Happy Robot Team for RoboCup@Home 2026

This is the official website of the Happy Robot team from Kanazawa Institute of Technology, Japan, for evaluation in the RoboCup World Championship 2026, RoboCup@Home League.

Team Video

Photo of the robot Happy Edu

Fig.1 Happy Edu and its modular components

Since 2015, our robots have featured a friendly, approachable design to encourage acceptance among children, women, and the elderly in home environments. Based on this philosophy, we developed Happy Edu (Fig.1) in 2023—a small, lightweight, and affordable open-hardware robot aimed at lowering entry barriers for new RoboCup@Home teams.　For RoboCup 2026, we are implementing the following enhancements:

• Replacement of the 2D LiDAR with a 3D LiDAR

• Extension of the robot arm to 6 DoF with improved payload performance

Description of the approaches and information on scientific achievements

The Happy Robot team develops an open-hardware platform Happy Edu to lower entry barriers for RoboCup@Home and promote modular, extensible service robots. Our approach integrates multimodal perception, including speech interaction, open-vocabulary object recognition, and human-aware understanding.

Scientific achievements include a cost-effective 3D LiDAR–based re-identifiable human-following system that enables re-detection even after occlusion, ensuring robust tracking in domestic environments. We also proposed a foundation-model-driven planning framework for shelf display and disposal tasks, enabling adaptive decision-making without handcrafted rules. Additionally, we developed a robotic hand with four primitive motions for Bento assembly and a Fluorescent AR Marker method for automatic 6DoF pose annotation and estimation.

Team Descripton Paper

• HappyRobotTDP2026

Team Web Site

• https://demura.net/happyrobot2026

GitHub

• Team GitHub

Publications

• Book
  • These textbooks, based on our experience in RoboCup@Home, introduce the
    

    Fig.2: Introduction to AI Robot (2nd Ed.)

    fundamentals of robotics and AI together with practical programming using ROS2 and Python. They are widely used as university textbooks and for corporate training, and have become bestsellers in the field. Through these publications, we contribute to the RoboCup@Home community by supporting education, knowledge sharing, and the growth of new teams.

  • Kosei Demura, Yoshinobu Hagiwara, Yasuhiro Masutani, Jeffrey Too Chuan TAN: Introduction to AI Robot – Building and Learning with ROS2 and Python – , Revised Second Edition (in Japanese), Kodansha Ltd., Publishers, Feb, 2025 (Fig.2)
    • Overview
      This revised edition updates ROS 2 from Foxy to Humble, adopts actions and Cyclone DDS for greater stability, and integrates Whisper for improved speech processing. It also adds Nav2 Simple Commander, object segmentation, and new MoveIt and FlexBE programs for more practical manipulation and intuitive behavior planning.
    • Support site
      • https://github.com/AI-Robot-Book-Humble
  • Kosei Demura, Yoshinobu Hagiwara, Yasuhiro Masutani, Jeffrey Too Chuan
    

    Fig.3 Introduction to AI Robot (1st Ed.)

    TAN: Introduction to AI Robot – Building and Learning with ROS2 and Python –, First Edition (in Japanese), Kodansha Ltd., Publishers, Aug, 2022 (Fig.3)

• • • Overview
      This textbook guides readers in building AI robots using ROS2 and Python. It explains the integration of speech processing, navigation, image recognition, and natural language processing within ROS2, and provides example code and resources for practical implementation.
    • Support site
      • https://github.com/AI-Robot-Book

• Journal
  • Akitsugu Hasegawa, Kosei Demura: Development of a robot hand with four primitive motions for efficient assembly of various ingredients in Bento boxes, Advanced Robotics, 39(8) 441-456, 2025
  • Ren Matsubara, Kosei Demura: Development of a general-purpose gripper with selectable gripping method by jamming transfer and adhesion (in Japanese), Journal of the Robotics Society of Japan, 41(1) 61-71, 2023
  • Kosuke Mizutani, Nobuhiro Nagasawa, Kosei Demura: Development of automatic opening and closing shelf for convenience stores in cooperation with collaborative robot, Advanced Robotics, 36(23) 1241-1251, 2022
  • Shogo Okano, Tatsuhito Makino, Kosei Demura: Fluorescent Texture: Proposal of a 2-3D Automatic Annotation Method for Deep Learning (in Japanese), Journal of the Robotics Society of Japan, 40(1) 71-82, 2022
  • Mizuho Shibata, Kosei Demura, Shinichi Hirai, Akihiro Matsumoto:
    Comparative Study of Robotics Curricula, IEEE Transactions on Education, 64(3) 283-291, 2020

Team members

• Adviser: Prof. Kosei Demura, Dept. of Robotics, Kanazawa Institute of Technology. JAPAN
• Team Leader: Aoi Hayashi
• Members: Takuya Shimada, Yuta Okitsu, Kouki Sugimoto, Masaya Wada, Zinnsei Arai, Yamato Koizumi, Natsuki Sasaki, Keitatsu Sawanobori, Yoshiki Takahashi, Masami Takizawa, Yukitaka Tachibana, Sho Taniguchi, Masaya Watanabe
• Contact Person: Kosei Demura

Previous participation in RoboCup, local RoboCup tournaments, and rankings

• RoboCup World Championship
  • 2nd place in 2024 (@Home Playground)
  • 2nd place in 2023 (@Home Education Workshop and Challenge)
  • 5th place in 2018 (@Home league)
  • 9th place in 2017 (@Home league)
  • 8th place in 2016 (@Home league)
  • 9th place in 2015 (@Home league)
• RoboCup Japan Open
  • 3rd place in 2025 (Competition, @Home OPL)
  • 2nd place in 2025 (Open challenge, @Home OPL)
  • 3rd place in 2024 (Competition, @Home Bridge Competion)
  • 1st place in 2024 (Open challenge, @Home OPL)
  • 1st place in 2023 (Competition, @Home Education)
  • 1st place in 2022 (Competition, @Home Education)
  • 3rd place in 2017 (Competition, @Home OPL)
  • 1st place in 2026 (Competition, @Home Education)

The End