Northern Bites Blog

Here is a list released today of all teams that have ‘expressed their intention of participation’ for RoboCup 2007 in Atlanta. There are 27 teams total (though some teams may be omitted due to spam filters!).

- Impossibles Team
- Team ARAIBO
- Dutch Aibo Team
- UTAustinVilla
- TJArk
- Team Chaos
- The-CAT
- CMDash
- Microsoft Hellhounds
- NUbots
- SpelBots
- UChile
- WrightEagle
- ISocRob 4LL team
- Hamburg Dog Bots
- Twaves
- TecRams
- Northern Bites
- Cerberus
- GermanTeam
- Eagle Knights
- Brown University
- LTU Blue Devils
- Kouretes
- MetroBots
- DEN-INU
- SPQRLegged

Notable absences:

-rUNSWift. Second place finisher from last year. Looks like William Uther, rUNSWift’s leader, one of the main organizers from last year, and one of the dominant forces in RoboCup since its inception, will not be entering his team for another year. I had a chance to talk to Will last year in Bremen and the word was that 2006 was his last year at RoboCup because the organization he worked for was shifting priorities. Sadly, at least from this list, it looks like that fate came true.
-UPenn. I had heard through the grapevine that their participation this year was not certain. David Cohen, their student captain, graduated from UPenn last spring. Here’s hoping that their name was inadvertently forgotten on this list and that participate this year.

Notable additions:
-CMDash. They qualified but didn’t compete last year in Bremen. This year, the word is that they are going to give it a real go for the last (potentially) year of the four-legged league. Awesome.
-MetroBots, LTU Blue Devils, Brown University : three US teams who weren’t in Bremen last year and want to come to Atlanta this year. I suppose the proximity doesn’t hurt!

We shall see how the list shapes up. 27 teams applying and 24 slots means that there will be a lot fewer pissed off teams who don’t qualify. Also, it gives us, a second-year team, a better shot than last year, where 35 teams applied for 27 spots (I just checked the number). The downside of fewer teams applying tells me that some teams don’t have enough Aibos functioning, have moved onto newer, more exciting robot platforms, or simply have just lost their interest in the four-legged league.

The 2007 Rules were supposed to be announced today — I am really looking forward to see them — but I’ve seen no announcement. Hopefully they’ll come soon, as well as the announcement of the 2007 challenges, of which we want to spend a lot of time on this year.

just a few short hours on my improvements to this horizontal/perpendicular to the horizon vision scanning system.

horizon vision testing, originally uploaded by northern_bites.

The photo is a first attempt at a post scanning algorithm that starts at the horizon line and then goes upwards and downwards in decreasing frequency scanning parallel to the horizon.

Next up is to give a run structure another go that stores important colors.

The added bonuses of this system are:

1) it fixes the disproportions that show up when you move the head around, thus making the scan lines perpendicular to the ground
2) it scans a lot fewer pixels, hence making the whole vision system much faster

I’m going to see if I can’t get more out of this system this week as I’ll have little to do other than work on vision while the Lab is under construction.

Re-read and cleaned up a lot of our vision code. My basic plan is to over the next few days try to make some substantial vision improvements in two particular areas: speed optimization and horizon line utilization.

All night I’ve been working on a scanning routine that only scans parallel and perpendicular to the horizon line. The math is a bit complicated, but as I’ve worked most of it out it seems doable but time consuming. I’m doing most of the code out to see if this has better advantages over a blob rotation method. We’ll find out.

Not that exciting, but it’s interesting to see how far we’ve come — this was literally one week into making behaviors–in C++ no less!

I’m expecting the video this year to be like 83 times awesome-r.

So the Media, Contact, and Team Info pages on this blog have all gotten a brief facelift.

Media no longer says ‘In Progress’ and I included a link to our YouTube video page there, of which I’ll promise to finally get some of the full games up in the next couple of weeks.

The Contact page — actually, I didn’t update that page at all. Sorry.

Team Info includes the new 06/07 Northern Bites members + a few formatting updates.

Some New Goal work and some Horizon work.

First, I tried to debug and integrate Joho’s work on recognizing the new goals. I’ve narrowed down the buggy code, but couldn’t fix it. So hopefully more luck with that when Joho can take a closer look at it.

Second, I actually used the Horizon line calculation for some good. The purpose of the horizon line is basically twofold: it gives you an idea of where to look for things and it gives you an idea of where not to look for things. This seems simple but the GermanTeam’s report helped me clarify this a bit.

Most important objects more frequently appear around the horizon: goals, posts, far-away balls, etc. Close objects included really close goals, close balls, dogs, and lines. The former are also by nature further away from you and are therefore take up less room in the image. The horizon line gives you a good idea of where to scan intently. Beneath the horizon line you can scan sparsely. Above the horizon line–heavens to betsy–you don’t really have to scan at all.

This last bit was clear to me from the beginning. Scan less above the horizon line and you’ll cut down on false positives and speed up the vision system simply because it has fewer pixels to process. But giving you a better idea of where to scan more fervently, however, now that’s an idea that deserves some good coding.

More than 70 Teams from over 13 Countries. And we’re one of them.

Plus two teams I’ve never heard of before, one old, one new: Harzer Rollers and The Cat.

Picture 8.jpg, originally uploaded by northern_bites.

Finally got this issue out of the way — for real this time. Works with all variations of head values. Click here for more horizon images.

following the Apple Keynote Address! Actually, that’s pretty much all I did today.

Mark and I talked a bit about the state of localization and the way to integrate corner recognition into the ekf. Little bit tricky, but that should be done soon.

With a new fix of pose transforms last night, here are some new pose estimated distances of the ball to the center of the body, using nothing but the position of the body and the position of the ball on the screen (plus the known height of the ball):

Actual: 30 Reported: 32
Actual: 50 Reported: 49
Actual: 70 Reported: 69
Actual: 90 Reported: 92
Actual: 110 Reported: 113

As you can see, I am a genius. A few notes though: the estimates get noisier as ball gets further away. This is to be expected: variations in the angle from the focal point (camera point) to the ball xyz space gets narrower, hence the noise has a greater effect on the distance estimation. Now to check the distances at various head angles