Concerns regarding the green paneling/green shirts

[Roland]

Originally Posted by MrToast

What if you made your robot green to throw off other tracking bots? A little devious and non-GP, as I'll be the first to admit, but definitely a smart strategy...

Dave

There's an interesting thought.

[kaszeta]

Originally Posted by Roland

There's an interesting thought.

Rule <R26> claims "No devices or decorations are permitted on the robot that are intended to jam or interfere with the operation of the vision system (i.e. changing robot color to confuse opponent’s vision system)."

[Roland]

Originally Posted by kaszeta

Rule <R26> claims "No devices or decorations are permitted on the robot that are intended to jam or interfere with the operation of the vision system (i.e. changing robot color to confuse opponent’s vision system)."

Our school color is green, it's not intended to interfere with the sensors...

[karinka13]

Originally Posted by kaszeta

Rule <R26> claims "No devices or decorations are permitted on the robot that are intended to jam or interfere with the operation of the vision system (i.e. changing robot color to confuse opponent’s vision system)."

Now how would the judges know if it was intentional? I happen to like the color gren very much and would love to have a green bot...

[bigqueue]

Originally Posted by karinka13

Now how would the judges know if it was intentional? I happen to like the color gren very much and would love to have a green bot...

I happen to know if a team in Vt that in fact has had a very nice looking Green robot. I'm sure this will be a question asked to First....it will be interesting to see what the answer is. (will teams be forced to give-up their identity color!)

-Quentin

[Al Skierkiewicz]

I am less concerned about a false trigger on the vision system from green anythings, (including humans) than I am about variations in lighting from venue to venue. When a material looks green to you it may not appear green to a camera depending on the color of the light. It may not even appear to a camera if the light is reflecting in the right way. I think that if you read the paper on visualization you might get a better handle on how this recognition works. I would think a robot would only get in trouble if it had a green stripe of approx the same height and width as the tetra and the same altitude and texture. What I am saying is test like crazy to be sure.

[Petey]

Originally Posted by Al Skierkiewicz

I am less concerned about a false trigger on the vision system from green anythings, (including humans) than I am about variations in lighting from venue to venue. When a material looks green to you it may not appear green to a camera depending on the color of the light. It may not even appear to a camera if the light is reflecting in the right way. I think that if you read the paper on visualization you might get a better handle on how this recognition works. I would think a robot would only get in trouble if it had a green stripe of approx the same height and width as the tetra and the same altitude and texture. What I am saying is test like crazy to be sure.

Excellent point.

It will be difficult to test like that when you're concerned about other robots, though.

Think about it--that robot followed Dave around, and it also followed the green tetra, if I'm not mistaken. Those were wildly different greens.

--Petey

[Greg Marra]

Originally Posted by Petey

Excellent point.

It will be difficult to test like that when you're concerned about other robots, though.

Think about it--that robot followed Dave around, and it also followed the green tetra, if I'm not mistaken. Those were wildly different greens.

--Petey

I do not believe they showed the robot following a green tetra. That was only in the CG-demo and the people-demo.

[jedinite]

Well, certain members of our team, who will remain unnamed

*cough* me *cough*

have already begun a list of the top things the judges *DON'T* want to hear this year. The top of the list - "Well, it's your own fault for wearing that color. Don't blame us!"

We're just worried 'cause our shirts look like almost the same colors as the blue tetras. That might be a problem in practicing. I guess the same is true for green teams and red teams in practice matches. All I know is that I've already been instructed never to wear my tie-dye around the robot... it's already tried to get me enough times.

[Petey]

Interesting then.

I just want to see the answer.

--Petey

[Greg Marra]

Originally Posted by Petey

Interesting then.

I just want to see the answer.

--Petey

I notice a lot of people are posting about using the camera system to find "blue" and "red" and "yellow".

Really? My impression was you were just going to home into the green color that's only on the vision tetras. No need to look for other colors, the green is all you're interested in.

What was your thinking?

[Kyle]

i really don't think that the colors will have that much of an effect, i have been thinking about this alot and i have also been looking up info on the sensors and a team should be able to set the sensors to only pick up the exact color and the sensor will mostly work in the area it is pointing in, remember in the kickoff the sensor was mounted high to follow Dave, since the tetras are kinda low to the ground there shouldn't be much of a problem. at least i hope not..

[Salik Syed]

hmmmm.... maybe they don't want it so easy.....
i'm sure you could program in SOFTWARE to ensure that it is a vision tetra...
i.e after recognizing the green color you measure the length of the green... like move the camera left and right and see how long it takes to "lose" the green ....
i'm sure you could also adjsut the camera to dif light settings based on the beginning of the match... maybe make your robot drive forward to a known positon of color and register that value to calibrate the camera... however if there is ALOT of variable settings like diamond plate reflecting more light near the starting point etc.. some difficulties may come up!

[KevinRo]

Take a good look at the camera documentation. You will find several things that will help you out.

1) Each object is tracked by a bounding box. This is key. Remember it. Its important. Don't forget it! A bounding box is the smallest possible box that will enclose the color object. Consider the difference in view between a person in a shirt and a vision tetra. What can the bounding box tell you?

2) The field of view of the camera isn't as wide as you would think.

3) The percieved size of a distant object is related to the sine function. A good hint: Percieved Height is sort of = Height * (1 / radius). Draw a picture, think about what sine is, and see if you can figure that one out.

Kevin

[Petey]

Originally Posted by bigqueue

I happen to know if a team in Vt that in fact has had a very nice looking Green robot. I'm sure this will be a question asked to First....it will be interesting to see what the answer is. (will teams be forced to give-up their identity color!)

-Quentin

Exactly--885 would lose quite a bit of their identity.

Here is the (two part) question that I posted in the forum:

Regarding <R26>: Will there be any precautions taken--or any precautions necessary--to ensure that the cameras do not become attracted to robots or humans that are colored like field elements (eg clad in red, blue, green, yellow, silver?)

Clarifying Q. 981: Even if the intent is not to distract the robot? Since the cameras can be calibrated to sense many different colors, must some colors (& if so, which) be avoided by teams in decorating their robots and themselves?

Think about it--

If 811 built their normal red robot, and a team tried to sense the red tetras, the robot would be attracted to you, wouldn't it? Similarly, if a robot was built to sense the loading dock (yellow), and they went against Buzz, the Buzz robot could be mauled, couldn't it?

Interested to hear the answer. That's just one of the 7 or so questions I posted.

--Petey