A core objective of RoboCup is to promote and advance robotics and AI research through the challenges offered by its various leagues. The ultimate goal of the soccer competition is that, by 2050, a team of fully autonomous humanoid robots will defeat the most recent winner of the FIFA World Cup. To bring this vision closer to reality, the RoboCup Federation has announced several changes to the leagues. We spoke with Alessandra Rossi, a trustee who has been involved in the humanoid soccer league for many years, to learn more.
I am Alessandra Rossi from the University of Naples “Federico II”, where I am an Assistant Professor of Computer Science. I began working with and collaborating in RoboCup in 2016, when I started my PhD at the University of Hertfordshire in the UK. I am still affiliated with the University of Hertfordshire, as I remain a member of the humanoid KidSize team Bold Hearts, the longest continuously active team in the UK. After a few years, I became the team leader of Bold Hearts.
In 2019, I became a member of both the Technical Committee and the Organizing Committee of the Humanoid League. After serving on the Technical Committee for two years, I was elected to the Executive Committee of the Humanoid League. In 2025, I was elected to the Board of Trustees for the first time.
Over the years, I have steadily increased my involvement and commitment to RoboCup. I have always sought to actively engage the RoboCup community, both during competitions and outside of competition periods. I also work to encourage engagement between the major and junior leagues and to participate in regional RoboCup events.
While working at the University of Hertfordshire as a Visiting Lecturer, we launched an online module that uses RoboCup as a benchmark for teaching robotics to undergraduate students. The module is still running. I initially served as the module leader, and this role has since been taken over by our Bold Hearts teammate, Bente Riegler.
Last year, Maike Paetzel-Prüsmann, Merel Keijsers, and I (as lead authors), in collaboration with several trustees and many members from different leagues, published a paper on the current and future challenges in humanoid robotics. The paper was published in Autonomous Robots and is, to the best of my knowledge, the first to involve such a large and diverse group of contributors from across the RoboCup leagues. It discusses research within RoboCup and the collaboration and synergies between the leagues.
Group photo of the humanoid league teams at RoboCup 2025.
The 2050 goal of the RoboCup Federation, as many people are probably aware, is for a team of humanoid robots to play against the winners of the FIFA World Cup. To achieve this, it is necessary to push further in that direction. One of the key changes, therefore, will be a stronger focus on humanoid robots.
Another major change will be the merger of the Standard Platform League (SPL) and the KidSize Humanoid League. This merged league will have the freedom to define its exact format and to develop a new roadmap that aligns the entire league toward a shared objective. While the 2050 goal itself remains unchanged, the path toward achieving it will need to be adjusted.
It is crucial to continue fostering the engagement of teams in the leagues that will be affected by these changes. At the same time, we must recognize that technology is advancing rapidly. Over the past year, in particular, we have seen significant progress in both hardware platforms and large language models. As RoboCup serves as a global benchmark for robotics research, we should continuously strive to advance technology and research—while still having fun.
Soccer is the complex task and behavior we are studying, and it is complex in many dimensions: from physical control and robot motion, to communication and strategy, and even human-like interactions. These include responding to the referee’s whistle, verbal and non-verbal communication among team members, interactions with the coach, and communication with the referee. All of these aspects will ultimately need to be incorporated into the humanoid league.
I believe we will see a mix of different robots. With the three companies currently sponsoring RoboCup, we have already seen that their robots can achieve a wide range of behaviors, and there have been significant improvements in robot control. Some of these robots can walk very quickly—almost to the point of running.
Initially, there may be the possibility of multiple teams using the same platform. However, we must keep in mind that both hardware and software can become obsolete very quickly, so we need to remain open to multiple options. A robot that is state of the art today may no longer be so in a year or two. As a result, committing to a single standard platform could limit future progress.
For this reason, the current idea is to remain open to multiple platforms. Many teams already have excellent custom-built robots, and further improvements to these platforms should be encouraged. That said, the exact structure has not yet been decided, and these decisions will be made in consultation with the teams. It is important to give the RoboCup community the time it needs to adapt and move forward.
One major change is that we have added extra robots to each team. Previously, teams played with just two robots per side, but matches are now played three versus three.
Another important improvement is the reduced presence of humans on the field. There is no longer a handler assigned to each robot. In the past, a team member had to walk behind the robots in case they fell and risked being damaged.
I have actually played in a match against the winning humanoid team. Naturally, the human team won, but it was an enjoyable and very interesting game, as the robots were surprisingly fast.
Yes, it depends on which league you are part of. The reactions have been a mix of excitement and passion. Of course, everyone is keen to see improvements, and participants have always been prepared for changes to the rules and the league structures. However, there are still some open questions, and teams are waiting to see how things will evolve. Tomorrow, there will be a meeting with the President and several trustees to address questions raised by the leagues.
The overall direction of RoboCup, guided by the 2050 goal has not changed. Each league has been extremely valuable and has contributed in different ways toward achieving that goal. RoboCup has also been immensely valuable for robotics research more broadly. Beyond being fun, the challenges involved in making robots play soccer are extraordinarily complex. The research and solutions developed within RoboCup can be applied to many other fields and applications.
|
Alessandra is Assistant Professor at the University of Naples Federico II, Italy. Her PhD thesis was part of the Marie Sklodowska-Curie Research ETN SECURE project at the University of Hertfordshire (UK). Her research interests include Human–(Multi) Robot Interaction, social robotics, trust, XAI, multi-agent systems and user profiling. She is Project Manager and co-supervisor of the MSCA PERSEO (955778), TRAIL (101072488) and SWEET (101168792). She is also co-PI of the project ERROR (FA8655-23-1-7060), and part of several national and international projects. Alessandra is also trustee member of RoboCup Federation, and member of the Humanoid League team called Bold Hearts. She is Chair of the IEEE P3108 |
If you’ve ever gone hiking, you know trails can be challenging and unpredictable. A path that was clear last week might be blocked today by a fallen tree. Poor maintenance, exposed roots, loose rocks, and uneven ground further complicate the terrain, making trails difficult for a robot to navigate autonomously. After a storm, puddles can form, mud can shift, and erosion can reshape the landscape. This was the fundamental challenge in our work: how can a robot perceive, plan, and adapt in real time to safely navigate hiking trails?
Autonomous trail navigation is not just a fun robotics problem; it has potential for real-world impact. In the United States alone, there are over 193,500 miles of trails on federal lands, with many more managed by state and local agencies. Millions of people hike these trails every year.
Robots capable of navigating trails could help with:
Driving off-trail introduces even more uncertainty. From an environmental perspective, leaving the trail can damage vegetation, accelerate erosion, and disturb wildlife. Still, there are moments when staying strictly on the trail is unsafe or impossible. So our question became: how can a robot get from A to B while staying on the trail when possible, and intelligently leaving it when necessary for safety?
Our main contribution is handling uncertainty by combining two complementary ways of understanding and mapping the environment:
Geometry is great for detecting big hazards, but it struggles with small obstacles and terrain that looks geometrically similar, like sand versus firm ground, or shallow puddles versus dry soil, that are dangerous enough to get a robot stuck or damaged. Semantic perception can visually distinguish these cases, especially the trail the robot is meant to follow. However, camera-based systems are sensitive to lighting and visibility, making them unreliable on their own. By fusing geometry and semantics, we obtain a far more robust representation of what is safe to drive on.
We built a hiking trail dataset, labeling images into eight terrain classes, and trained a semantic segmentation model. Notably, the model became very good at recognizing established trails. These semantic labels were projected into 3D using depth and combined with the LiDAR based geometric terrain analysis map. Using a dual k-d tree structure, we fuse everything into a single traversability map, where each point in space has a cost representing how safe it is to traverse, prioritizing trail terrain.
The next step is deciding where the robot should go next, which we address using a hierarchical planning approach. At the global level, instead of planning a full path in a single pass, the planner operates in a receding-horizon manner, continuously replanning as the robot moves through the environment. We developed a custom RRT* that biases its search toward areas with higher traversability probability and uses the traversability values as its cost function. This makes it effective at generating intermediate waypoints. A local planner then handles motion between waypoints using precomputed arc trajectories and collision avoidance from the traversability and terrain analysis maps.
In practice, this makes the robot prefer staying on the trail, but not stubborn. If the trail ahead is blocked by a hazard, such as a large rock or a steep drop, it can temporarily route through grass or another safe area around the trail and then rejoin it once conditions improve. This behavior turns out to be crucial for real trails, where obstacles are common and rarely marked in advance.
We tested our system at the West Virginia University Core Arboretum using a Clearpath Husky robot. The video below summarizes our approach, showing the robot navigating the trail alongside the geometric traversability map, the semantic map, and the combined representation that ultimately drives planning decisions.
Overall, this work shows that robots do not need perfectly paved roads to navigate effectively. With the right combination of perception and planning, they can handle winding, messy, and unstructured hiking trails.
There is still plenty of room for improvement. Expanding the dataset to include different seasons and trail types would increase robustness. Better handling of extreme lighting and weather conditions is another important step. On the planning side, we see opportunities to further optimize how the robot balances trail adherence against efficiency.
If you’re interested in learning more, check out our paper “Autonomous Hiking Trail Navigation via Semantic Segmentation and Geometric Analysis”. We’ve also made our dataset and code open-source. And if you’re an undergraduate student interested in contributing, keep an eye out for summer REU opportunities at West Virginia University, we’re always excited to welcome new people into robotics.
Wall Street Journal writer Christopher Mims reports that while AI is plenty smart across a wide spectrum of tasks, too few people know how to use AI well.
Observes Mims: “There is a huge gap between what AI can already do today and what most people are actually doing with it.”
In other news and analysis on AI writing:
*Dead Heat: New Study Finds ChatGPT, Gemini, Claude Equally Powerful: A new study finds that ChatGPT, Gemini and Claude essentially deliver the same level of results when it comes to general AI use, agentic use, programming use and scientific reasoning use.
That’s gotta sting for Google, which just a few weeks ago, lunged ahead as the AI chatbot-to-beat across a wide range of benchmarks.
Even so, picking the best AI for your own use boils down to giving all contenders a thorough run-through on how you personally use AI — and then choosing a personal favorite.
For example: For AI-generated writing, I still strongly prefer ChatGPT 4.0, which is still the most creative writer of the bunch to this day.
*ChatGPT Still Most Popular AI – By a Mile: While Google has been coming on strong, ChatGPT still dominates the AI universe.
New analysis from Windows Latest, for example, finds that ChatGPT owns 64.5% of the market, followed by Google’s Gemini at 21%.
Somewhat embarrassing for Microsoft: Its Copilot Chatbot only commands 1% of the AI market.
*Free-for-All: AI Gmail Tools for Writing, Summarizing and Email Drafts Now Gratis: AI users just got a generous present from Google for 2026: Free access to a number of powerful AI tools for Gmail:
–Help Me Write, which helps you draft everyday emails in Gmail
–Suggested Replies, which reads your email and auto-generates a reply that includes context and tone
–AI Emails Summary, which pops-up offering a bulleted summary of key points extracted from an email thread
*ChatGPT for Power Users: A Curated Video Guide: Skill Leap offers an excellent rundown on advanced uses of the chatbot in this 17-minute video.
Among the picks:
–Creating different writing styles with ChatGPT for different use cases
–Scheduling daily or weekly reminders with ChatGPT
–Getting ChatGPT to ‘disappear’ certain chats for privacy reasons
*Microsoft Copilot: Rough Going for Gmail and Outlook Email Users: In an unusual move, Microsoft CEO Satya Nadella has openly admitted that Microsoft Copilot barely works with Gmail and Outlook Email.
Observes writer Matthias Bastian: “This wasn’t a one-off complaint. Over the past few months, Microsoft’s CEO has essentially become the company’s top product (Copilot) manager.”
“To close the technical gaps, Nadella is personally investing in recruiting. He calls potential hires himself and approves unusually high salaries to poach top talent from OpenAI and Google DeepMind.”
*Brain Rot?: Not Everyone Gung-Ho on AI in the Schools: AI’s push into K-12 and beyond has some educators worried that the tech will diminish critical thinking, cause developmental issues in the young and trigger a widespread cheating culture.
Observes writer Natasha Singer: “Teachers currently have few rigorous studies to guide generative AI use in schools.”
And “researchers are just beginning to follow the long-term effects of AI chatbots on teenagers and schoolchildren,” Singer adds.
*AI and the Law: What to Expect in 2026: Fourteen experts in AI law have released a free eBook serving-up their predictions on how AI will reshape the law in 2026 and beyond.
Key co-authors include:
–Richard Troman, founder, Artificial Lawyer – a media outlet
–Adam Wehler, Director of e-Discovery Strategies and Litigation Technology, Smith Anderson
–Melina Efstathiou, AI Strategic Advisor, Legal Data Intelligence
*Top Five AI Writing Tools for 2026: SSBCrack News has released its list of the top five AI writing tools for the coming year.
All are AI writing pioneers. And all have appeared on many top five and top ten lists for years now.
SSB’s Take: While no tool is perfect, these five tools balance features like content generation, editing and optimization.
*AI Big Picture: Chinese AI Running Seven Months Behind U.S.: Despite releasing head-turning, extremely inexpensive alternatives to top AI, China is still about seven months behind the U.S. in AI development.
The new study, released by Epoch AI, reveals that the trend has persisted since 2023, when Chinese alternatives to ChatGPT and similar began popping up on the market.
One downside to Chinese AI: Researchers have found that some Chinese AI apps include code that can be used to forward your data to the Chinese Communist Party.
Share a Link: Please consider sharing a link to https://RobotWritersAI.com from your blog, social media post, publication or emails. More links leading to RobotWritersAI.com helps everyone interested in AI-generated writing.
–Joe Dysart is editor of RobotWritersAI.com and a tech journalist with 20+ years experience. His work has appeared in 150+ publications, including The New York Times and the Financial Times of London.
The post Playing AI Catch-Up appeared first on Robot Writers AI.
Claire chatted to Christine Evers from University of Southampton about helping robots understand the world around them through sound.
Christine Evers is an Associate Professor in Computer Science and Director of the Centre for Robotics at the University of Southampton. Her research pushes the boundaries of machine listening, enabling robots to make sense of life in sound. Her current focus is embedding our understanding of the human auditory process into deep-learning audio architectures. This bio-inspired approach moves away from massive, internet-scale models toward compute-efficient and inherently interpretable systems – opening the door to a new generation of embodied auditory intelligence.
“Study Design”, and a member of the “Appendix” groups, she is Program Chair of IEEE RO-MAN 2027, she has been Robotic Challenge Chair at ICSR 2025, Special Session Chair of IEEE RO-MAN 2024, Publicity Chair of IEEE RO-MAN 2022 and 2023, Organising Chair of the 26th RoboCup International Symposium 2023, and she is on the program committee of several international conferences on human–robot interaction and artificial intelligence.