing. But you know what, forget all that, too! You know why this is really great? UC Berkeley used a Willow Garage robot to develop their own sophisticated robotics program. That validates the whole premise of the PR2 – faster development by letting researchers use a common platform. Score one for open source robotics!

(…) Of course, watching robots fold towels is pretty frakkin’ awesome just on its own. The UC Berkeley team, under Professor Pieter Abbeel, has created a great algorithm for the PR2. It picks up a randomly folded towel it’s never seen before and twirls it until it finds a corner. Then it grasps that corner and finds the next until all corners are accounted for. Once the corners are identified the robot folds the towel and stacks them on a table. It’s elegant in its simplicity, complex in its visual recognition, and fun to watch when it’s sped up:

Willow Garage and the PR2 are children of the Stanford Personal Robotics Program. There are several videos on the web produced by the Berkeley robotics researchers. Our favorite is this video of the PR2 folding 5 different types of towels. Keep in mind this is speeded-up by 50:1.

Note: Willow Garage is giving away ten free PR2 robots!

If are lucky enough to live anywhere near Menlo Park you might be able to wangle an invite to Willow Garage.

Agricultural robotics

Have a look at the survey of agricultural robots in Fields of automation. I’m optimistic over the medium term as I think the very rapid advances in low cost sensors are certain to accelerate progress in this very challenging field of industrial automation. Plant tending is just a bit more variable and complex than welding automotive panels 🙂

It has been almost 30 years since I was involved briefly with dairy automation. No robotics, just automated monitoring of the input/outputs for each specific cow so that the software could optimize the individual feeding. The payoffs from micro knowledge of each plant should be similar (big).


(…) “It is actually not hard to pick an orange, but it is very hard to pick an orange cost effectively,” says Tony Stentz of the Robotics Institute at Carnegie Mellon University in Pittsburgh. Because robots can work all day without a break, they have one advantage over manual labour. But it is their potential for accurate information-gathering that is proving to be an equally important talent.

Crop-tending robots that use vision systems, laser sensors, satellite positioning and instruments to measure things like humidity can build up a database of information about each plant. This can be used to detect the onset of disease, says Dr Stentz. A “smart sprayer” can then deliver precise amounts of chemical to only those plants that require attention instead of spraying an entire field. By observing the development of each plan, crop yields can be predicted more accurately. Automated harvesters will then use the database to identify and gather individual produce whenever it is ready for harvest.