Evolution Robotics' ER1 Reviewed

Anonymous Coward writes "A useful review of Evolution Robotics' ER-1 by the boys at Techfocus. It covers: construction, customization, hardware requirements, best features, programming, durability of equipment -- and all that good stuff. One interesting factoid is that the robot can recognize objects until the object is blocked - up to 40% - by something (like a piece of furniture). Techfocus aptly points out the Orwellian implications... Another thing that rocked my world is the notion that the robot is not as much of a drag on CPU as one might suspect. TF ran the unit on an NEC Versa VXi running Windows 2000, with a 900mhz CPU and 128mb of RAM, and encountered absolutely no problems. Encouragingly, if you want to further customize your robot, why not just write a script in C or Perl -- the manual even points users toward an app primarily based in Linux. What's not surprising: it's pricey. Also some nice pictures of how the robot really looks right out of the box."

Comments

Real world robots

[Lakers]

I've seen so many robot articles. Robots to mow your lawn, vacuum your carpet, walk your dog...

Where are they though? I have yet to walk down my street and see a mowing robot or visit a friends house and see a robot cleaning the windows. Most of these articles will say that they will be available to consumers in the next year or so.

Funny, I've been reading articles about robots for what seems like forever

Sensors?

[Hayzeus]

Any sensors available other than the camera? For long term useage, I'd expect at least rudimentary obstacle sensing; a robot that runs around an unstructured environment for too long will generally not do to well without decent obstacle sensors. Anybody else have one of these that would care to comment?

How about

[Anonymous Coward]

We quit using the word Orwellian.

Especially for topics like this where it doesn't apply even remotely. Name one Orwell book about toy robots.

God, you all are buzzword loving fucktards.

Re:CPU usage depends on tasks

[gwernol]

The largest requirement for a robot able to recognize objects would be memory/storage. Kind of like those 20 questions programs, it is very simple processing to compare input with a matrix of possibilities.

I'm sorry but that's a gross simplification. Computer recognition of images, especially images of the real 3D world, is a very hard and computationally intense process. This problem is still at the cutting edge of research. Describing it as "simple processing to compare the input with a matrix of possibilities" is on the same level as describing Doom III as "adds a couple of numbers together and displays some colored dots on the screen". It may be at some level accurate but it misses out the hard parts entirely.

To learn more, you could start at CMU's computer vision page. There's a whole world of interesting techniques out there, jump in and try some.