Built on our Data Foundation Model (DFM), delivering higher-quality, more scalable, and more efficient Ego+Fingers data production.Industry-first DFM enables end-to-end data processing#EmbodiedAI# #HumanData# #6DPose# #PhysicalAI# #RobotLearning# #EgoData#

Can an AI agent learn a pool table’s physics by playing on it? 🎱 Closing the visual gap between reality and simulation is one thing. Closing the dynamics gap is much harder. In this fun project, we let an agent take real shots, observe the outcomes, and iteratively improve its simulation of the physical world. The idea: rather than just observing the world, let agents actively experiment with it and learn its physics through interaction. A fun demonstration of a key capability for Physical AI: learning the physics of the real world through autonomous experimentation. A @corl_conf late breaking contribution. If you plan to attend #CoRL#, see you there! In collaboration with @XilunZhangXZ @MatthewFoutter @Luis_A_Pabon @Liam862373 Check it out: #PhysicalAI# #Robotics# #AgenticAI# #RobotLearning# @StanfordAILab @StanfordASL

How do we make RL-powered humanoid robots safe without sacrificing performance? In our latest #CoRL2026# paper, Constrained Whole-Body Tracking for Humanoid Robots, we introduce safety filters that enforce kinematic and dynamic constraints—even those never encountered during training. The approach minimally interferes with the underlying RL policy and requires *no retraining*. At CoRL in Austin? Come meet @danielpmorton at Poster Session 2, Tuesday evening, #204#! Project: Paper: Work led by @danielpmorton, in collaboration with Pranit Mohnot #HumanoidRobotics# #ReinforcementLearning# #RobotLearning# #PhysicalAISafety# #Robotics# @StanfordAILab @StanfordASL

Human motion. Human touch. A new chapter begins. Two next-generation products from debuting at CoRL 2026: 🔹 DAS Ego 2.0 — A first-person multimodal data collection system with hand-tracking precision within 4 mm. 🔹 DAS Dex 2.0 — A high-fidelity human dexterity data glove with e-skin tactile sensing. From whole-body motion to tactile sensing, perfectly in sync. Come experience it live. See you at Booth #200#! 📅 November 9–11, 2026 📍 110 E 2nd St, Austin, TX 78701, USA #CoRL2026# #GenRobotAI# #Robotics# #EgoData# #WholeBodyManipulation# #DexterousManipulation# #EmbodiedAI# #RobotLearning#

🤖 Great to meet robotics builders at our Embodied Intelligence Workshop at RoseLab, Toulouse! With SenseCraft Robotics, you can bring the robot arm workflow into one platform:🔗 Connect → 📊 Collect Data → 🧠 Train → 🚀 Deploy 🎁 New users get 1,000 free credits on first login. 👉 #SenseCraftRobotics# #SeeedStudio# #Robotics# #RobotLearning# #EmbodiedAI#

Can we steer a robot foundation model without retraining it? Our new paper explores this question through control-inspired notions of feature observability and controllability in Vision-Language-Action (VLA) models. We find that state- and action-relevant information can often be linearly predicted from VLA internal representations—and that these representations can be steered at inference time to change robot behavior, without fine-tuning. As an example, on a real robot, our approach increased the preferred handle-grasp rate from 14% to 74%, while adding only ~1% inference-time overhead. The broader idea is that representation-level control could provide a lightweight interface for adapting robot foundation models to new preferences and constraints—without retraining. Joint work with Hugo Buurmeijer Carmen Amo Alonso @SwannAiden Paper: #PhysicalAI# #Robotics# #VLA# #RobotLearning# @StanfordEng @StanfordAILab

How reliably can today’s robot policies complete tasks when the world changes mid-execution? In real-world robotics, things rarely go exactly as planned. Objects move, unexpected obstacles appear, and observations change as robots interact with their surroundings. Understanding how well robot policies handle these changes is essential for deploying Physical AI in the real world. In our new paper, LIBERO-MAX: Do Robot Policies Adapt When the World Changes?, we introduce a benchmark designed to study this question. We evaluate 14 state-of-the-art robot policies across 8,000 cases, introducing controlled changes after the robot has already begun acting. The results suggest that adapting to a changing world remains a key challenge for today’s robot policies. Task success drops by 11–26 percentage points, particularly when geometry or observations change, and simply updating policies more frequently does not close the gap. LIBERO-MAX provides a systematic way to measure these challenges, helping identify where current policies fall short and guiding the development of more adaptive and robust Physical AI systems. 📄 Paper: 🌐 Benchmark and project website: 💻 Code: Work led by @YunbeiZhang, in collaboration with Zijian Jin, Yuanzhe Liu, Janet Wang, Xilun Zhang, Yuyou Zhang, Zhenyu Zhang, Daoan Zhang, Shuaicheng Niu, Gen Li, Jianfei Yang, Jihun Hamm, Ismini Lourentzou, Weirui Ye, Bo Liu, and Peter Stone. #Robotics# #PhysicalAI# #RobotLearning# #RobotFoundationModels# #AutonomousSystems#

🤖 Expensive robot data is scarce, so why not learn from our everyday first-person videos? This work turns human hand motion into robot actions to pretrain VLA models. 📰 Title: ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining 🔗 URL: 💡 Overview ACE-Ego-0 unifies robot demonstrations with egocentric human videos (Ego4D, EPIC-KITCHENS, and more) to pretrain Vision-Language-Action (VLA) models, trained on over 6,000 hours of combined data. 🔍 Challenges Solved Robot demonstrations are costly to collect, while human videos are cheap and abundant. But the two differ in action space, embodiment structure, temporal dynamics, and supervision quality, so naively mixing them breaks training. 🛠 Methodology & Proposed Approach ・Unifies actions in head-camera coordinates with 6D rotations, treating the human hand as an end-effector ・Encodes robot URDFs into morphology tokens via a GNN to absorb structural differences ・Chunks actions by consistent physical duration instead of fixed steps for temporal alignment ・Applies a reliability-weighted loss to noisy human videos, focusing on trustworthy position channels 📊 Use Cases / Results On RoboCasa it hits 72.8% average success (vs GR00T-N1.6 at 47.6%) and ~91% on RoboTwin 2.0. On a real bimanual robot it reaches 78.3% average (π0.5: 71.7%). Strikingly, on a task with only 34 robot demos, adding 419 human video episodes lifted success from 10% to 40%, a 4x gain. #RobotLearning# #VLA#

🦾 Why Data, Not Models, Is the Real Moat in Embodied AI The timing of this question is hard to miss. This week, the World Humanoid Robot Games released a 2,500+ hour dataset covering 12 scenario categories, 44 operations, and more than 10,000 tasks. Crucially, it also includes failures and edge cases. But raw hours tell only part of the story. Zhihu contributor 于超, an assistant professor at Tsinghua Shenzhen International Graduate School, shares his team’s view on why data has become embodied AI’s hardest-to-replicate advantage. 1️⃣ Robot scaling is fundamentally asymmetric Like language models, robot policies appear to benefit from more data, larger models, and greater compute. But these three inputs do not scale equally. Model architectures can be studied and reproduced quickly. General-purpose compute can, in principle, be purchased. High-quality robot data is different. It must be accumulated through physical interaction, and competitors cannot recreate it overnight. That asymmetry is what turns data into a moat. 2️⃣ Robot data must be manufactured LLMs inherited decades of internet data. Robots did not. Every useful trajectory must be produced through physical interaction. Even a simple cup-grasping task changes with the object, lighting, environment, camera angle, and robot body. So raw hours are not enough. What matters is the diversity of embodiments, tasks, objects, failures, and recoveries. Open X-Embodiment needed more than 20 institutions and 22 robot platforms to collect over one million trajectories. DROID used 50 collectors for a year, producing only 350 hours of data. New methods such as UMI and egocentric recording make collection easier. But every hour still requires real people, equipment, and time. 3️⃣ A successful trajectory can still be bad data Robot data quality is more complicated than whether a task was completed. On the hardware side, camera accuracy, encoder readings, force sensors, calibration, communication latency, and synchronization across modalities can all corrupt a trajectory. The human operator adds another source of noise. Teleoperating a robot is not the same as performing the action directly. Operators hesitate, pause, readjust, and develop habits for compensating for the control system. A task may succeed even when parts of the demonstration should never be imitated. Success is therefore only the coarsest possible label. One trajectory can contain both excellent behavior and inefficient or misleading actions. Training on the entire trajectory without distinction effectively tells the robot to learn both. 4️⃣ The next challenge is information density Collecting more trajectories is only half the problem. Teams must also identify which parts are worth learning from. Yu Chao’s team developed STEAM to detect local progress within a trajectory without frame-by-frame annotation or manually designed rewards. It separates useful progress from hesitation, failure, and recovery. The key question is shifting from “How many trajectories do we have?” to “How much useful information does each trajectory contain?” 5️⃣ Embodied data is physically expensive Text can be copied. Videos can be downloaded. Robot data requires a physical production process. Collecting one hour may involve a robot, sensors, teleoperation equipment, an operator, a suitable environment, task materials, and engineers who maintain and calibrate the system. Real factories, stores, and homes add even more complexity. And pressing the record button is only the beginning. Transmission, cleaning, governance, and storage can cost more than collection itself. The author offers a rough calculation. If a company wants one million hours of real-world data and reduces the combined collection and management cost to RMB 200 per hour, the total still reaches RMB 200 million. 🔑 The real moat compounds over time Quantity, quality, and cost explain why embodied AI data cannot be replicated through a short burst of spending. Large, diverse, high-quality datasets require physical infrastructure, operational discipline, and years of accumulation. As robot policies continue to benefit from scaling, the durable advantage will belong to teams that can repeatedly: 🔹 Collect broader real-world experience 🔹 Identify the most informative behavior 🔹 Preserve failures and recovery signals 🔹 Turn noisy trajectories into useful learning data In embodied AI, having data and knowing how to use it are becoming two very different capabilities. And the second may ultimately matter even more than the first. 🔗 Full analysis: #EmbodiedAI# #Robotics# #PhysicalAI# #RobotLearning# #AIData# #ScalingLaw# #Tsinghua#