Wednesday 17 July 2024

Group Phase Day 1

Did you notice how I just obscured that I did not post for 2 days after the Day 0 update? To the untrained eye, it might even look like we weren't so incredibly busy that we had enough time to write blog posts. But like any good deception, there's hopefully just enough truth to it to keep you reading further. Specifically, the matches have indeed just begun and we just played our first match against B-Human, our eternal adversary. Statistically, we managed an ~11% performance increase going from a 9:0 loss at the Bordeaux final to an 8:0 today, if you ignore the German Open, that is.

Oh well, there is no nice way of saying it: That was pretty terrible. Robots fresh from the NAO clinic were still a little shakey on their feet, maybe the meds hadn't worn off just yet? Either way, we sent them right back after the fact. Additionally, our most recent changes did not work all the time - 3 own goals in the first half are a troubling sign of underlying issues, we're on it!

Either way, see for yourself (if you can bear it)

The Green Screen interviews at the beginning of the videos are back and so is the voice over. Eileen tells you about her team B-Human and our very own Tobias provides insights to help you follow along. 

In the spirit of doing too much and going for the imaginary social media world champion title, we also added a quick little interview with one of the B-Human developers from the half time break - on the exact turf where the first half had just ended seconds before!

 


Game 2 with the Bembelbots
&
Techincal Challenge with Lennart

For round 2, we'll be facing off against the Bembelbots from Frankfurt later this afternoon, who are sitting right behind us in the team area. 

 



After that, we'll head straight to the area for the Technical Challenge, where Lennart, our youngest teammate at just 15 years of age, will put his skills to the test in the Shared Autonomy Challenge. 


Monday 15 July 2024

Day 0 (but we're counting upwards so it's really just the beginning)

 

Genießen Sie Ihr Leben in vollen Zügen

RoboCup 2024 – we’re going to Eindhoven! Today, with palpable exictement in the air and lots of heavy equipment in our bags, the day had finally come – catch the train to Frankfurt – Düsseldorf – Herzogenrath – Heerlen – Eindhoven each time switching into a slower train. The last one felt like it was going backwards through the station, but that might just have been us – excited about the week ahead, we just couldn’t wait to get there. But apparently, we were not alone in that. Some trains Eindhoven-wards were so overfilled, they looked more like a RoboCup match with horrible lighting conditions in Round 1: everyone is really crowded and stumbling over each other, packages are getting lost everywhere, nothing is moving and the people in charge are trying to make sense while making sure noone breaks anything. We took one good look and knew – we’re better off taking the next train. That turned out to be the right idea – in the end, we arrived at the main station faster than otherwise. We were immediately greeted by RoboCup flags and posters everywhere! Eindhoven seems to be just as excited as we are.






Having made it to the Hotel, we quickly unpacked and went out for dinner and some final inspiration before the cup in form of the European Championship title match between Spain and England. Fun Fact: Our signature kick-off move is conincidentally identical to the back pass maneauver by Real Madrid. A case of true convergent software evolution! And the Spanish must be doing something right! So if that’s not a good omen, I don’t know what is!

Tomorrow, we’ll start our first of two set-up days before matches commence on Wednesday. The technical challenge concludes on Friday and the Main Round of the Champion’s Cup will keep us busy on the weekend. We’ll post the schedule, links to the live stream and more updates as we get them!



Monday 1 July 2024

RoboCup 2024!

 

Ohne Holland Nach Holland Nach Noord-Brabant fahr'n wir zur WM!

    As the UEFA Euro Championship slowly but surely draws to it's climax, we're just getting started! On Sunday, July 14th, we're heading to Eindhoven for this year's RoboCup. The sting of last year's 0:9 final against B-Human was memorably unpleasant, at the German Open in April we managed a 4:1 against the northeners which isn't exactly a win, I know, but it didn't go unnoticed that we applied a considerable amount of pressure and ruined their perfect score balance, ha! In case you missed it:


 But yes, losing by a smaller margin is less bad but obviously not enough to dethrone the reigning world champion. So the question persists: What do? Let's highlight two innovations:

What's the T, Roboboy?

    Self-localization on the field is one of the principal problems of robofootball If the NAO doesn't know where it is, there is not much that can come from that. And if the robot communicates the wrong position, the break-down in efficacy just cascades through the entire team-strategy. Our new solution: finding T-shaped line sections on the field to boost the network processing the camera images. Sounds easy, right? No? Well, matter of taste. Oh and that means of course that you need to differentiate different kinds of T-lines, light conditions change all the time so color is strongly relative, the resolution is not exactly full HD and the images are tiny. So I guess it's actually quite tricky, nevermind. Did I mention that you need a substantial amount of training data? But the idea is very promising and our Machine Learning expert Tobias reports great results so far, so that's something to be excited about! We'll report how it goes!

Beep Boop, Baby!

    Another novelty is a true wild card - we've been working on a new communication protocol - using sound! This seemingly obvious choice for making yourself understood - humans have overall been relatively successful with that - comes however, with several caveats if you're talking robots. Whistles, referees, a rowdy crowd and a constant backdrop of chaotic noises from the robots themselves create a perfect storm of interference, so we had to get creative. The idea: if the interferences mainly consist of human-discriminable acoustic patterns - we need to pivot to physical properties that operate on an entirely different level: in chaotic interference, structured interference patterns are uniquely... unique. Spectacularly enough, quantitative musicology has quite a few things to say about that. Throw some symbolic communication strategies from theoretical linguistics into the mix, add a little dynamic data compression et voilá: Let's hope it works, fingers crossed! More updates to follow!

 

But wait, there's more!

As we get closer to the RoboCup, I'll post more about what we have been working on. 

Up next: This year's technical challenge Shared Autonomy: 2 against 2, one team fully autonomous, one team half autonomous, half human-operated. Will the humans and robots really work together? What could go wrong? Who will tell science-fiction writers that we're really starting to catch up?