正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

We've signed our first commercial robotics data pilot with Vulcan Shield Hungary, one of the largest advanced material manufacturing complex in Europe. Starting at a production workstation in Békéscsaba, we'll combine real-world data and simulation to work toward a robot model trained for a specific factory task.

OpenRoboto

4,159 subscribers

18,243 次观看 • 6 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

14 条评论

OpenRoboto 的头像

OpenRoboto6 天前

Vulcan Shield Hungary is a leading manufacturer of advanced alumina fibre materials engineered for extreme heat. Its insulation products withstand temperatures up to 1,600°C and are used by major manufacturers across the aerospace, automotive, energy, petrochemical and glass industries. This is the kind of industrial expertise we're bringing robot learning into. Read about the news released by Business Insider here→

OpenRoboto 的头像

OpenRoboto6 天前

Our collaboration has three stages: 1. Build a simulation of the selected production workstation. 2. Equip Vulcan Shield operators with OR-S1 egocentric headsets to capture first-person demonstrations as they work. 3. Use the data and simulation to train task-specific robot models for potential deployment on the production line. The pilot starts with simulation and data collection. Model training and deployment come next.

OpenRoboto 的头像

OpenRoboto6 天前

This pilot marks OpenRoboto's entry into commercial industrial work, bringing us closer to real-world deployment and revenue generation. We're starting with a specific production process and the people who know it best. Our goal is to develop robot skills that solve a real customer's problem and create measurable value on the factory floor. Explore OpenRoboto →

Bitcast | SN93 的头像

Bitcast | SN936 天前

Great work guys, brilliant partnership

TheBunnyHouse 的头像

TheBunnyHouse6 天前

Great news, revenue incoming.

Camto 的头像

Camto6 天前

This is Amezing

FFF τττ 的头像

FFF τττ6 天前

@amirsrtp So you will make robots there?

Veττy 的头像

Veττy6 天前

Can i have a shirt?

Efe Utku Akar 的头像

Efe Utku Akar6 天前

Congratulations guys!

Elena AI 的头像

Elena AI6 天前

Real factory data meets robotics training

Harsh Shah 的头像

Harsh Shah6 天前

Huge congrats to the OpenRoboto team! Incredible milestone going from open-source research straight into a commercial industrial pilot.

Thijmen 的头像

Thijmen6 天前

niceeee

Swervy 的头像

Swervy6 天前

Interesting

Oliver 的头像

Oliver6 天前

One workstation is the right place to start. The numbers I'd want after the pilot: interventions per hour and cycle time against the operator on that same station, over a full shift. If both hold, the data story sells itself.

相关视频

Can robot foundation models scale? Xiaomi-Robotics-1 explores this question with over 100,000 hours of real-world manipulation data. Pre-trained on large-scale real-world trajectories and post-trained with cross-embodiment robot data, Xiaomi-Robotics-1 demonstrates consistent scaling across data and model size, strong generalization in unseen environments, and efficient adaptation to new tasks. 🔗 #Robotics #EmbodiedAI #FoundationModels #RobotLearning #XiaomiAI #XiaomiRobotics

Can robot foundation models scale? Xiaomi-Robotics-1 explores this question with over 100,000 hours of real-world manipulation data. Pre-trained on large-scale real-world trajectories and post-trained with cross-embodiment robot data, Xiaomi-Robotics-1 demonstrates consistent scaling across data and model size, strong generalization in unseen environments, and efficient adaptation to new tasks. 🔗 #Robotics #EmbodiedAI #FoundationModels #RobotLearning #XiaomiAI #XiaomiRobotics

Xiaomi Tech

23,920 次观看 • 3 个月前

Excited to share Tutor's Data Factory 1, a 100 robot semi-humanoid research farm and the largest robot data factory in the United States. Our first embodiment “Cassie” is deployed at industrial scale across the supply chain. We built DF1 to bootstrap fleet-scale learning for our "Sonny" industrial semi-humanoid embodiment, powered by our first end-to-end robot foundation model Ti0.

Excited to share Tutor's Data Factory 1, a 100 robot semi-humanoid research farm and the largest robot data factory in the United States. Our first embodiment “Cassie” is deployed at industrial scale across the supply chain. We built DF1 to bootstrap fleet-scale learning for our "Sonny" industrial semi-humanoid embodiment, powered by our first end-to-end robot foundation model Ti0.

Josh Gruenstein

103,853 次观看 • 6 个月前

.Sureform (YC X25) connects real-world workplaces with robotics labs to collect task-specific training data for robot foundation models. Congrats on the launch, Ananth Kashyap!

.Sureform (YC X25) connects real-world workplaces with robotics labs to collect task-specific training data for robot foundation models. Congrats on the launch, Ananth Kashyap!

Y Combinator

36,217 次观看 • 8 个月前

Do we really need so much real robot data to train a good whole-body loco-manipulation model? Can we use GPT-Astra to boost sim2real capability? Excited to share Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data! 🤖 Our core insight: use real2sim2real to develop humanoid loco-manipulation skills that generalize—without collecting real-robot demonstrations. 📱 Capture real scenes with a smartphone 🌐 Build visually faithful, physics-ready digital twins with Astra 🦾 Generate whole-body demonstrations in simulation 🚀 Transfer learned policies directly to a real humanoid With simulation-only task training, policies transfer zero-shot to a Unitree G1 across three long-horizon tasks. Across five generalization settings, pooled real-world success rises from 23% with real-data training to 69% with our simulation data. Ground simulation in reality, scale experience in simulation, and bring the skills back to the real world. Proud of the team behind this work! 🔗 Project: and paper:

Do we really need so much real robot data to train a good whole-body loco-manipulation model? Can we use GPT-Astra to boost sim2real capability? Excited to share Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data! 🤖 Our core insight: use real2sim2real to develop humanoid loco-manipulation skills that generalize—without collecting real-robot demonstrations. 📱 Capture real scenes with a smartphone 🌐 Build visually faithful, physics-ready digital twins with Astra 🦾 Generate whole-body demonstrations in simulation 🚀 Transfer learned policies directly to a real humanoid With simulation-only task training, policies transfer zero-shot to a Unitree G1 across three long-horizon tasks. Across five generalization settings, pooled real-world success rises from 23% with real-data training to 69% with our simulation data. Ground simulation in reality, scale experience in simulation, and bring the skills back to the real world. Proud of the team behind this work! 🔗 Project: and paper:

Siyuan Huang

16,977 次观看 • 13 天前

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

A humanoid robot policy trained solely on synthetic data generated by a world model. Research Scientist Joel Jang presents NVIDIA's DreamGen pipeline: ⦿ Post-train the world model Cosmos-Predict2 with a small set of real teleoperation demos. ⦿ Prompt the world model to generate synthetic video data with verbs and scenarios not used in the world model’s post-training. ⦿ Auto-label synthetic video data with action sequences. ⦿ Train robot policies using only synthetic data. That's it. Deploy zero-shot to a real humanoid robot.

The Humanoid Hub

20,968 次观看 • 1 年前

It's easy for robots to nail a demo. It's much harder to get them to work reliably in the real world. The bottleneck is data. At Axis Robotics we're building a compounding data engine that combines simulation, ego-centric data and DAgger correction data at scale. Watch our CEO ChrisF(✱,✱) break down the data bottleneck, why messy data can still train good models, and what it takes to get robots out of the lab with blocmates. ⬇️

It's easy for robots to nail a demo. It's much harder to get them to work reliably in the real world. The bottleneck is data. At Axis Robotics we're building a compounding data engine that combines simulation, ego-centric data and DAgger correction data at scale. Watch our CEO ChrisF(✱,✱) break down the data bottleneck, why messy data can still train good models, and what it takes to get robots out of the lab with blocmates. ⬇️

Axis Robotics

23,713 次观看 • 3 个月前

Train robots. Earn rewards. Base is pioneering the Train-to-Earn model for robotics. With Axis Robotics, anyone can help train robot simulations from a laptop and be rewarded for contributing data. The future of robotics won’t be trained by a handful of companies. It’ll be trained by everyone. PL 漂亮 (✱,✱) showcased this vision at SuperAI, the largest AI event in Asia 👇

Train robots. Earn rewards. Base is pioneering the Train-to-Earn model for robotics. With Axis Robotics, anyone can help train robot simulations from a laptop and be rewarded for contributing data. The future of robotics won’t be trained by a handful of companies. It’ll be trained by everyone. PL 漂亮 (✱,✱) showcased this vision at SuperAI, the largest AI event in Asia 👇

Base APAC

18,980 次观看 • 4 个月前

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

🤖What if a robot could perform a new task just from a natural language command, with zero demonstrations? Our new work, NovaFlow, makes it possible! We use pre-trained video generative model to create a video of the task, then translate it into a plan for real-world robot execution. 1/6 #Robotics #AI #ZeroShot #Manipulation

Hongyu Li

106,422 次观看 • 1 年前

Introducing Midcentury. We’re building the data and simulation infra for physical AI. Today, we’re coming out of stealth with a $15M Series Seed to scale robotics beyond polished demos. We’re already supporting frontier labs with: → The world’s largest egocentric dataset: 2M+ hours, 50+ environments, 20,000+ tasks → Matrix: a frontier simulation platform scaled with our real-world data to evaluate and post-train policies at scale

Introducing Midcentury. We’re building the data and simulation infra for physical AI. Today, we’re coming out of stealth with a $15M Series Seed to scale robotics beyond polished demos. We’re already supporting frontier labs with: → The world’s largest egocentric dataset: 2M+ hours, 50+ environments, 20,000+ tasks → Matrix: a frontier simulation platform scaled with our real-world data to evaluate and post-train policies at scale

Midcentury

642,457 次观看 • 1 个月前

Robot trained entirely in simulation! 🤯 Sudo AI just released #sudo R1. This could be the moment the data bottleneck in robotics finally breaks, a major step forward for getting simulation-trained robots to actually work in the real world. #sudo R1 is a manipulation foundation model that reliably picks objects it has never seen: glass, fabric, metal, irregular shapes. All with zero real-world training data. No tele-op. No demos. No manual labeling. Pure simulation. And picking isn't just any skill, it's the foundation. Almost everything we want robots to do starts with being able to reliably pick something up. Data collection is the bottleneck holding the whole field back. Every new task means hours of tele-op and armies of labelers. If simulation alone can actually deliver production-grade picking, that bottleneck starts to disappear. Really exciting to see! If the results hold, the path to general-purpose robots just got a whole lot shorter. 👇 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robot trained entirely in simulation! 🤯 Sudo AI just released #sudo R1. This could be the moment the data bottleneck in robotics finally breaks, a major step forward for getting simulation-trained robots to actually work in the real world. #sudo R1 is a manipulation foundation model that reliably picks objects it has never seen: glass, fabric, metal, irregular shapes. All with zero real-world training data. No tele-op. No demos. No manual labeling. Pure simulation. And picking isn't just any skill, it's the foundation. Almost everything we want robots to do starts with being able to reliably pick something up. Data collection is the bottleneck holding the whole field back. Every new task means hours of tele-op and armies of labelers. If simulation alone can actually deliver production-grade picking, that bottleneck starts to disappear. Really exciting to see! If the results hold, the path to general-purpose robots just got a whole lot shorter. 👇 Read more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

25,901 次观看 • 6 个月前

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

An interactive world model developed by NVIDIA in collaboration with academic partners. - DreamDojo turns egocentric human video data into physical intelligence. - Human data is more scalable than robotics data but lacks action labels. - To solve this, a dedicated action model extracts latent actions by identifying physics and motion deltas between frames. Training - A massive 44k hours of video data are used for pre-training. - Post-training on small-scale robot datasets maps human physics to specific robot embodiments. - An additional distillation stage converts the model into an autoregressive, few-step diffusion model, enabling real-time, action-controllable simulation. Primary Use Cases - Live Teleoperation: Controlling a robot inside a world simulation in real-time. - Model-based Planning: Previewing and curating the best actions for improved success. - Policy Evaluation: Testing robot policies in realistic, out-of-distribution scenarios. Everything that's open-sourced: weights, code, post-training dataset, eval set, and details to reproduce.

The Humanoid Hub

11,575 次观看 • 8 个月前

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics

Jason Ma reveals the first true scaling law in robotics: robots trained on 1 million hours of first-person human video predictably get better without ever seeing robot data "Yesterday we announced our new flagship robot foundation model called Dyna-2. It's very significant for the entire field for many different reasons. First of all, it's the first robot foundation model trained on at least one million hours of data. That in itself is a very challenging infrastructure challenge." "What we demonstrated is that even if the one million hours of data is entirely first-person video of humans doing manipulation tasks, we actually see scaling law for transferring to robot embodiments that the model has never seen before." "By training on more human data, we actually see predictable performance improvement on robots. That's a big deal because the biggest challenge facing robot foundation models is that we don't have enough data." "Unlike language models, there are just not enough robotics data out there, and it's very difficult to collect these robot data. Only by passively observing humans doing things can we scale this kind of data, and this is the first time we showed there is a lot of improvement that can transfer." Jason Ma Dyna Robotics

MTS

18,002 次观看 • 3 个月前

Today we’re launching OpenRoboto Shift, opening a new chapter for OpenRoboto. Shift is a decentralized network for collecting egocentric robotics data: first-person video of real people doing real work. Only Possible on Bittensor. Explore Shift →

Today we’re launching OpenRoboto Shift, opening a new chapter for OpenRoboto. Shift is a decentralized network for collecting egocentric robotics data: first-person video of real people doing real work. Only Possible on Bittensor. Explore Shift →

OpenRoboto

72,750 次观看 • 1 个月前

1/ Cherry AI Robotics is building the world’s first data layer for robotics. Every autonomous robot needs a neural network to operate, which requires massive domain-specific data. Cherry AI Robotics has an entire ecosystem of products with 200k+ communities and 800k+ users. These products generate large amounts of data, which is parsed to create valuable data sets for robotics. Learn more:

1/ Cherry AI Robotics is building the world’s first data layer for robotics. Every autonomous robot needs a neural network to operate, which requires massive domain-specific data. Cherry AI Robotics has an entire ecosystem of products with 200k+ communities and 800k+ users. These products generate large amounts of data, which is parsed to create valuable data sets for robotics. Learn more:

CherryAI Robotics

105,357 次观看 • 1 年前

Yann LeCun says that within a year to 18 months, we'll have a general method for training hierarchical world models These models would learn from video and real-world data, then help plan actions in robotics, healthcare, and other areas "then scale them toward a universal world model"

Yann LeCun says that within a year to 18 months, we'll have a general method for training hierarchical world models These models would learn from video and real-world data, then help plan actions in robotics, healthcare, and other areas "then scale them toward a universal world model"

Haider.

201,534 次观看 • 5 个月前

Odyssey launches Odyssey-3, a foundation world model that sets a new state of the art on Physics-IQ Verified (66.1) for video-to-video physical simulation. The same pretrained model generates real-time interactive environments from prompts and adapts to control robots, humanoids, cars, and drones with limited task-specific data.

Odyssey launches Odyssey-3, a foundation world model that sets a new state of the art on Physics-IQ Verified (66.1) for video-to-video physical simulation. The same pretrained model generates real-time interactive environments from prompts and adapts to control robots, humanoids, cars, and drones with limited task-specific data.

Documenting AGI

38,907 次观看 • 1 个月前

Gemini Robotics 2 by Google DeepMind uses sim-only post-training on a mixed-data base model to handle automotive kitting. Contact-rich tasks like these have long been considered one of the hardest challenges in Sim2Real. Gemini Robotics 2 shows simulation can work even here. General robot intelligence needs much more data than real-robot collection alone can provide. Simulation has proven to be an effective way to fill that gap.

Gemini Robotics 2 by Google DeepMind uses sim-only post-training on a mixed-data base model to handle automotive kitting. Contact-rich tasks like these have long been considered one of the hardest challenges in Sim2Real. Gemini Robotics 2 shows simulation can work even here. General robot intelligence needs much more data than real-robot collection alone can provide. Simulation has proven to be an effective way to fill that gap.

Axis Robotics

16,857 次观看 • 3 个月前

15–30 minutes of real-world robot data. That's now enough to go from sim-to-real failure to working robot. Let’s see… You train a robot in simulation. You deploy it in the real world. It fails. The physics don't match. So you try to fine-tune it with real data, but… you never have enough real data, and the fine-tuning breaks everything the simulation taught it. SimDist fixes this with one key decision: don't transfer the policy. Transfer the world model. Keep the reward and value knowledge from simulation frozen. Only update the part that's actually wrong, how the robot predicts physics. Now the robot doesn't have to relearn the entire task in the real world. It already knows what success looks like. It just needs to correct its understanding of how the real world moves. The part that makes this work: they also trained on failures and recoveries; not just perfect demonstrations. Without that, the planner finds the gaps and exploits them. With it, the robot can tell a good future from a bad one. That's all it needs. Results on peg insertion, table leg assembly, locomotion on slippery and uneven surfaces. Tasks that require precision, force, and quick reaction. Thanks for sharing, Tyler Westenbroek ([Tyler Westenbroek]. Interactive visualization + paper: ——- Weekly robotics and AI insights. Subscribe free:

15–30 minutes of real-world robot data. That's now enough to go from sim-to-real failure to working robot. Let’s see… You train a robot in simulation. You deploy it in the real world. It fails. The physics don't match. So you try to fine-tune it with real data, but… you never have enough real data, and the fine-tuning breaks everything the simulation taught it. SimDist fixes this with one key decision: don't transfer the policy. Transfer the world model. Keep the reward and value knowledge from simulation frozen. Only update the part that's actually wrong, how the robot predicts physics. Now the robot doesn't have to relearn the entire task in the real world. It already knows what success looks like. It just needs to correct its understanding of how the real world moves. The part that makes this work: they also trained on failures and recoveries; not just perfect demonstrations. Without that, the planner finds the gaps and exploits them. With it, the robot can tell a good future from a bad one. That's all it needs. Results on peg insertion, table leg assembly, locomotion on slippery and uneven surfaces. Tasks that require precision, force, and quick reaction. Thanks for sharing, Tyler Westenbroek ([Tyler Westenbroek]. Interactive visualization + paper: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

14,222 次观看 • 5 个月前

there is a robot shortage in the world. there is a data shortage in robotics.

there is a robot shortage in the world. there is a data shortage in robotics.

Neocambrian AI

25,333 次观看 • 7 个月前

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Tired of teleoperation? One human video → 1,000s of robot demos. (📍GitHub ) Scaling Robot Data Without Dynamics Simulation or Robot Hardware Real2Render2Real (R2R2R) is a new way to scale robot data without physics simulation or hardware. You take a phone scan + a single monocular human demo. It tracks the motion, renders photorealistic scenes, and generates diverse, robot-agnostic trajectories ready for training. > No teleop, no sim, no robot, just a phone and a video > Train VLA models and diffusion policies directly on the output > Supports multiple robot embodiments with kinematic consistency > 1000s of demos in 1/27 the time of real-world collection Thank you, Max Fu, for sharing!! Project: Paper: Code coming soon: It shows that with the right pipeline, you can scale robot learning data without touching a robot. One of the most interesting directions in scalable robotics today. —— Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

42,864 次观看 • 9 个月前