Last week in Zürich, we co-hosted a panel with Foxglove at #ACTUATE Field Sessions around an honest challenge facing robotics today: Why general purpose robot learning hasn’t had its breakthrough moment yet? The panel agreed: it's not simply about having more data, it's about having the right data. Robots need to interact with the world through touch, not just perception. Bridging that gap requires curation, better simulation, and more robots actually learning from real-world scenarios. The data gap is real, but we’re closing it. A great conversation moderated by Ilir Aliu, with David Hoeller, Klajd Lika, Mayank M., Antonio Arbues and the Foxglove team. #HumanoidRobots #Flexion
Info
We are building the autonomy stack for humanoid robots - from command to control, from manipulation to locomotion, across any hardware and task. Leveraging the power of simulation and reinforcement learning, our software scales to the real world with minimal human involvement.
- Website
-
https://flexion.ai
Externer Link zu Flexion Robotics
- Branche
- Robotik
- Größe
- 11–50 Beschäftigte
- Hauptsitz
- Zurich
- Art
- Einzelunternehmen (Gewerbe, Freiberufler etc.)
Orte
-
Primär
Wegbeschreibung
Affolternstrasse 42
Zurich, 8050, CH
Beschäftigte von Flexion Robotics
Updates
-
Robots are getting smarter and the way we build them is changing fast. Simulation + reinforcement learning can now train a robot in days, not years. At Flexion, we're building a general-purpose brain that runs across different robot hardware; trained in simulation, deployed in the real world. Our CEO Nikita Rudin sat down with Evan O'Donnell for The Times Blog to unpack simulation, adaptability, and the real process behind teaching robots how to move. Link to the article in the comments. #HumanoidRobots #Flexion
-
How do we solve the data gap in robotics? We're co-hosting a panel at #ActuateFieldSessions alongside Foxglove. Come listen to the ones driving the conversation: Ilir Aliu - Founder 22Astronauts David Hoeller - Co-Founder & CTO Flexion Robotics Klajd Lika - CEO Bota Systems AG Mayank M. - Research Scientist NVIDIA Antonio Arbues - CTO Loki Robotics Join us on May 6th at 1:30pm. Only a few spots left - link in the comments. 📍 Zürich, Switzerland #HumanoidRobots #Flexion #Actuate
-
-
Physical intelligence isn't a headline for the future, it's what we build and deploy today. That's the conversation happening at VENTURE SPRIND 2026 in Berlin. Our Co-Founder and Perception Lead, Julian Nubert, will dive into how physical intelligence is reshaping the way robots learn, adapt, and work alongside humans, redefining work and the future of European industry. Julian is sharing the stage with Martin Kiefel, Sören Heß, and Leonard Schenk, discussing the approaches that will define tomorrow's economy. Session link in the comments. #Robotics #PhysicalIntelligence #VentureSprind2026 #Innovation #Berlin
-
-
What does it take to build the brain of a humanoid robot? Great having Andreas Klinger at the office to see it firsthand — from robots learning to move through reinforcement learning, to the bigger vision of one AI platform for any humanoid hardware.
Do you want to see a humanoid AI lab from the inside? I do 🙂 – join me and let’s visit Flexion Robotics: Europe’s leading lab building the AI brains for humanoids! Their goal? Build the Android of robotics. One operating system that works on any humanoid hardware. It is crazy what their robots can do. We pushed a robot on the stairs. It didn't care. They left one in a rainy forest it was never trained on. No issue. And because they let robots train on their own, from zero through reinforcement learning, the robots do odd things. They stand up from the ground in ways no human ever would. Because they learned what's best for a robot body, not a human one. Backflips? Surprisingly easy. Finding and picking up a box without crushing it? That's still a hard problem to enable more industry usecases. And Flexion is exactly working on that. If their humanoid brain works, this will be industry defining. This is why Flexion is one of Europe's Most Ambitious Startups. 🇪🇺🔥 Full Video on Youtube: https://lnkd.in/e-2YnrjE Subscribe to all our full updates here: https://lnkd.in/d9n3Hujn Thanks to Nikita Rudin & Julian Nubert for inviting me and showing me around.
-
The future of robotics won't be owned by a single company. It will be shaped by the ecosystems we build together. That's exactly what we're bringing to NVIDIA GTC Our CTO and Co-Founder, David Hoeller, on March 17th at the panel "Build Physical Intelligence: Open Collaboration Across Robotics Ecosystems", will explore what it truly means to build a collaborative robotics ecosystem: From open collaboration and shared infrastructure to the strategic partnerships that will define the next era of the industry. If you're interested in where robotics is heading, this is a conversation you don't want to miss. Make sure to add this session to your GTC agenda. Link in the comments. #Robotics #NVIDIAGTC #GTC2026 #OpenCollaboration #RoboticsEcosystem
-
-
While others rely on teleoperation, we are betting on simulation at scale. Here is how Flexion is building the data flywheel differently. 👇
“Teleoperation in robotics is very popular right now. We’re intentionally avoiding it.” Nikita Rudin, CEO of Flexion Robotics on how they’re training robots at scale: “We’re betting heavily on simulation and reinforcement learning.” “No motion-capture suits. No VR headsets. No armies of people piloting robots.” “Instead, we train as much as possible in simulation.” “If a new robot comes in, we load its URDF, retrain in the simulator, and deploy a new neural network.” “So when we train one robot on a task, we’re effectively training dozens or hundreds of embodiments at once.” “That’s the flywheel.”
-
“My hot take is this: there isn’t a single humanoid robot today that truly generates value. Some robots can do something close to the intended task. But not the actual task. And if a robot needs human handlers to clean up after it, you’re not creating value. In many cases, the value is arguably negative. We’ll fix that.” Our Co-Founder and CEO, Nikita Rudin, joined the TWIML AI podcast to share a grounded view on where robotics stands at the beginning of 2026 and how the next few years will reshape the industry. 🎧 Listen to the full conversation below.
Today, we're joined by Nikita Rudin, co-founder and CEO of Flexion Robotics to discuss the gap between current robotic capabilities and what’s required to deploy fully autonomous robots in the real world. Nikita explains how reinforcement learning and simulation have driven rapid progress in robot locomotion—and why locomotion is still far from “solved.” We dig into the sim2real gap, and how adding visual inputs introduces noise and significantly complicates sim-to-real transfer. We also explore the debate between end-to-end models and modular approaches, and why separating locomotion, planning, and semantics remains a pragmatic approach today. Nikita also introduces the concept of "real-to-sim", which uses real-world data to refine simulation parameters for higher fidelity training, discusses how reinforcement learning, imitation learning, and teleoperation data are combined to train robust policies for both quadruped and humanoid robots, and introduces Flexion's hierarchical approach that utilizes pre-trained Vision-Language Models (VLMs) for high-level task orchestration with Vision-Language-Action (VLA) models and low-level whole-body trackers. Finally, Nikita shares the behind-the-scenes in humanoid robot demos, his take on reinforcement learning in simulation versus the real world, the nuances of reward tuning, and offers practical advice for researchers and practitioners looking to get started in robotics today. 🎧 / 🎥 Listen or watch the full episode on our page: https://twimlai.com/go/760.
-