📢 AIRoA has released its robot foundation model, "AIRoA-0" (A-0)! 📢
A-0 learns from 16,151 hours of manipulation data recorded by people using the YUBI handheld gripper, without robots. It can perform bimanual tasks such as towel folding and small-parts sorting in environments different from those where the data was collected.
We have also verified its responses when a person moves sorting bins during a task, as well as its operation on four platforms equipped with YUBI: Franka, TX-G2, OpenArm, and UR.
📦 Open-Source Assets:
・Pre- & post-trained model weights (Hugging Face)
・Data collection, post-training, and example inference code (GitHub)
・A technical report detailing methods and evaluation benchmarks
Post-training on your own task data can also be completed in under four hours.*
(*Using a single node with eight H200 GPUs.)
Check it out and let us know your feedback!
airoa.org/updates/20261106/8…#AIRoA#RobotLearning#PhysicalAI#Robotics#VLA
AIRoA Director Genki Sano (Telexistence Inc. Co-founder, CTO) delivered a talk titled "The Current State of Physical AI in Japan and Prospects for Social Implementation" at NexTech Week 2026 [Autumn], held at Makuhari Messe on November 12.
The talk covered the latest trends and technical challenges in physical AI, as well as AIRoA's work on real-world data collection and robot foundation model R&D.
Thank you to everyone who attended.
We will continue working toward a physical AI ecosystem originating in Japan.
#NexTechWeek#PhysicalAI#AIRoA
Today at #CoRL2026 — The UMI Arena: From Handheld Devices to Real-World Policies 🤖
After months of preparation, we’re excited to bring the UMI Arena to Austin today.
The workshop brings together researchers working across data collection, robot learning, and real-world deployment through three tracks:
🦾 Policy Competition — evaluating policies on shared real robots and common tasks
🖐️ Device Exhibition — hands-on trials of UMI-style data-collection devices
📄 Contributed Papers — new research on data collection, cross-embodiment deployment, VLA models, tactile sensing, benchmarking, and more
The program includes 30 accepted papers, 13 devices, 6 spotlight talks, live robot demonstrations, and invited talks.
🏆 Awards will also be presented for Best Policy, Best Device, and Best Paper.
📅 Today, Nov. 12 | 14:00–18:00
📍 JW 303–304, JW Marriott Austin
If you’re at CoRL, come join us this afternoon for hands-on demos, real-robot evaluation, and discussions around the future of UMI-based robot learning.
Workshop details:
umi-arena.airoa.io/#AIRoA#CoRL2026#RobotLearning#Robotics#PhysicalAI#UMI#Workshop#Awards
We are excited to announce that AIRoA’s workshop proposal, “The UMI Arena,” has been accepted at CoRL 2026!
At the UMI Arena, participating teams will compete by deploying their robot control policies on shared tasks in a common real-robot environment.
To support model development, a subset of real-world robot manipulation data collected using the YUBI data-collection device will be provided exclusively to participating teams, together with a reference policy model and training code. We plan to expand the data available to participants in stages to approximately 20,000 hours by September 2026.
The workshop will feature three tracks:
・Policy Competition
・Data-Collection Device Exhibition
・Paper and Poster Session Through
these tracks, we aim to build a shared real-robot evaluation platform and advance the standardization of evaluation methods.
Invited speakers are expected to include Shuran Song, Andy Zeng, Hao-Shu Fang, and Yang Gao.
■ November 12, 2026 | Austin,
Texas Learn more ▼
airoa.org/updates/20260821/6…
Workshop website ▼
umi-arena.airoa.io/#AIRoA#CoRL2026#RobotLearning#Robotics#PhysicalAI#YUBI
📍 Where to find AIRoA at CoRL 2026
Not sure how to get from our exhibition booth on the 2nd floor to the Demo Area on the 3rd floor?
We made a short video to show you the way 👇
Today, Nov. 10, you can find us at:
🤖 Exhibition Booth #210 — 2F
Meet the AIRoA team, try YUBI, see the ELEY demo, and take a spin on our YUBI-powered gacha.
🦾 Demo 7 — 3F
See A-0 / YUBI on Franka in action throughout the day.
And you can find more AIRoA research across CoRL:
✏️AIRoA-0: a robot foundation model trained on 16,151 hours of handheld YUBI data, released with open weights and code.
Led by Yueh-Hua Wu & Kei Ota with the AIRoA team. Booth 210 and Demo 7.
Project: a-0.airoa.io/
✏️S2 (See Less Specify More): goal-preserving local language plus a learned visual evidence budget, so VLAs act only from task-sufficient cues.
Led by Yueh-Hua Wu. Poster 25, Tue, Nov 10 PM.
Project: s2.airoa.io/
✏️Counter Align: counterfactual relabeling that turns expert demos into an instruction-grounded reward for offline RL.
Led by Haru Kondoh and Yueh-Hua Wu, Poster 31, Tue, Nov 10 PM.
Project: counteralign.airoa.io/
✏️YUBI: a finger-aligned handheld gripper for bimanual data collection at scale, with open hardware, software and data.
Led by Take Ohkawa & Jumpei Arima. Poster 267, Wed Nov 11 AM and demo session.
Project: yubi.airoa.io/
✏️YUBI-Real2Sim: 3DGS scene verification that tells when a real-to-sim scene is good enough to rank policies. By Hiroki Nishizawa. Late Breaking Results & UMI Arena Paper track, Tue Nov 10 lunch, board 126.
Paper: lnkd.in/g8CgMB39
✏️YUBI-STAG: automatic contact- and object-grounded language for demonstrations that aligns VLAs with fine-grained instructions.
Led by Masatoshi Tateno and Take Ohkawa. Spotlight talk at The UMI Arena.
Project: lnkd.in/gwtMwhyT
✏️RoboPace: contact-aware retiming that runs action chunks fast in free space and slows down at contact, with no retraining.
Led by Mimo Shirasaka and Kei Ota. UMI Arena Paper track.
Project: lnkd.in/gm8G5ieR
✏️YUBI in the Dark: tactile sensing on a handheld gripper that guides manipulation when vision fails.
Led by Yuma Shin with Asako Kanezaki, Rei Kawakami, and Kei Ota. UMI Arena Paper track.
Paper list: lnkd.in/gHCTQVUX
✏️YUBI Go: an open-source Quest app that records bimanual YUBI demonstrations anywhere. Led by Yuki Noguchi with Yuya Kanai and Kengo Ikeuchi. UMI Arena Device Track.
Code: lnkd.in/gD3DbxS5
🍽️ Networking Dinner — Nov. 10 evening
AIRoA is also hosting a networking dinner tonight. If you’re interested in joining, feel free to send us a DM.
Come find us at the booth, demo, posters, talks — and dinner!
#AIRoA#CoRL2026#RobotLearning#PhysicalAI#Robotics#VLA#Demo
AIRoA has arrived at CoRL 2026! 🤖🇺🇸
Our booth is all set up, and day one is almost wrapped up. Huge thanks to everyone who helped with the setup — great work today ☕️
Starting tomorrow, you can catch Franka / YUBI at the Demo Booth, and at our exhibition booth #210, we’ll have live demos of ELEY and hands-on YUBI experiences.
We’ll also have a gacha capsule machine you can spin using YUBI 🎁
On Nov. 12, AIRoA will also host the workshop “The UMI Arena: From Handheld Devices to Real-World Policies.”
More details: umi-arena.airoa.io/
If you’re attending CoRL 2026, please stop by the AIRoA booth and say hello!
#AIRoA#CoRL2026#RobotLearning#PhysicalAI#Robotics#VLA#Gacha#Demo
Three AIRoA research papers and a YUBI(Yielding Universal Bidigital Interface) demo proposal have been accepted to #CoRL2026! 🎉
Find us in Austin for:
• 3 paper presentations
• Interactive YUBI demo in the official Demo Area, Nov 9–10
• “The UMI Arena” workshop, Nov 12
• Live Franka + YUBI and ELEY demos at Booth 210
🔗 airoa.org/updates/20261028/7…#RobotLearning#Robotics#PhysicalAI#VLA
We are exhibiting at CEATEC 2026
Building robot foundation models for the world, right from Japan. Visit our booth to learn about our initiatives toward the social implementation of Physical AI, featuring live demonstrations on physical robots.We look forward to seeing you at our booth.
📅 October 13 (Tue) – 16 (Fri), 2026
📍 Makuhari Messe Hall 5 General Exhibits area
NEDO Booth, “AI & Robotics” area (Booth No. 5H440)
Exhibits:
・YUBI (Yielding Universal Bimanual Interface): A handheld device designed for collecting robot learning data
・Foundation Model Demo: Demonstration of a foundation model trained on YUBI-collected data, deployed on a Franka Research 3 robot that autonomously executes tasks based on language instructions
・Prototype Robots: Select prototype units developed in Japan’s national general-purpose robot development competition
#CEATEC2026#CEATEC#NEDO#AIRoA#Robotics#幕張メッセ#Physicalai
📢 AIRoA will participate in the 1st International Workshop on Industrial Applications of Robot Learning at #IROS2026 on Sep. 27 in Pittsburgh.
AIRoA President Tetsuya Ogata will give an invited talk, while Head of AI and Robotics Kei Ota joins as an Organizer.
From research to real-world deployment, the workshop will explore the future of industrial robot learning and recognize outstanding work through its Research Awards.
🔗 airoa.org/updates/20260921/7…#RobotLearning#PhysicalAI#Robotics#AIRoA
The Physical AI Summit wrapped up with a great reception!
AIRoA Chairman Ogata @tetsuyaogata1presented our initiatives in robot foundation model development and data ecosystem building.
After the evening reception leaders from industry, academia, and startups were brought together for rich invigorating discussions.
Thank you to everyone who was able to joinus.
Stay tuned for more from AIRoA.
airoa.org#フィジカルAISummit#AIRoA#Robotics#PhysicalAI
Physical AI Summit is now open! AIRoA joins as a Special Supporting Sponsor.
Prototype Exhibition: 9:00–17:00
Showcasing the latest prototypes from companies selected fromJapan's General-Purpose Robot Development Competition.
Company Pitches: 9:50–10:30
Panel Discussion: from 14:20
Theme: "Challenges in Japan's Robot Supply Chain and Expectations for Government and Industry"
Panelists:
· Hiroyuki Osone (EmplifAI, President & CEO)@emplifai
· Teruki Ito (NACHI-FUJIKOSHI, Deputy General Manager, Robot Development Div.)
· Takashi Tokuda (Keigan, Representative Director & CEO)@KEIGAN_PR
· Koichi Yamada (ugo, CTO)@ugo_robot
Moderator: Secretary General Okada, AIRoA
See Link for full program details.
nextech-week.jp/aisummit/ja-…#フィジカルAISummit#AIRoA#Robotics#PhysicalAI
Today, September 15, AIRoA CTO Tatsuya Matsushima will join a panel discussion at “The 4th GMO Conference Autumn Physical AI 2026.”
The session theme is:
“Creating Training Data for Physical AI — Collecting in the Real World or Generating Synthetically?”
The panel will discuss how real-world and synthetic data can be used together, the current state of training data, and key challenges around data collection and utilization from industry, government, and academic perspectives.
A live stream will also be available — please tune in!
▼ Event details
group.gmo/security/conferenc…#AIRoA#PhysicalAI#Robotics
AIRoA-related presentations at #RSJ2026 | Sep 4
9:00 | 3A1-01
Toward an Open Robot Foundation Model from Japan — AIRoA’s Data Ecosystem Vision
Kei Ota
9:12 | 3A1-02
AIRoA MoMa 5k: A Large-Scale Compositional Mobile Manipulation Dataset and Continual Pretraining of VLAs
Tatsuya Matsushima
10:32 | 3A2-02
See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs
Kei Ota
11:08 | 3A2-05
Personal Embodied Agent: A Robot That Grows as Part of the Family
Yuga Yano
13:20 | 3A3-01
Vision-based 6DoF Gripper Pose Estimation with a Fiducial Cube for the Portable YUBI System
Takehiko Ohkawa
13:56 | 3A3-04
Optimizing VLA Inference Under Robot Dynamics Constraints
Kei Ota
14:44 | 3A3-08
Building a Real2Sim Conversion Platform Using 3D Reconstruction and Evaluating VLA Policies
Takehiko Ohkawa
16:20 | 3B4-06
Data Collection with a Tactile-Sensing Portable Gripper and Training Tactile-Aware VLA Models
Yuma Shin
We look forward to seeing you at the presentations and at the AIRoA booth.
#AIRoA#RSJ2026#PhysicalAI#Robotics
AIRoA-related presentations at #RSJ2026 | Sep 2–3
■ Sep 2
13:56 | 1D3-04
Building and Deploying an Experimental Platform for Continuous Autonomization of Home Service Robots
Yuga Yano
■ Sep 3
9:12 | 2A1-02
Large-Scale Dataset Construction Using a Bimanual Humanoid Robot
Kei Ota
9:36 | 2A1-04
Offline Reinforcement Learning for Vision-Language-Action Models with Counterfactual Supervision
Kei Ota
10:32 | 2A2-02
YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale
Takehiko Ohkawa
11:08 | 2A2-05
Continuous Reasoning for Vision-Language-Action
Kei Ota
11:32 | 2A2-07
Omni-Supervised Policy Learning for Robot Manipulation
Tatsuya Matsushima
13:32 | 2A3-02
System Development Supporting Large-Scale Data Collection for Building Robot Foundation Models
Takuya Okubo
14:44 | 2A3-08
Zero-shot Temporal Action Segmentation for Bimanual Gripper Manipulation
Takehiko Ohkawa
Hardware demos and VLA demonstrations will also be available at the AIRoA booth.
#AIRoA#RSJ2026#Robotics
[Research & Development Partner Wanted]
Join us in advancing large-scale robot data collection with YUBI (Yielding Universal Bidigital Interface)!
AIRoA is looking for research collaboration partners from academia and industry to work with us using YUBI.
1. Community-scale data collection — expand our open dataset together
2. On-demand task collection — we collect the task data you need, free of charge, and release it publicly
3. Deployment on your robot — bring YUBI-trained policies to your own platform
If you're an engineer or researcher looking to accelerate robot learning through open data, check out the video.
We will also be showcasing YUBI with a live demo at our booth at RSJ 2026 (September 2–4). Come stop by!
youtu.be/o2pTYOngsho?si=2z0n…
Special Thanks: @TOYOTA_FRC#AIRoA#Robotics#OpenSource#Engineers#RSJ2026