Automaton

I found out just recently about Vision Robotics, a company in California with a pretty broad range of products (or eventual products), but all of them are based on computer vision and SLAM (simultaneous localization and mapping) navigation technology.

Their agricultural products look pretty interesting; they're looking at developing a robot that can go through an orchard and pick ripe oranges off of trees, as well as one that can prune grape vines. The concept appears to be that one robot will scan the trees in each orchard row with its vision system, mapping out where each fruit is, while a second robot (I can't tell from the renderings if it's attached to the first one or not -- though they do like like two discrete modules) with the picking arms follows it and picks the fruit it has identified. I have to say, if anyone else is familiar with the Boomers from the anime Bubblegum Crisis, this thing looks terrifying.

I found out about Vision Robotics through a student at Olin College (my alma mater), where the company is sponsoring a senior project to develop an end-effector that can gently grasp and pick an orange off a tree without breaking the skin. The student also compared apples to oranges, pointing out that oranges contrast with the tree, while apples tend to blend in with the green leaves, making oranges an easier target for a vision system. Still, Vision Robotics does appear to be designing an apple picker as well.

On the home robots side, they've got patents on a vacuuming and mopping robot. Even though iRobot beat them to the punch on the concepts, Vision Robotics patented a design that uses a remote cleaning head that is much smaller and more mobile than the Roomba body; a module carrying power and other large, heavy components can stay out of the way while the connected cleaning head does its work. Unlike the Roomba, this robot (as conceived) also maps the room before vacuuming.

They also list an elder care "personal service" robot, though as with all of these elder care concepts developed in the US and Japan, their feasibility remains to be seen. The floor cleaning model is much better proven.

For anyone interested in moving to San Diego (or anyone already there), they list an open development position on their Careers page (linked at the bottom of their site).

Image source: www.visionrobotics.com

From Spectrum's February issue:

The small motorboat meanders through the Amazonian swamp. The water is a turbid brown, the jungle a thicket of twisted trees. A cricrió bird chirps from the treetops. The Brazilian researchers stop the boat to have a look around. Suddenly a noise breaks the calm. Buzzzzzzzzzzzzzzz.

Within seconds, an angry swarm of cabas, Amazon wasps with a powerful sting, envelops the boat and its unlucky occupants. To hear Ney Robinson Salvi dos Reis tell the story, you almost feel you're right there in the rain forest with him, fighting off the bellicose bugs.

“Jumping into the water is not a good idea,” Reis says. “There are crocodiles, snakes, piranhas, and a bloodsucking little fish called candiru that can enter your body orifices. So I covered my head and told the mateiro”—the Amazon native piloting the boat—“to get us out of there fast!”

For Reis, a robotics engineer at Petrobras, Brazil's state-controlled oil company, fleeing from wild wasps through treacherous waterways in excruciating heat and humidity is just part of the fun. He heads the robotics laboratory at Petrobras's underwater technology division in Rio de Janeiro. The company's main oil fields reside in deep waters off the Brazilian coast, so Reis's lab specializes in developing all sorts of Jules Vernian contraptions—a caterpillar-like robot to unclog underwater pipelines, a supersized hydraulic wrench that can work down to 2000 meters.

Update: Some folks have had problems watching the QuickTime videos -- man, I did test this on Firefox running on both Mac OS X and Windows XP and it worked for me, but apologies anyway. And here's the solution: you can now watch the full video of the Crusher field trials without QuickTime.

Last week, our correspondent Sally Adee went to Fort Bliss, Texas, to attend the field trials of DARPA's 6.5-ton unmanned, autonomous off-road vehicle, Crusher, developed by Carnegie Mellon's National Robotics Engineering Center.

On the obstacle course, Crusher proved true to its name by obliterating old cars like a monster truck. But it's also smart enough to avoid certain obstacles in its path. Obstacles like our intrepid reporter herself!

Watch the video to see how Crusher approaches Adee, inspects her with its creepy batting LIDAR "eyes," recognizes her as something it shouldn't destroy, and then backs off.

How does the monster vehicle do that?

Sally Adee explains:

The batting "eyes" you see are LIDAR (which was explained to me as being "invisible laser beams"). Crusher uses it in combination with radar and optical cameras to sketch out the topography around it and in its path, and compare it to its database of known objects, to then draw its own conclusions about where to go and where not to go.

For example, when it comes across a big boulder, it analyzes the material, its reflectivity, and its shape. Then, having been loaded with pre-fab specifications of what constitutes a boulder, it decides on whether to back off, go around, or roll over the obstacle.

This is all on the fly-- all processing takes place on board in real time inside Crusher's brain. So what exactly is inside that brain?

To process the incoming "sensory" data stream, there are eight blade servers with a total of 32 cores of computing just to process all the images from the laser scanner and the stereo cameras.

Right behind the eyes, Crusher's autonomy system consists of 38 CPUs: commercial off-the-shelf chips like Xilinx FPGAs and Intel and AMD processors. This is how it figures out where to go and how to get there.

Just keep in mind that this monstrosity was constructed almost entirely at Carnegie Mellon by undergrads, grad students, professors, staff engineers and industry people (they did pretty much everything but load up the chassis). Now that's an engineering curriculum.

PS: Adee is preparing a complete video report on the trials -- it will be on Spectrum's site this Wednesday, check back. But if you want more Crusher now, continue reading this post for a video of the vehicle smashing two cars like sardine cans.

As we said last week, we were so glad our correspondent Sally Adee wasn't destroyed by Crusher, because she made it back to IEEE Spectrum's office and put together a full video report on the field trials she attended at Fort Bliss, Texas. The Crusher creators didn't fire its gun, but they demonstrated its might by obliterating some cars -- monster truck style.