Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Success rate has long been the primary metric for evaluating robot manipulation. What about speed? Today, we introduce ⚡️B-spline Policy (BSP). Instead of predicting discrete fixed-rate action chunks, we parameterize actions as continuous B-spline curves. Together with our system design, BSP enables fast manipulation on low-cost robot arms. This...

Haoyu_Xiong_'s profile picture

Haoyu Xiong

4,234 subscribers

69,465 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

I've been working on deformable object manipulation since my PhD. It was totally a nightmare years ago and my PhD advisor was telling me not to work on it for my own good. Today, at ByteDance Seed, we are dropping GR-RL, a new VLA+RL system that manages long-horizon precise dexterous manipulation of deformable objects. This is probably the first real-world RL system to make a robot: ✅ Lace up your shoes end to end ✅ Hit millimeter tolerance repeatedly ✅ Recover from mistakes (See video!) ✅ And complete continuous shoelace threading on a real bimanual platform 📈 Success rate: ↑ from 45.7% → 83.3% Yes, robots can now actually do this. Project page: ArXiv:
3:45

I've been working on deformable object manipulation since my PhD. It was totally a nightmare years ago and my PhD advisor was telling me not to work on it for my own good. Today, at ByteDance Seed, we are dropping GR-RL, a new VLA+RL system that manages long-horizon precise dexterous manipulation of deformable objects. This is probably the first real-world RL system to make a robot: ✅ Lace up your shoes end to end ✅ Hit millimeter tolerance repeatedly ✅ Recover from mistakes (See video!) ✅ And complete continuous shoelace threading on a real bimanual platform 📈 Success rate: ↑ from 45.7% → 83.3% Yes, robots can now actually do this. Project page: ArXiv:

Xiao Ma

110,461 Aufrufe • vor 9 Monaten

🔥 #ICRA2026 Best Paper Finalist The era of "robot VLA = single-arm gripper" is ending. Introducing Dexora — the first open-source Vision-Language-Action system for dual-arm, dual-hand, 36-DoF dexterous manipulation. 🦾 Dual Arms 🖐️ Dual Hands 🎯 36 DoF Control 🌍 Open Source Trained on: • 100K simulated trajectories • 10K real-world demonstrations Dexora achieves: ✓ 90%+ success on basic manipulation ✓ Strong dexterous manipulation performance ✓ Cross-embodiment generalization Our key hypothesis: Train on the hardest embodiment. Transfer to simpler robots later. Instead of scaling up gripper policies, we train directly in the most expressive action space and project downward to simpler embodiments. This may be a practical path toward universal robot controllers. 🎥 Demos: 📄 Paper:
2:58

🔥 #ICRA2026 Best Paper Finalist The era of "robot VLA = single-arm gripper" is ending. Introducing Dexora — the first open-source Vision-Language-Action system for dual-arm, dual-hand, 36-DoF dexterous manipulation. 🦾 Dual Arms 🖐️ Dual Hands 🎯 36 DoF Control 🌍 Open Source Trained on: • 100K simulated trajectories • 10K real-world demonstrations Dexora achieves: ✓ 90%+ success on basic manipulation ✓ Strong dexterous manipulation performance ✓ Cross-embodiment generalization Our key hypothesis: Train on the hardest embodiment. Transfer to simpler robots later. Instead of scaling up gripper policies, we train directly in the most expressive action space and project downward to simpler embodiments. This may be a practical path toward universal robot controllers. 🎥 Demos: 📄 Paper:

Hao Zhao

17,474 Aufrufe • vor 2 Monaten

Egocentric Videos for Robot Training 🧵 Researchers at NYU and UC Berkeley published research where they developed a system called EgoZero that trains robots using human demonstration videos recorded with smart glasses. 👓 The system converts first-person human actions into 3D point-based state-action representations. The policies executed on a gripper-equipped robot, achieved a 70% zero-shot success rate across seven manipulation tasks, with only 20 minutes of human data per task. EgoZero stands as one of the solid empirical proofs that egocentric smart-glass video collected from everyday human behavior can serve as powerful, scalable training data for real robot learning. Vincent Liu Ademi Adeniji
1:24

Egocentric Videos for Robot Training 🧵 Researchers at NYU and UC Berkeley published research where they developed a system called EgoZero that trains robots using human demonstration videos recorded with smart glasses. 👓 The system converts first-person human actions into 3D point-based state-action representations. The policies executed on a gripper-equipped robot, achieved a 70% zero-shot success rate across seven manipulation tasks, with only 20 minutes of human data per task. EgoZero stands as one of the solid empirical proofs that egocentric smart-glass video collected from everyday human behavior can serve as powerful, scalable training data for real robot learning. Vincent Liu Ademi Adeniji

VaderResearch

23,055 Aufrufe • vor 11 Monaten

Robot dog learned dexterity! 🤯 Robots usually struggle to move and handle objects at the same time, a challenge called loco-manipulation. Researchers at the RAI Institute have developed a new system called ReLIC that makes this easier. Instead of giving robots fixed roles for arms and legs, ReLIC lets them switch roles on the fly, for example, using a leg to help lift something while balancing on the others. This approach is more natural, similar to how humans use different body parts together without thinking about it. ReLIC was tested on a four-legged robot, which successfully performed tasks like moving boxes, opening drawers, and placing items into containers.
0:32

Robot dog learned dexterity! 🤯 Robots usually struggle to move and handle objects at the same time, a challenge called loco-manipulation. Researchers at the RAI Institute have developed a new system called ReLIC that makes this easier. Instead of giving robots fixed roles for arms and legs, ReLIC lets them switch roles on the fly, for example, using a leg to help lift something while balancing on the others. This approach is more natural, similar to how humans use different body parts together without thinking about it. ReLIC was tested on a four-legged robot, which successfully performed tasks like moving boxes, opening drawers, and placing items into containers.

Lukas Ziegler

19,743 Aufrufe • vor 11 Monaten

Introducing Open-TeleVision: with Fully Autonomous policy video👇. We can conduct a long-horizon task with inserting 12 cans nonstop without any interruptions. We offer: 🤖 Highly precise and smooth bimanual manipulation. 📺 Active egocentric vision (with a moving neck) feedback. It is achieved by imitation learning from teleoperation: We propose a VR-based REAL-TIME teleoperation that streams the stereo video observation from the robot camera to the VR device. The robot neck moves as the human head moves, the robot hands move as the human hands move, offering the operator an intuitive experience as the human herself becomes the robot. The devils are all in the details, and how to implement things right: ✅How to perform IK/retargeting for smooth and precise control. ✅How to do all these and also stream stereo video without no latency, all in real time. We released our code here: Active head hardware design: 1/n
0:33

Introducing Open-TeleVision: with Fully Autonomous policy video👇. We can conduct a long-horizon task with inserting 12 cans nonstop without any interruptions. We offer: 🤖 Highly precise and smooth bimanual manipulation. 📺 Active egocentric vision (with a moving neck) feedback. It is achieved by imitation learning from teleoperation: We propose a VR-based REAL-TIME teleoperation that streams the stereo video observation from the robot camera to the VR device. The robot neck moves as the human head moves, the robot hands move as the human hands move, offering the operator an intuitive experience as the human herself becomes the robot. The devils are all in the details, and how to implement things right: ✅How to perform IK/retargeting for smooth and precise control. ✅How to do all these and also stream stereo video without no latency, all in real time. We released our code here: Active head hardware design: 1/n

Xiaolong Wang

25,572 Aufrufe • vor 2 Jahren

A jaw-on-the-floor moment for the whole team was when we had taught the robot to pick up a baggie and shake a usb-brick out with the left hand. During one rollout, it decided to do it with the right hand—and we all stopped. We were stunned, because no one taught it to do that. This was one of the first models with our pretrained base, and it was the moment we realized there was something here that was very different from what any of us had ever built before. We now know this to be part of the improvisational intelligence that emerges with large-scale pretraining on real manipulation data, and it continues to be one of the things that we believe to be worth pushing forward as capability. Our CTO and cofounder Andy Barry joined Association for Advancing Automation to share more about these moments, and how his time at Boston Dynamics and the Broad Institute drove him to focus on building the 🧠 for robots at Generalist. Full ep 👇
0:28

A jaw-on-the-floor moment for the whole team was when we had taught the robot to pick up a baggie and shake a usb-brick out with the left hand. During one rollout, it decided to do it with the right hand—and we all stopped. We were stunned, because no one taught it to do that. This was one of the first models with our pretrained base, and it was the moment we realized there was something here that was very different from what any of us had ever built before. We now know this to be part of the improvisational intelligence that emerges with large-scale pretraining on real manipulation data, and it continues to be one of the things that we believe to be worth pushing forward as capability. Our CTO and cofounder Andy Barry joined Association for Advancing Automation to share more about these moments, and how his time at Boston Dynamics and the Broad Institute drove him to focus on building the 🧠 for robots at Generalist. Full ep 👇

Generalist

11,117 Aufrufe • vor 2 Monaten

Tesla Optimus can arrange batteries in their factories, ours can do skincare (on Yuzhe Qin)! We opensource Bunny-VisionPro, a teleoperation system for bimanual hand manipulation. The users can control the robot hands in real time using VisionPro, flexible like a bunny. 🐇 We also have kitchen tasks, playing Rubik's Cube, and dynamic motion tasks. Imitation learning policies are trained on sweeping with a broom, serving a drink, and wiping glasses. Check our website for more details: The project is led by Runyu Ding Runyu Ding, Yuzhe Qin Yuzhe Qin , and Jiyue Zhu
2:56

Tesla Optimus can arrange batteries in their factories, ours can do skincare (on Yuzhe Qin)! We opensource Bunny-VisionPro, a teleoperation system for bimanual hand manipulation. The users can control the robot hands in real time using VisionPro, flexible like a bunny. 🐇 We also have kitchen tasks, playing Rubik's Cube, and dynamic motion tasks. Imitation learning policies are trained on sweeping with a broom, serving a drink, and wiping glasses. Check our website for more details: The project is led by Runyu Ding Runyu Ding, Yuzhe Qin Yuzhe Qin , and Jiyue Zhu

Xiaolong Wang

90,938 Aufrufe • vor 2 Jahren

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.
1:13:32

For robots to be useful, they must be able to interact with a wide variety of environments; and yet, scaling interaction data is difficult, expensive, and time consuming. Instead, much research revolves around sim-to-real manipulation — but mostly this has not been mobile manipulation. Recently, though, this has begun to change. Two recent papers from Tairan He and Haoru Xue show us how to unlock the potential of this technique, building policies which, without any real data at all, can move objects around in the world and open doors in the real world with a humanoid robot. Watch Episode #60 of RoboPapers now to learn more, hosted by Chris Paxton and Jiafei Duan. In this episode, we cover two papers:. First is VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation; and second is DoorMan: Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer.

RoboPapers

30,767 Aufrufe • vor 7 Monaten

Agile Continuous Jumping in Discontinuous Terrains discuss: We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping requires accurately executing highly dynamic motions over long horizons, which is challenging for existing approaches. To accomplish this task, we design a hierarchical learning and control framework, which consists of a learned heightmap predictor for robust terrain perception, a reinforcement-learning-based centroidal-level motion policy for versatile and terrain-adaptive planning, and a low-level model-based leg controller for accurate motion tracking. In addition, we minimize the sim-to-real gap by accurately modeling the hardware characteristics. Our framework enables a Unitree Go1 robot to perform agile and continuous jumps on human-sized stairs and sparse stepping stones, for the first time to the best of our knowledge. In particular, the robot can cross two stair steps in each jump and completes a 3.5m long, 2.8m high, 14-step staircase in 4.5 seconds. Moreover, the same policy outperforms baselines in various other parkour tasks, such as jumping over single horizontal or vertical discontinuities.
0:25

Agile Continuous Jumping in Discontinuous Terrains discuss: We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping requires accurately executing highly dynamic motions over long horizons, which is challenging for existing approaches. To accomplish this task, we design a hierarchical learning and control framework, which consists of a learned heightmap predictor for robust terrain perception, a reinforcement-learning-based centroidal-level motion policy for versatile and terrain-adaptive planning, and a low-level model-based leg controller for accurate motion tracking. In addition, we minimize the sim-to-real gap by accurately modeling the hardware characteristics. Our framework enables a Unitree Go1 robot to perform agile and continuous jumps on human-sized stairs and sparse stepping stones, for the first time to the best of our knowledge. In particular, the robot can cross two stair steps in each jump and completes a 3.5m long, 2.8m high, 14-step staircase in 4.5 seconds. Moreover, the same policy outperforms baselines in various other parkour tasks, such as jumping over single horizontal or vertical discontinuities.

AK

35,794 Aufrufe • vor 1 Jahr

Milestone! We (robotic arms for gadgets assembly) finished the first commercial order, which brought the first revenue. Here are some learnings from this: The customer was a smart toy manufacturer. The task was to add a heatsink to Raspberry Pi. We received parts from them and returned the assembled modules back. Currently, it's done by teleoperation. Later it will be done by a remote employee via the Internet. Then it will be automated action by action, reducing the operator's time on this and making the task profitable. ps. If you have an assembly task that we can do for you asynchronically - leave a comment below. Learning 1. It's possible! This task which is usually done by the human arm with 5 fingers can be done with a two-finger gripper with the addition of a couple of simple tooling. The task was not simplified. We peeled off thin films from stickers, unpacked paper boxes, moved PCB boards full of components, etc. And no unsolvable problems have been encountered yet. Challenges: 1) The paper box shifted during the opening Solved with the plastic walls that you can lean against 2) Heat pad, stuck to the gripper instead of heat sync. Can be solved by gripper with a pump, but this time solved with the patience of the operator 3) The film on the pad is very thin. Turned out that sub-millimeter arm precision is enough to peel it off with just a regular gripper. 4) The working area has not enough space. You'll only know this by doing real tasks in bulk. This could be solved by an extra pair of long arms, but in this case, solved with the patience of the operator. I think that in the end, we will have 5-10 types of universal tooling and 5-10 types of grippers to solve almost all the problems in such assembly tasks. Learning 2. It's slow. It took 5 times more time, than doing it with human hands. But the good news is there's a lot of room for improvement. We now have specific “time for task” metrics, which we will decrease with iterations. The main reasons for slowness: 1) To rotate the gripper to a steep angle you are forced to control one robot arm with two hands instead of using both arms. We can fix this by just making more room for rotations. 2) Grabbing PCB board with two arms is hard. A slight difference in rotation can break the board, and it's hard to control these angles visually. To solve this, the best way is to use force feedback so you can feel the pressure applied to the item. 3) Accuracy and steadiness is still can be improved We will try a metal version and double the motors to do this. 4) It is physically difficult for the human hands to move with such precision To solve this, we will add a pad for the hands like in surgical robots Learning 3. It's a good business model The "Factory in the cloud" is a good business model for this stage. You send us parts and we send back assembled modules. Currently, it's more convenient than sending a robot to your place, as we can iterate/fix the robot quickly and utilize it 100% of the time. When we polish the set-up over time - we can send robots to your place. So if we can assemble something for you in the USA with Chinese prices by using modern automation - leave a comment below.
0:48

Milestone! We (robotic arms for gadgets assembly) finished the first commercial order, which brought the first revenue. Here are some learnings from this: The customer was a smart toy manufacturer. The task was to add a heatsink to Raspberry Pi. We received parts from them and returned the assembled modules back. Currently, it's done by teleoperation. Later it will be done by a remote employee via the Internet. Then it will be automated action by action, reducing the operator's time on this and making the task profitable. ps. If you have an assembly task that we can do for you asynchronically - leave a comment below. Learning 1. It's possible! This task which is usually done by the human arm with 5 fingers can be done with a two-finger gripper with the addition of a couple of simple tooling. The task was not simplified. We peeled off thin films from stickers, unpacked paper boxes, moved PCB boards full of components, etc. And no unsolvable problems have been encountered yet. Challenges: 1) The paper box shifted during the opening Solved with the plastic walls that you can lean against 2) Heat pad, stuck to the gripper instead of heat sync. Can be solved by gripper with a pump, but this time solved with the patience of the operator 3) The film on the pad is very thin. Turned out that sub-millimeter arm precision is enough to peel it off with just a regular gripper. 4) The working area has not enough space. You'll only know this by doing real tasks in bulk. This could be solved by an extra pair of long arms, but in this case, solved with the patience of the operator. I think that in the end, we will have 5-10 types of universal tooling and 5-10 types of grippers to solve almost all the problems in such assembly tasks. Learning 2. It's slow. It took 5 times more time, than doing it with human hands. But the good news is there's a lot of room for improvement. We now have specific “time for task” metrics, which we will decrease with iterations. The main reasons for slowness: 1) To rotate the gripper to a steep angle you are forced to control one robot arm with two hands instead of using both arms. We can fix this by just making more room for rotations. 2) Grabbing PCB board with two arms is hard. A slight difference in rotation can break the board, and it's hard to control these angles visually. To solve this, the best way is to use force feedback so you can feel the pressure applied to the item. 3) Accuracy and steadiness is still can be improved We will try a metal version and double the motors to do this. 4) It is physically difficult for the human hands to move with such precision To solve this, we will add a pad for the hands like in surgical robots Learning 3. It's a good business model The "Factory in the cloud" is a good business model for this stage. You send us parts and we send back assembled modules. Currently, it's more convenient than sending a robot to your place, as we can iterate/fix the robot quickly and utilize it 100% of the time. When we polish the set-up over time - we can send robots to your place. So if we can assemble something for you in the USA with Chinese prices by using modern automation - leave a comment below.

Igor Kulakov

37,266 Aufrufe • vor 1 Jahr

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵
2:21

Excited to announce GR00T N1, the world’s first open foundation model for humanoid robots! We are on a mission to democratize Physical AI. The power of general robot brain, in the palm of your hand - with only 2B parameters, N1 learns from the most diverse physical action dataset ever compiled and punches above its weight: - Real humanoid teleoperation data. - Large-scale simulation data: we are open-sourcing 300K+ trajectories! - Neural trajectories: we apply SOTA video generation models to “hallucinate” new synthetic data that features accurate physics in pixels. Using Jensen’s words, “systematically infinite data”! - Latent actions: we develop novel algorithms to extract action tokens from in-the-wild human videos and neural generated videos. GR00T N1 is a single end-to-end neural net, from photons to actions: - Vision-Language Model (System 2) that interprets the physical world through vision and language instructions, enabling robots to reason about their environment and instructions, and plan the right actions. - Diffusion Transformer (System 1) that “renders” smooth and precise motor actions at 120 Hz, executing the latent plan made by System 2. We deploy N1 on GR1 robot, 1X Neo robot, and a large collection of simulation benchmarks. N1 achieves up to +30% boost in diverse manipulation tasks for household and industrial settings. While humanoid robots are the main focus of N1, our model also supports cross-embodiment. We finetune it to work on the $110 HuggingFace LeRobot SO100 robot arm! Open robot brain runs on open hardware. Sounds just right. Let’s solve robotics, together, one token at a time. Links to our Whitepaper, Github repo, HuggingFace model, and open dataset page in the thread: 🧵

Jim Fan

466,814 Aufrufe • vor 1 Jahr

Announcing DreamDojo: our open-source, interactive world model that takes robot motor controls and generates the future in pixels. No engine, no meshes, no hand-authored dynamics. It's Simulation 2.0. Time for robotics to take the bitter lesson pill. Real-world robot learning is bottlenecked by time, wear, safety, and resets. If we want Physical AI to move at pretraining speed, we need a simulator that adapts to pretraining scale with as little human engineering as possible. Our key insights: (1) human egocentric videos are a scalable source of first-person physics; (2) latent actions make them "robot-readable" across different hardware; (3) real-time inference unlocks live teleop, policy eval, and test-time planning *inside* a dream. We pre-train on 44K hours of human videos: cheap, abundant, and collected with zero robot-in-the-loop. Humans have already explored the combinatorics: we grasp, pour, fold, assemble, fail, retry—across cluttered scenes, shifting viewpoints, changing light, and hour-long task chains—at a scale no robot fleet could match. The missing piece: these videos have no action labels. So we introduce latent actions: a unified representation inferred directly from videos that captures "what changed between world states" without knowing the underlying hardware. This lets us train on any first-person video as if it came with motor commands attached. As a result, DreamDojo generalizes zero-shot to objects and environments never seen in any robot training set, because humans saw them first. Next, we post-train onto each robot to fit its specific hardware. Think of it as separating "how the world looks and behaves" from "how this particular robot actuates." The base model follows the general physical rules, then "snaps onto" the robot's unique mechanics. It's kind of like loading a new character and scene assets into Unreal Engine, but done through gradient descent and generalizes far beyond the post-training dataset. A world simulator is only useful if it runs fast enough to close the loop. We train a real-time version of DreamDojo that runs at 10 FPS, stable for over a minute of continuous rollout. This unlocks exciting possibilities: - Live teleoperation *inside* a dream. Connect a VR controller, stream actions into DreamDojo, and teleop a virtual robot in real time. We demo this on Unitree G1 with a PICO headset and one RTX 5090. - Policy evaluation. You can benchmark a policy checkpoint in DreamDojo instead of the real world. The simulated success rates strongly correlate with real-world results - accurate enough to rank checkpoints without burning a single motor. - Model-based planning. Sample multiple action proposals → simulate them all in parallel → pick the best future. Gains +17% real-world success out of the box on a fruit packing task. We open-source everything!! Weights, code, post-training dataset, eval set, and whitepaper with tons of details to reproduce. DreamDojo is based on NVIDIA Cosmos, which is open-weight too. 2026 is the year of World Models for physical AI. We want you to build with us. Happy scaling! Links in thread:
1:17

Announcing DreamDojo: our open-source, interactive world model that takes robot motor controls and generates the future in pixels. No engine, no meshes, no hand-authored dynamics. It's Simulation 2.0. Time for robotics to take the bitter lesson pill. Real-world robot learning is bottlenecked by time, wear, safety, and resets. If we want Physical AI to move at pretraining speed, we need a simulator that adapts to pretraining scale with as little human engineering as possible. Our key insights: (1) human egocentric videos are a scalable source of first-person physics; (2) latent actions make them "robot-readable" across different hardware; (3) real-time inference unlocks live teleop, policy eval, and test-time planning *inside* a dream. We pre-train on 44K hours of human videos: cheap, abundant, and collected with zero robot-in-the-loop. Humans have already explored the combinatorics: we grasp, pour, fold, assemble, fail, retry—across cluttered scenes, shifting viewpoints, changing light, and hour-long task chains—at a scale no robot fleet could match. The missing piece: these videos have no action labels. So we introduce latent actions: a unified representation inferred directly from videos that captures "what changed between world states" without knowing the underlying hardware. This lets us train on any first-person video as if it came with motor commands attached. As a result, DreamDojo generalizes zero-shot to objects and environments never seen in any robot training set, because humans saw them first. Next, we post-train onto each robot to fit its specific hardware. Think of it as separating "how the world looks and behaves" from "how this particular robot actuates." The base model follows the general physical rules, then "snaps onto" the robot's unique mechanics. It's kind of like loading a new character and scene assets into Unreal Engine, but done through gradient descent and generalizes far beyond the post-training dataset. A world simulator is only useful if it runs fast enough to close the loop. We train a real-time version of DreamDojo that runs at 10 FPS, stable for over a minute of continuous rollout. This unlocks exciting possibilities: - Live teleoperation *inside* a dream. Connect a VR controller, stream actions into DreamDojo, and teleop a virtual robot in real time. We demo this on Unitree G1 with a PICO headset and one RTX 5090. - Policy evaluation. You can benchmark a policy checkpoint in DreamDojo instead of the real world. The simulated success rates strongly correlate with real-world results - accurate enough to rank checkpoints without burning a single motor. - Model-based planning. Sample multiple action proposals → simulate them all in parallel → pick the best future. Gains +17% real-world success out of the box on a fruit packing task. We open-source everything!! Weights, code, post-training dataset, eval set, and whitepaper with tons of details to reproduce. DreamDojo is based on NVIDIA Cosmos, which is open-weight too. 2026 is the year of World Models for physical AI. We want you to build with us. Happy scaling! Links in thread:

Jim Fan

227,634 Aufrufe • vor 6 Monaten

I thought this was the most important moment from Elon's interview with Dwarkesh and John Collison Elon is saying the quiet part out loud here. The reality is that without securing a win in the race for AI and robotics, America will fall behind our peers in the future world order Worth a listen "We definitely can't win with just humans because China has 4 times our population. And frankly, America has been winning for so long that we, just like a pro sports team that has been winning for a long time, tend to get complacent and entitled. And that is why they stop winning because they just dont work as hard anymore My observation is that the average work ethic in China is higher than in the U.S. So it's not just that there is 4x the population, the amount of work they put in is higher. We cant win on the human front, and our birth rate has been low for a very long time. U.S. birth rate has been below replacement since roughly 1971. We have more people domestically dying than being born. We definitely cant win on the human front, but we might have a shot at the robot front"
4:16

I thought this was the most important moment from Elon's interview with Dwarkesh and John Collison Elon is saying the quiet part out loud here. The reality is that without securing a win in the race for AI and robotics, America will fall behind our peers in the future world order Worth a listen "We definitely can't win with just humans because China has 4 times our population. And frankly, America has been winning for so long that we, just like a pro sports team that has been winning for a long time, tend to get complacent and entitled. And that is why they stop winning because they just dont work as hard anymore My observation is that the average work ethic in China is higher than in the U.S. So it's not just that there is 4x the population, the amount of work they put in is higher. We cant win on the human front, and our birth rate has been low for a very long time. U.S. birth rate has been below replacement since roughly 1971. We have more people domestically dying than being born. We definitely cant win on the human front, but we might have a shot at the robot front"

Boring_Business

43,199 Aufrufe • vor 6 Monaten

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n
1:48

1/🧠Humans are the best robot data source — but video alone misses one thing: force. 2/🙁Tactile gloves capture force — but they're costly and block the real touch manipulation depends on. 3/💪Maybe the future of touch lives on your wrist: surface EMG reads the muscles that cause force — tactile sensing without ever touching a tactile sensor. 4/🔥Want a fully open-source framework — hardware + software — to train your own force-aware learn-from-human-data robot policy? 🚀We introduce ForceBand: Learning Forceful Manipulation with sEMG -- bring force into human videos with sEMG, for force-aware manipulation ⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Force Beyond Vision ✦ Free-Hand Force Sensing ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Low-Cost & Easy-to-Implement Let's squeeze every bit of signal out of human data, and let robots feel the force! 🌐 Website: 📄 Paper: 💻 Code: 🎥 Video: 🧵 1/n

Zhi (Leo) Wang

51,729 Aufrufe • vor 2 Monaten

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate? 🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch. 🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks. Code is fully released; check out our: Homepage: Paper link: Github:
3:55

🤖 What if a humanoid robot could make a hamburger from raw ingredients—all the way to your plate? 🔥 Excited to announce ViTacFormer: our new pipeline for next-level dexterous manipulation with active vision + high-resolution touch. 🎯 For the first time ever, we demonstrate ~2.5 minutes of continuous, autonomous control—combining active vision, high-res touch, and high-DoF robot hands SharpaWave — to complete complex, real-world tasks. Code is fully released; check out our: Homepage: Paper link: Github:

Haoran Geng

95,773 Aufrufe • vor 1 Jahr

Want to use Depth Anything, but need metric depth rather than relative depth? Thrilled to introduce Prompt Depth Anything, a new paradigm for accurate metric depth estimation with up to 4K resolution. 👉Key Message: Depth foundation models like DA have already internalized rich geometric knowledge of the 3D world but lack a proper way to elicit it. Inspired by the success of prompting in LLMs, we propose prompting Depth Anything with metric cues to produce metric depth. This method proves to be very effective when using a low-cost lidar (e.g., iPhone's LiDAR), which is widely available, as prompts. We believe the prompt can generalize to other forms as long as scale information is provided. Prompt Depth Anything offers 1⃣A series of models for iPhone lidars. 2⃣4D reconstruction from monocular videos (captured with iPhone). 3⃣Improved generalization ability for robot manipulation, e.g. Training on cans but generalizing on glasses. 4⃣More detailed depth annotations for the ScanNet++ dataset. The first author is our excellent intern Haotong Lin. Paper: Huggingface: Project Page: Code:
1:20

Want to use Depth Anything, but need metric depth rather than relative depth? Thrilled to introduce Prompt Depth Anything, a new paradigm for accurate metric depth estimation with up to 4K resolution. 👉Key Message: Depth foundation models like DA have already internalized rich geometric knowledge of the 3D world but lack a proper way to elicit it. Inspired by the success of prompting in LLMs, we propose prompting Depth Anything with metric cues to produce metric depth. This method proves to be very effective when using a low-cost lidar (e.g., iPhone's LiDAR), which is widely available, as prompts. We believe the prompt can generalize to other forms as long as scale information is provided. Prompt Depth Anything offers 1⃣A series of models for iPhone lidars. 2⃣4D reconstruction from monocular videos (captured with iPhone). 3⃣Improved generalization ability for robot manipulation, e.g. Training on cans but generalizing on glasses. 4⃣More detailed depth annotations for the ScanNet++ dataset. The first author is our excellent intern Haotong Lin. Paper: Huggingface: Project Page: Code:

Bingyi Kang

67,706 Aufrufe • vor 1 Jahr

QACE Dynamics | Autonomous Navigation Preview Today we are showing autonomous navigation running live inside QACE, the robot plans its route on the map, then adjusts in real time as lidar and vision pick up new obstacles. All of this runs through a single navigation block inside QACE, ready to plug into different robots without touching low-level control. This navigation block is one of the core building pieces of QACE autonomy, and it’s just the first of many we will be rolling out.
0:58

QACE Dynamics | Autonomous Navigation Preview Today we are showing autonomous navigation running live inside QACE, the robot plans its route on the map, then adjusts in real time as lidar and vision pick up new obstacles. All of this runs through a single navigation block inside QACE, ready to plug into different robots without touching low-level control. This navigation block is one of the core building pieces of QACE autonomy, and it’s just the first of many we will be rolling out.

Qace Dynamics

12,654 Aufrufe • vor 9 Monaten

📢 Announcing one of the most exciting works from us this year on **scalable robot policy evaluation through real-to-sim transfer**, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is **orders of magnitude slower** than the development of language agents. We propose a new framework where simulation performance **strongly correlates** with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing **state-of-the-art correlation** between simulation and reality for deformable object manipulation. It provides a **scalable and reproducible evaluation engine** for robot learning. 🌐
3:04

📢 Announcing one of the most exciting works from us this year on **scalable robot policy evaluation through real-to-sim transfer**, moving toward a scalable evaluation engine with structured world models that capture the appearance, geometry, and dynamics of environments involving deformable objects. 🤖 Evaluation remains one of the biggest bottlenecks in building general-purpose robots. Today, robots are still evaluated only in the real world, which is **orders of magnitude slower** than the development of language agents. We propose a new framework where simulation performance **strongly correlates** with the real world (r > 0.9), even for deformable objects. The key difference from existing work lies in the correlation between simulation and reality: if a robot model performs better in the digital world, does it also perform better in the real world? This question has long made people hesitant about simulation-based evaluation — especially for deformable objects. We are changing that. Our pipeline achieves effective real-to-sim transfer, establishing **state-of-the-art correlation** between simulation and reality for deformable object manipulation. It provides a **scalable and reproducible evaluation engine** for robot learning. 🌐

Yunzhu Li

39,960 Aufrufe • vor 9 Monaten

If you want a vision encoder for dexterous manipulation, what should be the most important part to model? 🤔 Current standard models like CLIP, SigLIP, and DINOv2 have an incredible grasp of semantics and spatial details. But they lack the action-centric structure needed for downstream visuomotor control. But collecting annotated robotic trajectories at scale is SUPER expensive and largely unrealistic. So, how do we bridge this gap? We introduce CAIP (Contrastive Action-Image Pre-training) ⬇️ 🔸 Action-centric upstream: we align visual observations with action chunks through a contrastive objective. 🔸 Human video as a proxy: we represent 3D human hand poses analogously to robotic end-effector actions, tapping into a massive source of human demonstrations. 🔸 Massive scale: pre-trained on over 32,000 hours of manipulation video, driving both sample efficiency and robust generalization. 🔸 Hardware proven: achieves a 76% average success rate on a real-world Dexmate Vega bimanual Dexmate manipulator with dual 22-DoF Sharpa Wave hands Sharpa . 🔸 State-of-the-art: significantly outperforms strong baselines like DINOv2, SigLIP, MVP, and Qwen3.5 ViT across complex tasks, even under unexpected lighting changes and visual distractors. 🌐 Project: 📝 Blog: 📄 Paper: 💻 Model:
1:30

If you want a vision encoder for dexterous manipulation, what should be the most important part to model? 🤔 Current standard models like CLIP, SigLIP, and DINOv2 have an incredible grasp of semantics and spatial details. But they lack the action-centric structure needed for downstream visuomotor control. But collecting annotated robotic trajectories at scale is SUPER expensive and largely unrealistic. So, how do we bridge this gap? We introduce CAIP (Contrastive Action-Image Pre-training) ⬇️ 🔸 Action-centric upstream: we align visual observations with action chunks through a contrastive objective. 🔸 Human video as a proxy: we represent 3D human hand poses analogously to robotic end-effector actions, tapping into a massive source of human demonstrations. 🔸 Massive scale: pre-trained on over 32,000 hours of manipulation video, driving both sample efficiency and robust generalization. 🔸 Hardware proven: achieves a 76% average success rate on a real-world Dexmate Vega bimanual Dexmate manipulator with dual 22-DoF Sharpa Wave hands Sharpa . 🔸 State-of-the-art: significantly outperforms strong baselines like DINOv2, SigLIP, MVP, and Qwen3.5 ViT across complex tasks, even under unexpected lighting changes and visual distractors. 🌐 Project: 📝 Blog: 📄 Paper: 💻 Model:

Roei Herzig

23,239 Aufrufe • vor 2 Monaten