Ontos retweeted
Robot-2-Robot Markets are just one example of the global markets SEDA's infrastructure is now serving.
We're evolving from an oracle to necessary infrastructure for the merger of global markets onchain.
study: @OntosWorld + @peaq
“10 years from now, there could be well over 1 billion humanoid robots” — Elon Musk
SEDA= Verification layer for robotic tasks
@peaq= Blockchain for machines
Ontos= Machine understanding of physical environments
Ontos retweeted
Cross Embodiment training sets are coming to P37 Neuro today.
I won’t be active here for the whole day but will put you all up to speed.
Introducing P37 Neuro, our open-source robot brain at @OntosWorld.
For a while, we’ve been working on a question:
Can we build a robot brain that keeps working when the body or task changes?
P37 Neuro is part of our answer.
The system is designed to understand the body it controls, interpret the state of the robot and its environment, follow a task or demonstration, and turn that information into physical actions.
A new robot or task shouldn’t always require a completely new model.
P37 has an embodiment layer that represents the robot itself, high- and low-level policies for planning and control, and memory that carries context across actions and failures.
It also supports reinforcement learning, simulation in MuJoCo and Isaac Lab, and a C++ runtime that connects the learned policy to the physical machine.
Around the model, we’ve built the infrastructure for training, evaluation, safety, model releases, fleet feedback, and rollback.
The current software path covers P37-E0 through E6.
We’ve begun testing the ideas behind the system.
A shared model has been trained across different synthetic robot morphologies and evaluated on bodies it had never encountered during training.
We’ve also tested demonstration conditioning on unseen tasks, with no fine-tuning during evaluation.
For the memory tests, we gave the model information before a simulated failure, then compared its performance when that memory was preserved and when it was removed.
Ontos retweeted
Our product briefing page remains available for enterprises and developers exploring and building inference solutions for robotics and hardware applications.
You can also explore our open-source products and developer resources on our website, designed to support innovation and accelerate real-world AI deployment.
A robot navigating a crowded warehouse needs to account for more than the obstacles it can currently see. People move, pathways become blocked, and objects change position.
World models give robots a way to represent these environments and estimate how they might evolve over time.
Using observations from sensors and knowledge of physical dynamics, a world model can predict possible future states under different actions. A robot can use these predictions to evaluate a route, anticipate an interaction, or adjust its plan when conditions change.
For manipulation tasks, this could mean estimating how an object will move when pushed, whether a grasp will remain stable, or where an object might land.
These predictions are imperfect, particularly in unfamiliar environments. Robots need to continually update their understanding using real-world feedback.
Building reliable world models is an active area of robotics research, with implications for navigation, manipulation, and longer autonomous tasks.
A simple product scan can be the start of a verifiable record.
We built Ontos Verify to help developers connect physical-world activity with onchain verification.
A machine reads a barcode, QR code or NFC tag. The software collects the required evidence, and verification checks it against defined conditions, with the result linked to an onchain record.
Built for applications where machines need to prove what happened in the physical world.
Ontos retweeted
Diving deeper into machine-executed data settlement next week with @promiseeuler from @OntosWorld
Ontos retweeted
Ontos World Robots are entering the workforce
@sedaprotocol is their data layer
@peaq is their blockchain
@OntosWorld how they translate real world.
Love seeing the growth from the Ontos team and looking forward to talking more about what's happening here.
note: Ontos is still in testnet and under development, but a very cool story unfolding
P37 Neuro is Ontos’ general-purpose robot intelligence system, built to learn across different robot bodies, understand task context, and turn it into physical action.
The images show the core P37 Neuro flow: how different robot bodies are represented, how sensor and machine state become structured context, how that context is turned into physical action, and how the system learns and is evaluated across simulation and real-world environments.
Ontos retweeted
We’re opening product briefings with a small number of teams working across robotics and physical AI.
we’ve built a growing set of products around machine reasoning, spatial understanding, machine identity, coordination, and real-world deployment.
Request access to a briefing 👇👇
We built P37 Neuro around a goal of having one robot brain that can work across different bodies and tasks without requiring a completely new model every time.
The core system is now open source.
P37 brings together embodiment understanding, task context, memory, learned control, simulation, reinforcement learning, and a deterministic runtime for physical machines.
This is the foundation we are building on as we move into larger-scale simulation and physical validation.
If you work in robotics or physical AI, we’d like you to test it and build with us.
Get started here 👇👇
Introducing P37 Neuro, our open-source robot brain at @OntosWorld.
For a while, we’ve been working on a question:
Can we build a robot brain that keeps working when the body or task changes?
P37 Neuro is part of our answer.
The system is designed to understand the body it controls, interpret the state of the robot and its environment, follow a task or demonstration, and turn that information into physical actions.
A new robot or task shouldn’t always require a completely new model.
P37 has an embodiment layer that represents the robot itself, high- and low-level policies for planning and control, and memory that carries context across actions and failures.
It also supports reinforcement learning, simulation in MuJoCo and Isaac Lab, and a C++ runtime that connects the learned policy to the physical machine.
Around the model, we’ve built the infrastructure for training, evaluation, safety, model releases, fleet feedback, and rollback.
The current software path covers P37-E0 through E6.
We’ve begun testing the ideas behind the system.
A shared model has been trained across different synthetic robot morphologies and evaluated on bodies it had never encountered during training.
We’ve also tested demonstration conditioning on unseen tasks, with no fine-tuning during evaluation.
For the memory tests, we gave the model information before a simulated failure, then compared its performance when that memory was preserved and when it was removed.
Ontos retweeted
Introducing P37 Neuro, our open-source robot brain at @OntosWorld.
For a while, we’ve been working on a question:
Can we build a robot brain that keeps working when the body or task changes?
P37 Neuro is part of our answer.
The system is designed to understand the body it controls, interpret the state of the robot and its environment, follow a task or demonstration, and turn that information into physical actions.
A new robot or task shouldn’t always require a completely new model.
P37 has an embodiment layer that represents the robot itself, high- and low-level policies for planning and control, and memory that carries context across actions and failures.
It also supports reinforcement learning, simulation in MuJoCo and Isaac Lab, and a C++ runtime that connects the learned policy to the physical machine.
Around the model, we’ve built the infrastructure for training, evaluation, safety, model releases, fleet feedback, and rollback.
The current software path covers P37-E0 through E6.
We’ve begun testing the ideas behind the system.
A shared model has been trained across different synthetic robot morphologies and evaluated on bodies it had never encountered during training.
We’ve also tested demonstration conditioning on unseen tasks, with no fine-tuning during evaluation.
For the memory tests, we gave the model information before a simulated failure, then compared its performance when that memory was preserved and when it was removed.
Ontos retweeted
Introducing Sense, an open-source SDK for physical machine context.
We built Sense at Ontos while testing our reasoning model for physical machines that required peaq services.
The idea is simple: a model should not only understand a machine, it should also know what that machine can actually do right now based on its current state.
Sense takes live data like battery level, safety state, connectivity and sensor health, and turns it into capability states:
AVAILABLE<>DEGRADED<>UNAVAILABLE<>UNKNOWN
It runs locally, works with ROS 2, MQTT and HTTP, and can also publish capability changes as peaq Activity Events.
We open-sourced it so developers can test it with different machines, extend it, and help us explore better ways for machines to communicate what they can actually do in the real world.
Ontos retweeted
We built a 3B parameter model at Ontos focused on physics and mathematics for robotics, and we are benchmarking it against frontier models using public, independently verifiable benchmarks and published research.
For robots, perception is not enough. They also need to reason about spatial relationships, motion, force, geometry and how objects interact in the physical world.
That is what we are building this model for.
We are currently testing it against much larger frontier models on physics, applied mathematics, rigid-body dynamics, kinematics, geometry, mainly to measure how much physical reasoning and spatial reasoning we can get from a smaller model.
The model is already in private testing with a few dev partners.
We will share the benchmark results, more technical details and the launch date soon.
A big part of robotics for us is getting machines to build a better understanding of the physical world they operate in.
Ontos retweeted
Spent part of the weekend pushing a few new developments at @OntosWorld and setting up what I want us to test this week.
I have also been watching how fast the space is moving.
World Labs is pushing further into spatial intelligence with the new atlas release. NVIDIA continues to expand its robotics stack, and Physical Intelligence is making progress toward more general robotics.
There is a lot happening, but also a lot that still needs to be built.
Looking at this image gives me a very clear thinking path around where all of this can go. There is so much to do, so much to test, and a lot we still want to prove.
I am very optimistic about the direction we are taking.
We are here to win.
Ontos retweeted
You cannot keep every AI model on a robot running at full speed all the time.
The robot is using the same battery to move, run its cameras, read its sensors, and stay connected. The models also need power, so I have to decide which ones should run and when they are needed.
Some things just need a quick answer. The robot needs to know when something is in its way, when it should stop, and how to keep moving safely, that work needs to happen on the robot.
A larger planning task can wait a little longer. The robot can ask for help with the plan when it needs it, then continue the task using the models it already has within it.
These are a few notes on how we manage different instances for robots at ontos, you need to identify what needs to be used at every single time
ALT Where should the model run on a robot