System identification (sysid) is the process of finding the... physical parameters that make a simulation match reality. If you're training an RL locomotion policy in simulation, the accuracy of your motor model directly affects how well the policy transfers to the real robot. A recent git commit by Kevin Zakka added a sysid toolbox to MuJoCo which automates this process: you provide recorded motor data and a MuJoCo model, and it optimizes the model parameters to minimize the difference between simulated and real trajectories. For my RobStride Dynamics RS02 QDD motors (17 Nm peak, 7.75:1 gear), I built a Rust tool that sends multi-sine torque excitation at 1 kHz and records position/velocity feedback. I then feed this data into MuJoCo's sysid optimizer.show more

This is how Strike Robot turns Simulation into Reality!... One of the biggest challenges in robotics is ensuring that behaviors validated in simulation work reliably in the real world. For this experiment, we reconstructed part of a real laboratory at Eastworlds inside SR Platform. The generated layout was then deployed into MuJoCo. Using SR Agentic, the robot was tasked with finding abnormal objects in a cluttered environment and sending a Telegram notification when detected. Before deployment, everything is validated in simulation.show more

Excited to share a few presentations, demos, and workshop... talks from our group and collaborators at #ICRA2026! We will present recent work on real-to-sim-to-real robot policy evaluation, model-based planning with learned dynamics, and multi-modal manipulation. We will also have a joint live demo between SceniX and Analog Devices, Inc. on real-to-sim-to-real cable manipulation at the ICRA exhibition. This is a small teaser of what we have been building, with more to come soon! If you are at ICRA, please stop by the sessions or the demo booth. Happy to chat about robot learning, simulation, world models, and sim-to-real!show more

I've gotten a mujoco sim RL training loop for... a unitree robot at 200k SPS. I'm looking into the physics for friction, contact dynamics. My goal: can I reproduce & beat the mujoco playground RL baselines This is running in my web browser with raylib. Its the baselineshow more

Guys, I translated the model into English, but unfortunately,... for some reason, the parameters were hidden when I added it - I'm so sorry! Here’s how to translate the model into English and reveal the customization parameters.show more

System ID for legged robots is hard: (1) Discontinuous... dynamics and (2) many parameters to identify and hard to "excite" them. SPI-Active is a general tool for legged robot system ID. Key ideas: (1) massively parallel sampling-based optimization, (2) structured parameter space, and (3) active exploration based on Fisher Information to collect the most informative data in real. SPI-Active provides an accurate robot model and effectively reduces the sim2real gap. In sim2real policy learning setting, it outperforms baselines by 42-63% in various quadruped & humanoid tasks. Led by Nikhil Sobanbabu Guanqi Heshow more

A simple MPC controller for path tracking implemented in... python. Few resources actually teach it without assuming a PhD first. This open-source project does exactly that: An iterative MPC tracking controller (built with CVXPY and MuJoCo) that shows how to make a robot (or autonomous vehicle) follow a path and avoid obstacles in real time. → Autonomous logistics, robot navigation, vehicle control; there's a path-following algorithm behind all of it. → Most implementations are black boxes. This one shows you what's actually happening. → It uses convex optimization (no non-linear solver), and still handles real vehicle physics through iterative linearization. What makes it practical is that you can run it with the mushr car model in MuJoCo, or headless without any physics simulation if you just want to understand the logic. If you're making the jump from classical control to real-time optimisation, this is a very good starting point. 📌 Repository: ——- Weekly robotics and AI insights. Subscribe free:show more

A visualisation of different velocity factors in a PCB.... Both simulations use the same excitation and port parameters. Only the permittivity is different, showing how the signal travels much faster in low Dk dielectrics. This simulation shows an embedded trace. A signal on an outer layer also travels faster because part of the EM field propagates through air, which has a Dk very close to 1show more

In flow matching, a coupling determines how noise and... data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.show more

Super excited about Hydra-0 from Hongyu Li and team!... The key idea is to use flow as a shared visual interface across embodiments/objects for controllable video generation, allowing a single generalist world model to learn from human, handheld-gripper, and robot interaction data. My favorite result is the video below: start from a real video of a human doing the task (left), extract the desired object flow, and condition the model on that flow (right). The model then hallucinates a plausible robot motion that could produce the same object motion. Very cool glimpse of how a generalist world model can bridge human demonstrations and robot control.show more

hi all, excited to join! i'm building an expressive... mini "shoggoth" robot which will eventually be hooked up to gpt4o realtime voice. i'm currently working on the low-level policies, which are trained in a mujoco simulation with RL. to delay working on raw-pixels for now, i trained a pose-estimation model using deeplabcut and triangulate the position in 3d space using the stereo cameras. eventually, i'll use gpt4o's tool calling capabilities to activate several of these policies (closed and open loop) based on the dialog flow! captions: manual actuation of the tentacle / 3d pose estimation / target designshow more

A $50B market. A new model for data. And... a Reserve that grows with every customer. If Pyth captures even 1% of the institutional data market, that’s $500M ARR flowing into the PYTH Reserve. This is the scale of what’s ahead.show more

A Letter to Our Community: The Road Ahead for... Robotics To our Community and Partners, As we step into 2026, our mission at Axis is clearer than ever: Constructing the definitive End-to-End Scaling Layer for Robotics. Our goal is to accelerate the transfer of diverse human intelligence into Robotics General Intelligence (RGI). By owning the critical path of intelligence creation, we are turning the physical limitations of robotics into a scalable, software-driven future. Here is our strategic outlook and roadmap for the year ahead. The Core Thesis: Simulation is the Only Way Out The path to RGI is currently blocked by Data Scarcity, Generalization Fragility, and Hardware Fragmentation. At Axis, we believe Simulation is the only way out. Our Simulation Data Platform and Data Augmentation Engine transform raw data into "Synthetic Gold". Backed by academic milestones like Roboverse, Skill Blending, and GraspVLA, we have proven that pure simulation can achieve the generalization required for the real world. We don’t just collect data; we architect it. The Engine: Why Crypto? We believe RGI should come from all, not a few. Crypto is not just a feature; it is the primitive that powers our entire ecosystem flywheel: - Incentive Mechanism: Democratizing contribution and rewarding the trainers and developers. - Assetization: Turning proprietary data and refined models into liquid, ownable assets. - Verifiable Workflow: We are opening the "Black Box" of AI. By bringing total transparency to the Task Generation → Data Collection → Model Training pipeline, we ensure every byte of intelligence is verifiable, traceable, and secure. 2026 Strategic Deliverables This year, we are committed to delivering three foundational pillars: - The World's Largest Training Dataset for Robots: A robot training set—diverse, high-quality interaction data at an unprecedented scale. - A Robotics Foundation Model: A universal robotic brain trained on our pure simulation and synthetic data, capable of robust cross-embodiment transfer and open-world adaptability. - Evolvable Robot Hardware: Robots deployed with Axis models that autonomously evolve through continuous interaction, turning every deployment into a self-improving node within our RGI network. The Ultimate Vision We are building more than models; we are architecting the Distributed Machine Economy. A future where every dataset, model, and robotic embodiment is a verifiable asset in a global, autonomous network. Thank you for building the future of intelligence with us✌️📷show more

AI has had exactly two scaling axes that worked... so far, and the second one is starting to look finite too the first one was pretraining: with scaling parameters and data, we got world knowledge (i.e. ChatGPT had read enough to know things), but it started saturating a while ago the second one was RL, and people had been doing RL the whole time before that: RLHF is RL but it never scaled far because it was trying to control the exact output, which tokens come out, how the text reads, but you can only push that so far before you’re just polishing RLVR dropped that constraint: giving the model a task, then checking whether the final answer is right, and ignoring everything in between -- so the model does whatever it wants in the middle and only the endpoint gets graded, and that’s much closer to actual RL and it’s what bought us planning and reasoning (arguably, tool use sits around 2.5 on this list -- while useful, it's not a different kind of thing) so one axis gave knowledge, the other gave reasoning, and both of them are one model working alone the next axis is how many models you can get working on the same problem, which is a different kind of axis than the previous two we know that multi-agent RL has always been the harder problem: I spent years in that literature and the gap between single-agent and multi-agent is definitely not incremental -- it’s a whole different class of difficulty! which is also why the derivatives are steep at the start, nobody has picked the easy wins yet... and the thing that gates this multi-agent coordination is communication: models can only coordinate as well as they can exchange information, and right now they do that by writing sentences to each other imagine what could we possibly achieve if we properly open that third axis development by letting models to exchange information in their native "language" without loosing any computational data that they produce during inferenceshow more

I built more 3-statement models by hand at Morgan... Stanley than I'd like to admit. Claude in Excel is a game changer .... here's how I build any model in 5 passes: The process is all about context window management to minimize hardcodes + hallucinations and maximize control over model style. (1) Gather the sources. Filings, earnings transcripts, raw financials and any model or template I already have. I have it make a clean folder I point Claude to. (2) Turn the sources into a JSON or .md input. A short inputs file with historicals, segment KPIs, accounting definitions and operating drivers. This step converts many megabites of PDF's into a liteweight doc for RAG. (3) Build the structure (in your firm style). Building the shell lets you reverse engineer your firm model style .... which Claude will never have context for. (4) Add the forecast. I take the same historicals JSON or .md and run a deep research workflow to fill in those parameters but for forward assumptions. Obviously with sources so I can check assumptions. Then I layer in that file to project out forward assumptions. (5) Audit it in a fresh chat. New chat is necessary to hard reset the context window (improves quality). A simple prompt even to check for hard + soft errors can rank issues by severity (eg broken formulas and things that don't tie to assumptions that look off) If you're really advanced at Claude Code - you can wrap this into a programmatic skill package in your firm build style .... maybe I write a thread about that next time. In the meantime, I've put together this AI for Excel build guide here:show more

How does Edge0 run a 35B model with only... 1–2.5 GB of peak memory? In simple terms: • The full model stays in storage. • Only the parameters needed for the current step are loaded into memory. • The next parameters are prepared while the current step is running. • Memory is reused instead of loading the entire model at once. Large model. Small working set. Fully on-device.show more

Coarse2Real (C2R) transfers simple 3D renderings into realistic style... video. Check our paper and project page to learn how to hedge small amount of synthetic paired data with real non-pair data for training the C2R model. We will release the model soon!show more

result of some overnight sweeping with my simulator. it... looks like its abusing something to move faster, but the good news is that the same behaviour transfers to mujoco cpu This is my policy trained on dingsim, top running on dingsim, and bottom on mujocoshow more