Slashdot Mirror

Think Strogg.

The simple fact is that while we use senses in our bodies to do things, the similar versions for robots and autonomous vehicles are crude, expensive, and no-one is quite sure how to make them work the way we think they should. Computer vision is becoming a big thing, and despite the millions of people working with it or on it around the globe, there is still no standard way to immitate what a biological organism does with one eye, let alone two.Then there is that inner-ear thing, and this tells us many things: if we are vertical, falling, rising, moving forward or sideways... Our eyes do way more than a movie camera does. People are only now beginning to understand how many ways that we analyze the visual data presented to us through our eyes.

Fortunately the problems of autonomous underwater vehicles similar to planes and they are not as bad as the problems faced by ground-based vehicles. On the surface, there is so much to run into, get stuck on, fall off of etc. Just writing some code to keep a toy robot from getting stuck under the kitchen table is a huge task without boatloads of sensory data and processing power.

The tasks these vehicles are trying to accomplish ARE that difficult, well, using animal brains might help.

There are two groups you can try if you are interested in finding out more about hobbyists that are working on these problems http://www.dprg.org/ and http://www.seattlerobotics.org/index.php. There are many others, of course, but these two are fairly active groups.

The gyros detect the direction (yaw, roll, pitch) of the controller and the angle of the controller.

An accelerometer detects the amount of movement in 3D space that you make. It's probably in the same unit as the gyros (see some examples at http://www.dprg.org/projects/2003-01a/).

This is all you need to determine your position in 3D space. The gyros give you the direction, and you can derive the speed and distance traveled by the controller from the acceleration (assuming there is a clock that times the duration of the movement).

It's quite trivial and does not require any sensors outside of the controller, or any additional inputs such as bouncing infrared beams.

With Old Glory Robot Insurance

when they grab you with those metal claws, you can't break free..
because they're made of metal, and robots are strong.

YES, this task is THAT hard. If the military could simply throw money at the problem and get the solution, there would be no DARPA Grand Challenge competition at all.

The simple fact is that while we use senses in our bodies to do things, the similar versions for robots and autonomous vehicles are crude, expensive, and no-one is quite sure how to make them work the way we think they should. Computer vision is becoming a big thing, and despite the millions of people working with it or on it around the globe, there is still no standard way to immitate what the human does with one eye, let alone two. Humans have that inner-ear thing, and this tells us many things: if we are vertical, falling, rising, moving forward or sideways... Our eyes do way more than a movie camera does. People are only now beginning to understand how many ways that we analyze the visual data presented to us through our eyes.

The problems of autonomous ground vehicles are greater than that of planes because there is so much to run into, get stuck on, fall off of etc. Just writing some code to keep a toy robot from getting stuck under the kitchen table is a huge task without boatloads of sensory data and processing power.

The tasks the DARPA GC vehicles are trying to accomplish ARE that difficult.

There are two groups you can try if you are interested in finding out more about hobbyists that are working on these problems http://www.dprg.org/ and http://www.seattlerobotics.org/index.php . There are many others, of course, but these two are fairly active groups.

I can't clain to have built the bot either, but I can vouch for author. If there are errors you could get help directly from the author or from any number of robot club mailing lists.

Chibots
AHRC
DPRG

And more. The clubs often have links to one another, check around for one in your area and you could possibly get in person help if you have a problem.

Others who are doing robotics can be found via searches, or by following the links on most robotics clubs pages. I'm directly involved with Twin Cities Robotics. There are a bunch of others around the country, Portland Area Robotics (PARTS), Seattle Robotics Society (SRS), Triangle Amateur Robotics, Dallas Personal Robotics Group, Central Illinois Robot Club, Home Brew Robotics, and San Francisco Robotics Society of America to name a few.