The joint team from the University of Bremen and the German Research Center for Artificial Intelligence (DFKI) won the World Championship in robot soccer in Incheon, South Korea. With a new robot platform, B-Human continues its winning streak.
The twelve-time world champion had been dominating the RoboCup Standard Platform League for years. This league has now merged with the former Humanoid League to form the new Humanoid Soccer League. For the first time, B-Human competed with a new robot platform: the Booster K1 humanoid robot from Booster Robotics.
The new Humanoid Soccer League is divided into three divisions: Small, Middle, and Large, which differ according to the size and weight of the robots. B-Human competed in the Middle Division with 15 other teams. This division is considered the successor to the former Standard Platform League because all teams currently use the same robot platform.
Larger and Faster Robots
The Booster K1 is significantly larger and faster than the NAO robot previously used in the competition. This makes the games considerably more dynamic. All teams use motion routines trained through deep reinforcement learning. While many participants relied on movements provided by the robot manufacturer, B-Human developed its own solutions for running, shooting, and standing up. This gave the team a decisive advantage. The team’s work also resulted in an academic paper, which was presented at the closing RoboCup Symposium.
In the Middle Division, the Bremen team won all eight games. B-Human dominated both the preliminary round and the semifinals. On average, the team scored 9.2 goals per game and conceded only 0.4.
In the final, B-Human faced the HTWK Robots from Leipzig University of Applied Sciences, Technology, Business, and Culture, who had previously won the world championship title in the Kid Size Division of the Humanoid League. B-Human won the final with a score of 6–0.
In addition to the world championship title, B-Human received the Best Software Award for their long-standing contributions to the competition's software infrastructure.
World Premiere: First 11-vs-11 Soccer Match
After the official competition, the teams took part in a world premiere: B-Human and the HTWK Robots played the first 11-v-11 soccer match between humanoid robots in RoboCup history. The match was played on a significantly larger field. The Bremen team benefited from its sophisticated passing game, a key component of its success in previous years. The match lasted one half, which B-Human won 4–0.
About B-Human
B-Human is a joint project of the University of Bremen and the DFKI’s research department for Cyber-Physical Systems, led by Prof. Dr. Rolf Drechsler. With numerous national and international titles, the team ranks among the most successful in RoboCup history.
In Incheon, the team consisted of ten University of Bremen students and one doctoral candidate. Dr. Thomas Röfer (DFKI Cyber-Physical Systems research department) and Dr. Tim Laue (Multisensory Interactive Systems research group, University of Bremen) provided academic supervision.
The company CONTACT Software, a leading provider of solutions for product processes and the digital transformation, has been the team’s main sponsor since 2017. Other supporters include Cellumation, Ubica Robotics, Just Add AI, and the University of Bremen Alumni Network.
https://www.b-human.de/index.html
B-Human players (in red shirts) in a one-on-one battle.
Source: Ayleen Lührsen
Copyright: Ayleen Lührsen
Criteria of this press release:
Journalists
Information technology
regional
Contests / awards, Miscellaneous scientific news/publications
English

You can combine search terms with and, or and/or not, e.g. Philo not logy.
You can use brackets to separate combinations from each other, e.g. (Philo not logy) or (Psycho and logy).
Coherent groups of words will be located as complete phrases if you put them into quotation marks, e.g. “Federal Republic of Germany”.
You can also use the advanced search without entering search terms. It will then follow the criteria you have selected (e.g. country or subject area).
If you have not selected any criteria in a given category, the entire category will be searched (e.g. all subject areas or all countries).