A robot has to be able to remember, so we’re joining forces with NXAI to build out the memory of cognitive robots. Read the full story here: neura-robotics.com/neura-rob…

When a robot opens a lock, only sound and touch can tell it whether the job is done. That’s why Neuron AI, our Perception-Language-Action (PLA) model, combines several senses at once. 3D images, tactile and force signals, audio, the robot’s own position and movement, and language flow into one shared picture of the situation, updated moment by moment. Based on it, the robot decides what to do next. The second building block is memory. Humans develop object permanence in their first two years of life, the ability to remember objects when they are out of sight. Robots need it too, because they work in a physical world where things leave their field of view and every action has consequences. We adapted our architecture specifically for this. The model gets its knowledge from three kinds of experience: our robots in NEURA Gyms, simulations that vary each scenario, and people wearing sensor-equipped suits who demonstrate the movements. After thousands of hours of base training across all five of our robot types, the model is fine-tuned on a robot and learns each specific skill from demonstration. Through the Neuraverse, customers fine-tune Neuron AI for their own processes and deploy the results to entire fleets. This makes Time-to-Skill a central measure of progress: how quickly a robot learns a new task and performs it reliably. Read more: neura-robotics.com/neuron-ai…

We are proud to announce Neuron AI: our multimodal foundation model for Physical AI Neuron AI connects 3D vision, touch, audio, robot state and language with memory and turns that information into action. That’s the idea behind PLA, short for Perception-Language-Action. Vision alone is not enough. People feel whether a screw has caught and hear when a connector clicks into place. Neuron AI applies that principle to robots, so they can react to what cameras cannot capture. It runs across five of our robot embodiments and their grippers and hands, and partners can fine-tune it for their own tasks. We call it the brain of the physical world. Neuron AI, developed and trained in-house in Metzingen, Germany, is now available via Neuraverse. Sign up for NEURA Gym and get started today. Read the full story: neura-robotics.com/neura-rob…

We wrote an article about data sovereignty, have a look 👇 neura-robotics.com/data-sove…

We wrote an article about the topic of data sovereignty in cognitive robotics, have a look👇 neura-robotics.com/data-sove…

Ever kicked a robot? A few of our colleagues do it every day, on purpose. And yes, it's part of their job. If you want to be one of them, we are hiring: Reinforcement Learning Expert, Humanoid. The human kind. Zurich. 🦾 jobs.neura-robotics.com/offe…

A new step forward in scaling Physical AI from Europe. We are glad to welcome a new partner to our ecosystem. We're joining forces with SECO, an Italian company with deep expertise in embedded and edge AI computing, to help bring our cognitive robots, including our humanoid 4NE1, into series production. Our robots run on a Brain and Nervous System architecture, because intelligence doesn't just sit in one central brain, it lives directly in the limbs, so arms and legs can sense and react in real time without waiting on a round trip to a central processor. We call this innovative concept Smart Limbs, and they run on Qualcomm Technologies' Dragonwing™ processors, which deliver the on-device AI performance, power efficiency and low latency this decentralized layer needs. SECO engineers the compute modules and manufactures at the volumes our scale-up requires, while also collaborating on real-world industrial data and automation solutions for semiconductor and electronics manufacturing, creating technologies that can ultimately be deployed globally: neura-robotics.com/neura-rob…

What does it actually take to get a robot ready for the real world? It takes a physical environment that mirrors real operations, a way to capture how experienced people do the work, and a pipeline that turns that into a validated model. Building all of that in-house means investing in infrastructure, engineering headcount, and pipeline management before a single robot goes into operation. In the NEURA Gym, all of it is already in place. The result: a robot trained for their specific use case, at up to 7x lower cost than building the same setup themselves. 🦾 Apply for the NEURA Gym: neura-robotics.com/neuragym/

We're continuing to expand our portfolio of autonomous service robot systems and taking over ADLATUS Robotics. Their cleaning and sweeping robots for industry, logistics, and public facilities will be integrated into NEURA Mobile Robots: neura-robotics.com/neura-acq…

NEURA Executive Talk Episode 3 is live! David Reger sits down with Klaus Rosenfeld, CEO of Schaeffler, on scaling humanoid robots into the millions without losing quality. Watch here: piped.video/watch?v=paHfLzW3…

Choose your task. Choose your robot. Start training. 🤖 This is how it works in the NEURA Gym. Companies that partner with us choose the use case their operations need: it starts by defining together exactly what the robot needs to do. This isn’t a generic capability, but a specific task mapped to the company’s own processes, requirements, and the environment it will run in. This way, the expertise their most experienced operators carry gets captured as trained robot skills and can be scaled across the entire organization. Got a task in your operations that's ready for a robot? Apply for the NEURA Gym: neura-robotics.com/neuragym/

Companies are already training robots inside the NEURA Gym. Schaeffler, Beumer Group, Bosch, TUM and many others rely on us as their Physical AI partner. Curious how? Join our webinar with Automationspraxis on July 29. Save your spot: industrie.de/firmenverzeichn… The webinar will be held in German.

We're continuing the global rollout of our NEURA Gyms. In partnership with RWTH Aachen university, we're launching the NEURA Gym RWTH Aachen. Five locations across Europe, the United States, and China will be up and running by the end of 2026. Read more: neura-robotics.com/neura-rob…

How do humanoid robots develop their skills? Before a humanoid can work on any factory floor, it needs task-specific training. Not just in simulation, but in authentic environments, generating real-world data. Humanoid automation is accelerating fast, and the companies training now will be ready for deployment while others are still catching up. 🤖 On July 29, 10 to 11 am, we're hosting a webinar to show exactly how that training happens inside the NEURA Gyms. Save your spot now: industrie.de/firmenverzeichn… Please note: The webinar will be held in German.

Factories everywhere are running short on people for the toughest jobs. Humanoids are stepping in… but only if they're trained for your specific tasks. Here's the catch: most humanoid training happens in simulation. That's fine for generic movement, but it fails the moment a robot needs to handle your real tools, your real floor. NEURA Gym solves this: a global network of physical training facilities where humanoids and other robots practice real tasks in authentic environments, generating the kind of high-fidelity data simulation simply can't produce. As a partner, you get direct access to humanoids to train specifically for your use case, validated before they ever touch your production floor. 🦾 The companies training their humanoids now will be the first ones deploying them. Everyone else will be catching up. Want to see if your use case is a fit? Talk to our team: neura-robotics.com/neuragym/