Axis is officially LIVE on @base. 🔵
Axis is scaling Physical AI for the real world, contributed by everyone.
You can control robots in a virtual world, generate training data at scale, and help build the brain behind tomorrow's robots. All from browser. No hardware needed.
Start building robotics intelligence today: hub.axisrobotics.ai
7/7 Built on open data
Our open Franka task datasets are in LeRobot v3.0 format: Parquet + MP4 at 15 fps, third-person and wrist cameras, joint states, actions and end-effector pose per frame.
14.6 TB of data is open on Hugging Face, with a sample task ready to download.
Need a skill, custom task data or a commercial licence? Tell us your robot, tasks and eval goal: partnerships@axisrobotics.ai
6/7 Task explorer
Search by task name, or filter by:
• Skill
• Robot
• Scene: kitchen, workshop, office, home and more
• Difficulty: 1-5 stars
Watch demos, build a shortlist and export it as CSV.
5/7 Skills in combination
Real tasks are rarely a single motion. A single task can draw on several skills at once. In the Atlas, 3,533 tasks bring Pick and Place together, and 1,703 span Pick, Place, Stack and Transfer.
Open any combination to see the exact tasks that match it.
4/7 Skills across 6 embodiments, with more on the way
They range from the Franka Panda fixed-base arm and the PandaOmron wheeled base to dual-arm systems like the OpenArm V2 and the Booster T1 humanoid.
Select a skill to see which embodiments have it, or an embodiment to see its full task set.
2/7 Why this matters
The bottleneck for Physical AI is data, and the data has to be usable.
The Skills Atlas is the visible output of the AXIS data engine: what it has built, skill by skill, embodiment by embodiment, and what you can download today.
Robotic skills, distilled from 11,199 real manipulation tasks and 14.6 TB of open data.
Introducing the AXIS Skills Atlas: every skill mapped across embodiments, each number opening the real tasks behind it.
skills.axisrobotics.ai/
6/6 Simpler rules
Your Post-TGE Season 2 points are treated the same way as Season 1 points.
Referrals, scores and Challenger multipliers are gone. Your reward now depends only on the task you sign, and the leaderboard ranks $AXIS earned.
Alliance tasks earn $AXIS too.
5/6 Claim weekly
The amount shown the moment you sign is the amount you get.
Rewards settle every Saturday at 10:00 UTC. Open Portfolio-Rewards, and claim straight to your wallet on Base.
Miss a week and nothing is lost. Unclaimed $AXIS never expires.
Live: Sat 14 Nov, 10:00 UTC.
First claim: Sat 21 Nov, 10:00 UTC.
4/6 Harder tasks pay more
Per signed trajectory:
2 star: 1 $AXIS
3 star: 1.5
4 star: 2
5 star: 2.5
Practice and one-star tasks are for learning and pay 0. Five-star tasks need the Seek the Unseen badge. New badges are granted every weekend and stay yours for good.
3/6 Know your reward
Each task can be completed up to 5 times per person. Failed runs don't count.
Every verified, signed trajectory earns its task's $AXIS. Before you start, each task shows what one signed trajectory pays and the full task pool.
2/6 What changes
Pre-Training Season 1 is complete. All work from that phase is settled under the Points rules.
From Season 2, the focus moves to real-world deployment. We're targeting what models still can't do, and the reward pool is paid directly in $AXIS.
Every trajectory now earns $AXIS.
Points are done. From Saturday 14 November, every verified, signed trajectory earns $AXIS, and you can claim it every week.
Explore now: hub.axisrobotics.ai/
How it works ⬇️
We’ve been using ODE Policy for visual policy distillation, with strong early results. Learning how actions evolve over time gives the policy a natural way to capture the continuity of robot motion.
In the video, our Franka robot learns to thread a nut onto a bolt in simulation, reproducing the task from SGS.
Next, we plan to use ODE Policy to distill a wider range of assembly skills into policies that act from camera images, from fitting gears and inserting pegs to joining connectors.
🚀 Nature does not move in discrete jumps. Why should robot policies?
Super excited to release ODE Policy — perhaps our most exciting breakthrough in my lab this year! 🤖🔥
Think about how humans reach for a cup. Our movements evolve continuously, governed by underlying dynamics. Yet, most robot policies — from Diffusion and Flow Matching to VLAs — learn to predict explicit actions.
What if robots learned how actions evolve, instead of predicting actions?
💡 That's ODE Policy for Embodied AI.
We use a neural Ordinary Differential Equation (ODE) to learn continuous action dynamics, rather than directly generating actions.
One simple idea. Five types of robots. Multiple learning paradigms.
✅ Single-arm manipulation
✅ Dual-arm manipulation
✅ Dexterous hands
✅ Humanoid whole-body control
✅ Aerial robots
And it goes far beyond imitation learning:
⚡ VLA (π0.5): 96.0% vs. 75.5% success after one epoch.
🌍 4.5B World Action Model: 82.6% vs. 24.6% success, with ~4× faster action generation.
🏃 RL: More efficient humanoid whole-body motion learning.
For years, we've focused on scaling robot data, models, and compute.
But what if the next fundamental breakthrough comes from rethinking WHAT robots learn, rather than just HOW MUCH they learn?
Huge congratulations to Jindou Jia and our amazing team! 👏
📄 Paper: arxiv.org/abs/2611.01729
🌐 Project: ntumars.github.io/ODE/#ODEPolicy#EmbodiedAI#PhysicalAI#RobotLearning#WorldModels#VLA#MARSLab