Presentation of the perfect paper award on the RoboCup 2025 symposium.
An necessary facet of autonomous soccer-playing robots issues correct detection of the ball. That is the main target of labor by Can Lin, Daniele Affinita, Marco Zimmatore, Daniele Nardi, Domenico Bloisi, and Vincenzo Suriani, which received the perfect paper award on the latest RoboCup symposium. The symposium takes place alongside the annual RoboCup competitors, which this 12 months was held in Salvador, Brazil. We caught up with a few of the authors to search out out extra in regards to the work, how their technique could be transferred to functions past RoboCup, and their future plans for the competitors.
May you begin by giving us a short description of the issue that you just had been making an attempt to resolve in your paper “Self-supervised Characteristic Extraction for Enhanced Ball Detection on Soccer Robots”?
Daniele Affinita: The primary problem we confronted was that deep studying typically requires a considerable amount of labeled knowledge. This isn’t a significant downside for frequent duties which have already been studied, as a result of you may often discover labeled datasets on-line. However when the duty is extremely particular, like in RoboCup, it’s essential accumulate and label the information your self. Meaning gathering the information and manually annotating it earlier than you may even begin making use of deep studying. This course of just isn’t scalable and calls for a big human effort.
The thought behind our paper was to scale back this human effort. We approached the issue by self-supervised studying, which goals to be taught helpful representations of the information. In spite of everything, deep studying is basically about studying latent representations from the obtainable knowledge.
May you inform us a bit extra about your self-supervised studying framework and the way you went about growing it?
Daniele: Initially, let me introduce what self-supervised studying is. It’s a approach of studying the construction of the information with out getting access to labels. That is often performed by what we name pretext duties. These are duties that don’t require express labels, however as a substitute exploit the construction of the information. For instance, in our case we labored with pictures. You may randomly masks some patches and prepare the mannequin to foretell the lacking elements. By doing so, the mannequin is pressured to be taught significant options from the information.
In our paper, we enriched the information by utilizing not solely uncooked pictures but additionally exterior steerage. This got here from a bigger mannequin which we discuss with because the trainer. This mannequin was educated on a special process which is extra normal than the goal process we aimed for. This fashion the bigger mannequin can present steerage (an exterior sign) that helps the self-supervision to focus extra on the precise process we care about.
In our case, we needed to foretell a decent circle across the ball. To information this, we used an exterior pretrained mannequin (YOLO) for object detection, which as a substitute predicts a free bounding field across the ball. We will arguably say that the bounding field, a rectangle, is extra normal than a circle. So on this sense, we had been making an attempt to make use of exterior steerage that doesn’t clear up precisely the underlying process.
Overview of the information preparation pipeline.
Had been you capable of take a look at this mannequin out at RoboCup 2025?
Daniele: Sure, we deployed it at RoboCup 2025 and confirmed nice enhancements over our earlier benchmark, which was the mannequin we utilized in 2024. Specifically, we observed that the ultimate coaching requires a lot much less knowledge. The mannequin was additionally extra sturdy underneath totally different lighting circumstances. The difficulty we had with earlier fashions was that they had been tailor-made for particular conditions. However in fact, all of the venues are totally different, the lighting and the brightness are totally different, there is likely to be shadows on the sector. So it’s actually necessary to have a dependable mannequin and we actually observed an ideal enchancment this 12 months.
What’s your staff title, and will you speak a bit in regards to the competitors and the way it went?
Daniele: So our staff is SPQR. We’re from Rome, and we now have been competing in RoboCup for a very long time.
Domenico Blois: We began in 1998, so we’re one of many oldest groups in RoboCup.
Daniele: Yeah, I wasn’t even born then! Our staff began with the four-legged robots. After which the league shifted extra in the direction of biped robots as a result of they’re tougher, they require steadiness and, general it’s more durable to stroll on simply two legs.
Our staff has grown lots throughout latest years. We’ve been following a really constructive pattern, going from ninth place in 2019 to 3rd place on the German Open in 2025, and we received 4th place at RoboCup 2025. Our latest success has attracted extra college students to the staff. So it’s sort of a loop – you win extra, you entice extra college students, and you may work extra on the challenges proposed by RoboCup.
SPQR staff.
Domenico: I need to add that additionally, from a analysis standpoint, we now have received three greatest paper awards within the final 5 years, and we now have been proposing some new developments in the direction of, for instance, the usage of LLMs for coding (as a robotic’s behaviour generator underneath the supervision of a human coach). So we are attempting to maintain the open analysis area energetic in our staff. We need to win the matches however we additionally need to clear up the analysis issues which are sure along with the competitors.
One of many necessary contributions of our paper is in the direction of the usage of our algorithms exterior RoboCup. For instance, we are attempting to use the ball detector in precision farming. We need to use the identical method to detect rounded fruits. That is one thing that’s actually necessary for us; to exit the context of Robocup and to make use of Robocup instruments for brand new approaches in different fields. So if we lose a match, it’s not an enormous deal for us. We would like our college students, our staff members, to be open minded in the direction of the usage of RoboCup as a place to begin for understanding teamwork and for understanding how you can cope with strict deadlines. That is one thing that RoboCup can provide us. We attempt to have a staff that’s prepared for each sort of problem, not solely inside RoboCup, but additionally different sorts of AI functions. Successful just isn’t all the pieces for us. We’d desire to make use of our personal code and never win, than win utilizing code developed by others. This isn’t optimum for attaining first place, however we need to educate our college students to be ready for the analysis that’s exterior of RoboCup.
You mentioned that you just’ve beforehand received two different greatest paper awards. What did these papers cowl?
Domenico: So the final two greatest papers had been sort of visionary papers. In a single paper, we needed to provide an perception in how you can use the spectators to assist the robots rating. For instance, should you cheer louder, the robots are inclined to kick the ball. So that is one thing that isn’t truly used within the competitors now, however is one thing extra in the direction of the 2050 problem. So we need to think about how it is going to be 10 years from now.
The different paper was known as “play all over the place”, so you may, for instance, play with several types of ball, you may play exterior, you may even play with no particular purpose, you may play utilizing Coca-Cola cans as goalposts. So the robotic has to have a normal method that isn’t associated to the precise area utilized in RoboCup. That is in distinction to different groups which are very particular. We’ve a special method and that is one thing that makes it more durable for us to win the competitors. Nevertheless, we don’t need to win the competitors, we need to obtain this purpose of getting, in 2050, this match between the RoboCup winners and the FIFA World Cup winners.
I’m considering what you mentioned about transferring the tactic for ball detection to farming and different functions. May you say extra about that analysis?
Vincenzo Suriani: Our lab has been concerned in some totally different initiatives referring to farming functions. The Flourish venture ran from 2015 – 2018. Extra not too long ago, the CANOPIES venture has focussed on precision agriculture for everlasting crops the place farmworkers can effectively work along with groups of robots to carry out agronomic interventions, like harvesting or pruning.
We’ve one other venture that’s about detecting and harvesting grapes. There’s a large effort in bringing data again from RoboCup to different initiatives, and vice versa.
Domenico: Our imaginative and prescient now could be to give attention to the brand new era of humanoid robots. We participated in a brand new occasion, the World Humanoid Robotic Video games, held in Beijing in August 2025, as a result of we need to use the platform of RoboCup for different kinds of functions. The thought is to have a single platform with software program that’s derived from RoboCup code that can be utilized for different functions. When you have a humanoid robotic that should transfer, you may reuse the identical code from RoboCup as a result of you need to use the identical stabilization, the identical imaginative and prescient core, the identical framework (roughly), and you may simply change some modules and you may have a very totally different sort of software with the identical robotic with roughly the identical code. We need to go in the direction of this concept of reusing code and having RoboCup as a take a look at mattress. It’s a very robust take a look at mattress, however you need to use the leads to different fields and in different functions.
Trying particularly at RoboCup, what are your future plans for the staff? There are some large modifications deliberate for the RoboCup Leagues, so might you additionally say how this would possibly have an effect on your plans?
Domenico: We’ve a really sturdy staff and a few of the staff members will do a PhD within the coming years. One among our targets was to maintain the scholars contained in the college and the analysis ward, and we had been profitable on this, as a result of now they’re very passionate in regards to the RoboCup competitors and about AI basically.
When it comes to the modifications, there might be a brand new league inside RoboCup that may be a merger of the usual platform league (SPL) and the humanoid kid-size league. The humanoid adult-size league will stay, so we have to determine whether or not to affix the brand new merged league, or transfer to adult-sized robots. In the mean time we don’t have too many particulars, however what we all know is that we’ll go in the direction of a brand new period of robots. We acquired robots from Booster and we are actually buying one other G1 robotic from Unitree. So we are attempting to have an entire household of latest robots. After which I believe we’ll go in the direction of the league that’s chosen by the opposite groups within the SPL league. However for now we are attempting to arrange an occasion in October in Rome with two different groups to alternate concepts and to know the place we need to go. There will even be a workshop to debate the analysis aspect.
Vincenzo: We’re additionally in dialogue about the perfect dimension of robotic for the competitors. We’re going to have two totally different positions, as a result of robots have gotten cheaper and there are groups which are pushing to maneuver extra shortly to a much bigger platform. However, there are groups that need to keep on with a smaller platform in an effort to do analysis on multi brokers. We’ve seen a whole lot of functions for a single robotic however not many functions with a set of robots which are cooperating. And this has been traditionally one of many core elements of analysis we did in RoboCup, and in addition exterior of RoboCup.
There are many factors of view on which robotic dimension to make use of, as a result of there are a number of elements, and we don’t know the way quick the world will change in two or three years. We are attempting to form the principles and the circumstances to play for subsequent 12 months, however, due to how shortly issues are altering, we don’t know what the perfect determination might be. And likewise the analysis we’re going to do might be affected by the choice we make on this.
There might be some modifications to different leagues within the close to future too; the small and center sizes will shut in two years most likely, and the simulation league additionally. Lots will occur within the subsequent 5 years, most likely greater than over the last 10-15 years. It is a crucial 12 months as a result of the choices are based mostly on what we will see, what we will spot sooner or later, however we don’t have all the knowledge we’d like, so it is going to be difficult.
For instance, the SPL has an enormous, most likely the largest, group among the many RoboCup leagues. We’ve a whole lot of groups which are grouping by curiosity and so there are groups which are sticking to engaged on this particular downside with a selected platform and groups which are making an attempt to maneuver to a different platform and one other downside. So even inside the identical group we’re going to have multiple standpoint and hopes for the longer term. At a sure level we’ll strive to determine what’s the greatest for all of them.
Daniele: I simply need to add that in an effort to obtain the 2050 problem, for my part, it’s essential to have only one league encompassing all the pieces. So up thus far, totally different leagues have been specializing in totally different analysis issues. There have been leagues focusing solely on technique, others focusing solely on the {hardware}, our league focusing primarily on the coordination and dynamic dealing with of the gameplay. However on the finish of the day, in an effort to compete with people, there should be just one league bringing all these single points collectively. From my standpoint, it completely is sensible to maintain merging leagues collectively.
Concerning the authors
 | Daniele Affinita is a PhD scholar in Machine Studying at EPFL, specializing within the intersection of Machine Studying and Robotics. He has over 4 years of expertise competing in RoboCup with the SPQR staff. In 2024, he labored at Sony on area adaptation methods. He holds a Bachelor’s diploma in Laptop Engineering and a Grasp’s diploma in Synthetic Intelligence and Robotics from Sapienza College of Rome. |
 | Vincenzo Suriani earned his Ph.D. in Laptop Engineering in 2024 from Sapienza College of Rome, with a specialization in synthetic intelligence, robotic imaginative and prescient, and multi-agent coordination. Since 2016, he has served as Software program Growth Chief of the Sapienza Soccer Robotic Crew, contributing to main robotic competitions and worldwide initiatives resembling EUROBENCH, SciRoc, and Tech4YOU. He’s at the moment a Analysis Fellow on the College of Basilicata, the place he focuses on growing clever environments for software program testing automation. His analysis, acknowledged with award-winning papers on the RoboCup Worldwide Symposium (2021, 2023, 2025), facilities on robotic semantic mapping, object recognition, and human–robotic interplay. |
 | Domenico Daniele Bloisi is an affiliate professor of Synthetic Intelligence on the Worldwide College of Rome UNINT. Beforehand, he was affiliate professor on the College of Basilicata, assistant professor on the College of Verona, and assistant professor at Sapienza College of Rome. He acquired his PhD, grasp’s and bachelor’s levels in Laptop Engineering from Sapienza College of Rome in 2010, 2006 and 2004, respectively. He’s the writer of greater than 80 peer-reviewed papers printed in worldwide journals and conferences within the area of synthetic intelligence and robotics, with a give attention to picture evaluation, multi-robot coordination, visible notion and data fusion. Dr. Bloisi conducts analysis within the area of melanoma and oral carcinoma prevention by computerized medical picture evaluation in collaboration with specialised medical groups in Italy. As well as, Dr. Bloisi is WP3 chief of the EU H2020 SOLARIS venture, unit chief for the PRIN PNRR RETINA venture, unit chief for the PRIN 2022 AIDA venture. Since 2015, he’s the staff supervisor of the SPQR robotic soccer staff collaborating within the RoboCup world competitions |
 | Can Lin is a grasp scholar in Knowledge Science at Sapienza college of Rome. He holds a bachelor diploma in Laptop science and Synthetic intelligence from the identical college. He joined the SPQR staff in September of 2024, specializing in duties associated to pc imaginative and prescient. |
Lucy Smith
is Managing Editor for AIhub.