Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Check out our #ICRA2025 paper ! Robust, precise, and terrain-aware—our RL controller significantly improves over baselines for whole-body 6-DoF tracking.💥 Project website: Work led by: Tifanny Portela, Andrei Cramariuc, Mayank Mittal and Marco Hutter

Robotic Systems Lab

31,240 subscribers

16,165 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Bildung #ICRA2025

Anya Rossi• Live Now

Private livecam show

2 Kommentare

Profilbild von qTask

qTaskvor 1 Jahr

Impressive work in advancing whole-body 6-DoF tracking with your terrain-aware RL controller! The noteworthy improvements over baselines showcase the strength of merging robustness and precision in robotic control. Excited to see how this research enhances real-world robot mobility and autonomy at #ICRA2025. Kudos to TifannyPortela, Andrei Cramariuc, Mayank Mittal, and Marco Hutter for leading this innovative effort! 🚀🤖

Profilbild von SaoAI

SaoAIvor 1 Jahr

@TifannyPortela Fab work, fam! 😍✨ #Slay 💪🎉

Ähnliche Videos

Check out our #ICRA2025 paper where we train a home robot to walk quietly! Project site: Video: Authors: Ryo Watanabe, Takahiro Miki, Fan Shi, Yuki Kadokawa, Filip Bjelonic, Kento Kawaharazuka, Andrei Cramariuc and Marco Hutter

Check out our #ICRA2025 paper where we train a home robot to walk quietly! Project site: Video: Authors: Ryo Watanabe, Takahiro Miki, Fan Shi, Yuki Kadokawa, Filip Bjelonic, Kento Kawaharazuka, Andrei Cramariuc and Marco Hutter

Robotic Systems Lab

34,062 Aufrufe • vor 1 Jahr

How can lightweight drones without depth cameras navigate using monocular images? Check out our paper at ISER 2023! MonoNav: MAV Navigation via Monocular Depth Estimation and Reconstruction arXiv: website: Work led by Nate Simon

How can lightweight drones without depth cameras navigate using monocular images? Check out our paper at ISER 2023! MonoNav: MAV Navigation via Monocular Depth Estimation and Reconstruction arXiv: website: Work led by Nate Simon

Anirudha Majumdar

27,642 Aufrufe • vor 2 Jahren

Our work WorldScribe led by Ruei-Che Chang on generating context-aware live visual descriptions has received 🏆✨ Best Paper Award ✨ at #UIST2024!! Check out our new video below, and details in the thread! Here is what NotebookLM thought about it:

Our work WorldScribe led by Ruei-Che Chang on generating context-aware live visual descriptions has received 🏆✨ Best Paper Award ✨ at #UIST2024!! Check out our new video below, and details in the thread! Here is what NotebookLM thought about it:

Anhong Guo

13,266 Aufrufe • vor 1 Jahr

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

How do you give a humanoid the general motion capability? Not just single motions, but all motion? Introducing SONIC, our new work on supersizing motion tracking for natural humanoid control. We argue that motion tracking is the scalable foundation task for humanoids. So we "supersized" it: 9k+ GPU hours and 100M+ motion frames. But tracking alone is not enough; we show how to make a useful control system out of it: - Universal Kinematic Planner: Enables game-like gamepad control and high-level teleoperation, just like controlling a character in a game. - VR Full-Body Teleop: Direct, real-time whole-body control by a human wearing a VR headset. - VR Keypoint Teleop: Control the upper body (hands/head) while our planner handles robust locomotion automatically. - VLA Integration: We connect this motion tracker to autonomous Visual-Language-Action (VLA) models for autonomous task execution! We use a Universal Token Space to UNIFY this command space, turning our robust tracker into a general-purpose, programmable humanoid brain. This is the generalist "System 1" for humanoids. 🚀 Project: #Humanoids #Robotics #AI #FoundationModels #NVIDIAResearch 🧠🔥

Zhengyi “Zen” Luo

62,208 Aufrufe • vor 8 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.

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

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 project is co-led by Xiaoshen Han, check out his following threads for more details. 🧵 PS: one of my favorite parts of this project was the first time we saw the robots move significantly faster and smoother than the baselines. The videos below are all real time. 👇

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 project is co-led by Xiaoshen Han, check out his following threads for more details. 🧵 PS: one of my favorite parts of this project was the first time we saw the robots move significantly faster and smoother than the baselines. The videos below are all real time. 👇

Haoyu Xiong

66,099 Aufrufe • vor 17 Tagen

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that **force-related data wasn’t captured**: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a **portable visuo-tactile gripper** by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate **cross-modal representation learning** and **downstream policy learning** on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):

I was really impressed by the UMI gripper (Cheng Chi et al.), but a key limitation is that force-related data wasn’t captured: humans feel haptic feedback through the mechanical springs, but the robot couldn’t leverage that info, limiting the data’s value for fine-grained manipulation tasks. Led by my amazing students Yolanda Zhu and Binghao Huang, we designed a portable visuo-tactile gripper by integrating our dense, flexible tactile arrays with the UMI gripper to enable large-scale in-the-wild data collection. 🔗 We demonstrate cross-modal representation learning and downstream policy learning on tasks requiring in-hand state estimation (e.g., test tube reorientation) and fine-grained force sensing (e.g., pipette fluid transfer). Key takeaways: - Our flexible tactile arrays store the rich haptic information humans perceive as dense tactile signals. - Portability and robustness are key for in-the-wild data collection; our portable gripper is compact, lightweight, and durable. - Touch provides precise, robust measurements of in-hand object pose, invariant to lighting and viewpoint. - Cross-modal pretraining on large-scale in-the-wild data significantly improves policy robustness and sample efficiency (as shown many times before — and verified again here!). Also check out our previous investigations of dense, flexible tactile grids for understanding human-robot-environment interactions: - Dense tactile glove (Nature ’19): - 3D-ViTac (CoRL ’24):

Yunzhu Li

13,188 Aufrufe • vor 1 Jahr

🌍Are LLMs aware of cultural and legal safety in today’s geo-diverse world? 🚀Introducing SafeWorld, our #NeurIPS2024 paper and benchmark assessing LLMs’ understanding of geo-diverse safety, based on cultural norms and policies across 50 countries and 493 regions/races. ⚖️We also propose a multi-dimensional framework for evaluating contextual appropriateness, accuracy, and comprehensiveness, revealing major gaps in current LLMs. 🧨To address this, we train SafeWorldLM using DPO, achieving SOTA performance and a 20% higher global human evaluator rating in helpfulness and harmfulness over competing models, including GPT-4o. 🔗Paper: 💻 GitHub: 🫶🏻This is a joint leading effort with Da Yin. Also many thanks to the amazing team Kung-Hsiang Steeve Huang Kai-Wei Chang, and Violet Peng for their hard work. Check out more details and results we conclude from our paper in the thread below. 🧵

🌍Are LLMs aware of cultural and legal safety in today’s geo-diverse world? 🚀Introducing SafeWorld, our #NeurIPS2024 paper and benchmark assessing LLMs’ understanding of geo-diverse safety, based on cultural norms and policies across 50 countries and 493 regions/races. ⚖️We also propose a multi-dimensional framework for evaluating contextual appropriateness, accuracy, and comprehensiveness, revealing major gaps in current LLMs. 🧨To address this, we train SafeWorldLM using DPO, achieving SOTA performance and a 20% higher global human evaluator rating in helpfulness and harmfulness over competing models, including GPT-4o. 🔗Paper: 💻 GitHub: 🫶🏻This is a joint leading effort with Da Yin. Also many thanks to the amazing team Kung-Hsiang Steeve Huang Kai-Wei Chang, and Violet Peng for their hard work. Check out more details and results we conclude from our paper in the thread below. 🧵

Haoyi Qiu

16,344 Aufrufe • vor 1 Jahr

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n

The power of generative models — now embodied in humanoids. Announcing DreamControl –– After a year-long research effort at General Robotics — we present a scalable framework for whole-body humanoid control that fuses diffusion priors with reinforcement learning to unlock real-world scene interaction. Diffusion + RL → natural whole-body skills on real robots. DreamControl enables humanoids to move beyond locomotion demos → performing natural, human-like skills such as –– Picking & lifting objects, Opening drawers & doors, Precise punching, kicking, and jumping, Bimanual manipulation tasks Our key innovation: a diffusion prior over human motion that guides RL, eliminating the need for massive teleoperation datasets, and producing motions that look human while transferring to real hardware. Trained purely in simulation, deployed on the Unitree G1 humanoid, DreamControl policies run in real time, bridging sim-to-real with unprecedented naturalness. We leverage a novel hybrid edge + cloud infrastructure that runs RL-trained policies on the edge backed by powerful AI models running in the cloud This is the next step in General Robotics’ journey toward general-purpose humanoid assistants that interact, adapt, and assist autonomously. Paper: Blog: 1/n

Ashish Kapoor

118,133 Aufrufe • vor 10 Monaten

Meta presents Sapiens Foundation for Human Vision Models discuss: We present Sapiens, a family of models for four fundamental human-centric vision tasks - 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. We observe that, given the same computational budget, self-supervised pretraining on a curated dataset of human images significantly boosts the performance for a diverse set of human-centric tasks. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic. Our simple model design also brings scalability - model performance across tasks improves as we scale the number of parameters from 0.3 to 2 billion. Sapiens consistently surpasses existing baselines across various human-centric benchmarks. We achieve significant improvements over the prior state-of-the-art on Humans-5K (pose) by 7.6 mAP, Humans-2K (part-seg) by 17.1 mIoU, Hi4D (depth) by 22.4% relative RMSE, and THuman2 (normal) by 53.5% relative angular error.

Meta presents Sapiens Foundation for Human Vision Models discuss: We present Sapiens, a family of models for four fundamental human-centric vision tasks - 2D pose estimation, body-part segmentation, depth estimation, and surface normal prediction. Our models natively support 1K high-resolution inference and are extremely easy to adapt for individual tasks by simply fine-tuning models pretrained on over 300 million in-the-wild human images. We observe that, given the same computational budget, self-supervised pretraining on a curated dataset of human images significantly boosts the performance for a diverse set of human-centric tasks. The resulting models exhibit remarkable generalization to in-the-wild data, even when labeled data is scarce or entirely synthetic. Our simple model design also brings scalability - model performance across tasks improves as we scale the number of parameters from 0.3 to 2 billion. Sapiens consistently surpasses existing baselines across various human-centric benchmarks. We achieve significant improvements over the prior state-of-the-art on Humans-5K (pose) by 7.6 mAP, Humans-2K (part-seg) by 17.1 mIoU, Hi4D (depth) by 22.4% relative RMSE, and THuman2 (normal) by 53.5% relative angular error.

AK

151,582 Aufrufe • vor 1 Jahr

Big News: CR San Diego is back on Sept 22-23 - right on the water with a brand new website 👇 And we've made some huge changes for our event this year! Less tech talks. More brand talks. Less panels. More Keynotes. More giveaways. More brand activations. Even better Food. (yes even better than before) Lots of giveaways ($120,000 to be exact) Plenty of BRĒZ With over 600+ attendees expected, we're back for the 3rd year! $100 off tickets right now with coupon code: EARLYBIRD With a high focus on content led by the best MC: Nick Shackelford Some of our speakers include: Gary Vaynerchuk, Ezra Firestone, Taylor Holiday, , Alex Cooper, John Roman, Bryan Cano, Curtis Matsko, @MacCoyMerkle, Mehtab | Karta Ventures, Social Savannah, and many many more still finalizing. Get your tickets now -we've sold out of all our events 3 years in a row and expect to sell out once again this year! $100 off tickets right now with coupon code: EARLYBIRD Get your tickets now and check out our brand new website today!

Jimmy Kim

148,433 Aufrufe • vor 1 Jahr

You might have seen the WuBOT performing at the 2026 Spring Festival Gala; however, most high-dynamic extreme motions you see are executed by overfitted tracking policies. Until now, training a unified policy capable of performing various extreme motions with a high success rate remained an unsolved challenge. We spent an entire year digging into the barrier between general tracking and extreme physical behaviors. After burning through dozens of G1 robots, we finally identified the bottleneck of learning and physical executability. With these discoveries, we developed OmniXtreme: the first general policy that can execute diverse extreme motions, including consecutive flips, extreme balancing, and even breakdancing with rapid contact switches! This capability is achieved by pre-training a flow-based generative control policy and then post-training with actuation-aware residual RL for complex physical dynamics—a step we found critical for successful real-world transfer. This work is a joint collaboration with Unitree. Together, we are pushing the physical limits of humanoid robots. It is incredibly exciting to see a general "robot gymnast" and "robot breakdancer" come to life! It was also our first time publishing a paper with XingXing, which was an enlightening experience. The model checkpoints are now released—we welcome you to play with them! 📦 📄 Paper: 🌐 Project: 💻 Code:

You might have seen the WuBOT performing at the 2026 Spring Festival Gala; however, most high-dynamic extreme motions you see are executed by overfitted tracking policies. Until now, training a unified policy capable of performing various extreme motions with a high success rate remained an unsolved challenge. We spent an entire year digging into the barrier between general tracking and extreme physical behaviors. After burning through dozens of G1 robots, we finally identified the bottleneck of learning and physical executability. With these discoveries, we developed OmniXtreme: the first general policy that can execute diverse extreme motions, including consecutive flips, extreme balancing, and even breakdancing with rapid contact switches! This capability is achieved by pre-training a flow-based generative control policy and then post-training with actuation-aware residual RL for complex physical dynamics—a step we found critical for successful real-world transfer. This work is a joint collaboration with Unitree. Together, we are pushing the physical limits of humanoid robots. It is incredibly exciting to see a general "robot gymnast" and "robot breakdancer" come to life! It was also our first time publishing a paper with XingXing, which was an enlightening experience. The model checkpoints are now released—we welcome you to play with them! 📦 📄 Paper: 🌐 Project: 💻 Code:

Siyuan Huang

107,090 Aufrufe • vor 5 Monaten

Introducing Digital Red Queen (DRQ): Adversarial Program Evolution in Core War with LLMs Blog: Core War is a programming game where self-replicating assembly programs, called warriors, compete for control of a virtual machine. In this dynamic environment, where there is no distinction between code and data, warriors must crash opponents while defending themselves to survive. In this work, we explore how LLMs can drive open-ended adversarial evolution of these programs within Core War. Our approach is inspired by the Red Queen Hypothesis from evolutionary biology: the principle that species must continually adapt and evolve simply to survive against ever-changing competitors. We found that running our DRQ algorithm for longer durations produces warriors that become more generally robust. Most notably, we observed an emergent pressure towards convergent evolution. Independent runs, starting from completely different initial conditions, evolved toward similar general-purpose behaviors—mirroring how distinct species in nature often evolve similar traits to solve the same problems. Simulating these adversarial dynamics in an isolated sandbox offers a glimpse into the future, where deployed LLM systems might eventually compete against one another for computational or physical resources in the real world. This project is a collaboration between MIT and Sakana AI led by Akarsh Kumar Full Paper (Website): Full Paper (arxiv): Code:

Introducing Digital Red Queen (DRQ): Adversarial Program Evolution in Core War with LLMs Blog: Core War is a programming game where self-replicating assembly programs, called warriors, compete for control of a virtual machine. In this dynamic environment, where there is no distinction between code and data, warriors must crash opponents while defending themselves to survive. In this work, we explore how LLMs can drive open-ended adversarial evolution of these programs within Core War. Our approach is inspired by the Red Queen Hypothesis from evolutionary biology: the principle that species must continually adapt and evolve simply to survive against ever-changing competitors. We found that running our DRQ algorithm for longer durations produces warriors that become more generally robust. Most notably, we observed an emergent pressure towards convergent evolution. Independent runs, starting from completely different initial conditions, evolved toward similar general-purpose behaviors—mirroring how distinct species in nature often evolve similar traits to solve the same problems. Simulating these adversarial dynamics in an isolated sandbox offers a glimpse into the future, where deployed LLM systems might eventually compete against one another for computational or physical resources in the real world. This project is a collaboration between MIT and Sakana AI led by Akarsh Kumar Full Paper (Website): Full Paper (arxiv): Code:

Sakana AI

143,892 Aufrufe • vor 6 Monaten

Three years ago, we released one of our most iconic creations for Azuki Elementals, brilliantly directed by the talented Wesley Andrew. 🎬✨ We've noticed it popping up on other accounts and we're not sure if people really know who made it. Twas us! Haha and we couldn't be prouder of it. Can you imagine a whole series in this style? That'd slap right? Be sure to check out the lead credits below, showcasing the incredible team behind the film. For full credits, visit the project page on our website! Client: Azuki Director: Wesley Louis Director cover: Bjorn Erik Aschim Art Director: Agathe Leroux Producer: Katerina Grecova Animation Lead: Bishoy Gendi Compositing Lead: Nick Herbert Music & Audio: bxftys #Anime #azuki #animation #FilmCredits #2danimation #THELINE #AnimationMagic #AzukiElementals

Three years ago, we released one of our most iconic creations for Azuki Elementals, brilliantly directed by the talented Wesley Andrew. 🎬✨ We've noticed it popping up on other accounts and we're not sure if people really know who made it. Twas us! Haha and we couldn't be prouder of it. Can you imagine a whole series in this style? That'd slap right? Be sure to check out the lead credits below, showcasing the incredible team behind the film. For full credits, visit the project page on our website! Client: Azuki Director: Wesley Louis Director cover: Bjorn Erik Aschim Art Director: Agathe Leroux Producer: Katerina Grecova Animation Lead: Bishoy Gendi Compositing Lead: Nick Herbert Music & Audio: bxftys #Anime #azuki #animation #FilmCredits #2danimation #THELINE #AnimationMagic #AzukiElementals

THE LINE

89,228 Aufrufe • vor 1 Monat

This work is not about a new technique. GMT (General Motion Tracking) shows good engineering practices that you can actually train a single unified whole-body control policy for all agile motion, and it works in the real world, directly with sim2real without adaptation. This is different from many existing works that trains/adapts one individual policy for each specific motion. Instead of just showing the beautiful motions/dances, this is actually practical. Because now you can convert all types of commands into real actions in real time without tuning anything. Visit to check out how we handle the following challenges: ✅ Partial Observability. ✅ Hardware Limitations. ✅ Unbalanced Data Distribution. ✅ Model Expressiveness. Work led by Zixuan Chen Mazeyu Ji

This work is not about a new technique. GMT (General Motion Tracking) shows good engineering practices that you can actually train a single unified whole-body control policy for all agile motion, and it works in the real world, directly with sim2real without adaptation. This is different from many existing works that trains/adapts one individual policy for each specific motion. Instead of just showing the beautiful motions/dances, this is actually practical. Because now you can convert all types of commands into real actions in real time without tuning anything. Visit to check out how we handle the following challenges: ✅ Partial Observability. ✅ Hardware Limitations. ✅ Unbalanced Data Distribution. ✅ Model Expressiveness. Work led by Zixuan Chen Mazeyu Ji

Xiaolong Wang

83,261 Aufrufe • vor 1 Jahr

🤖 Ever dreamed of controlling a humanoid robot to perform complex, long-horizon tasks — using just a single Vision Pro? 🎉 Meet CLONE: a holistic, closed-loop, whole-body teleoperation system for long-horizon humanoid control! 🏃‍♂️🧍 CLONE enables rich and coordinated interactive tasks: 🥊 boxing 🏓 table tennis 🤲 object pickup 📦 room arrangement 🤝 handover … and more! 🌀 Our closed-loop error correction powered by LiDAR odometry ensures precision, while motion-captured demonstrations supercharge policy learning — unlocking the full potential of the G1 robot. 🎥 It’s hard to squeeze the magic into 1 minute — check out the full video demo and project page here: 🔗

🤖 Ever dreamed of controlling a humanoid robot to perform complex, long-horizon tasks — using just a single Vision Pro? 🎉 Meet CLONE: a holistic, closed-loop, whole-body teleoperation system for long-horizon humanoid control! 🏃‍♂️🧍 CLONE enables rich and coordinated interactive tasks: 🥊 boxing 🏓 table tennis 🤲 object pickup 📦 room arrangement 🤝 handover … and more! 🌀 Our closed-loop error correction powered by LiDAR odometry ensures precision, while motion-captured demonstrations supercharge policy learning — unlocking the full potential of the G1 robot. 🎥 It’s hard to squeeze the magic into 1 minute — check out the full video demo and project page here: 🔗

Siyuan Huang

66,737 Aufrufe • vor 1 Jahr

On Sunday, April 14, 2025, our community kitchen in Tawila - a joint project between Hope and Haven for Refugees, and Darfur Victims Support, was honored to provide meals for 300 individuals, with additional rations added to meet their nutritional needs. I hope you have seen news about ZamZam at some point over the past few days. ZamZam is the largest refugee camp in Sudan, holding 1.2 million souls before the brutal invasion and massacres that began to take place there over the weekend. These are some of the most vulnerable people in the world, displaced multiple times, and largely abandoned by international humanitarian organizations. ZamZam specifically is designated as a region that reached conditions of famine over a year ago. We are called to do more. Estimates suggest that around 400,000 refugees have traveled 60 km under the sun, mostly on foot, with no food and water, to escape the attack on ZamZam refugee camp. They arrive in poor physical condition, hungry and thirsty, exhausted and in need of care. Help us respond to this crisis by sharing our work and donating. Every dollar is quite literally the gift of life. This kitchen, as with all of our initiatives, are volunteer run; your donations pay for meals, not salaries. You may read the headlines and watch the news and feel helpless. Please remember. We are not helpless when we work together. Don’t ask where the world is. We are the world. Link in bio - please check out our work and donate so that we can both continue and expand services. Stay with us

On Sunday, April 14, 2025, our community kitchen in Tawila - a joint project between Hope and Haven for Refugees, and Darfur Victims Support, was honored to provide meals for 300 individuals, with additional rations added to meet their nutritional needs. I hope you have seen news about ZamZam at some point over the past few days. ZamZam is the largest refugee camp in Sudan, holding 1.2 million souls before the brutal invasion and massacres that began to take place there over the weekend. These are some of the most vulnerable people in the world, displaced multiple times, and largely abandoned by international humanitarian organizations. ZamZam specifically is designated as a region that reached conditions of famine over a year ago. We are called to do more. Estimates suggest that around 400,000 refugees have traveled 60 km under the sun, mostly on foot, with no food and water, to escape the attack on ZamZam refugee camp. They arrive in poor physical condition, hungry and thirsty, exhausted and in need of care. Help us respond to this crisis by sharing our work and donating. Every dollar is quite literally the gift of life. This kitchen, as with all of our initiatives, are volunteer run; your donations pay for meals, not salaries. You may read the headlines and watch the news and feel helpless. Please remember. We are not helpless when we work together. Don’t ask where the world is. We are the world. Link in bio - please check out our work and donate so that we can both continue and expand services. Stay with us

Sadeia

19,409 Aufrufe • vor 1 Jahr

Aligning historical data with live price (live price always gets to trump historical data, your job is to be able to id where that line in the sand is and adjust your trades and risk) What the Daily Profiler is? It is a 3-month Trading Bootcamp for just $100—only 14 slots left! Class starts in a week Learn to dominate the markets with a proven, repeatable workflow designed for intraday trading success. Here’s what you get: Master your performance by understanding the intraday market conditions & volatility: We teach you how to analyze statistical market conditions and volatility and aligning it with live price daily to turn your trading system ON or OFF. Assign expected values to trades and calculate precise risk per trade. Our hybrid Daily Profiler indicator, paired with our statistical dashboard (#NQ_F, #ES_F, #YM_F, #BTC, #Copper, #Bond, #Euro, #Gold, #CrudeOil), helps you decide whether to buy the dip or sell the rip with confidence. coming soon this class our own trade journaling software that sync our data with your trades to allow you focus on mastering your performance. Live Trading & Education Phases: Over 3 months, progress through education, risk profiling, and active trading phases. Master position sizing, taking partials, and adding to winning positions—all backed by robust backtest data. Coming soon this next three months ALGO Trading. Coded by a professional LLC who has done it for multiple capitals so no nonsense glitches. Ranger Buddy AI: Your personal trading assistant checks your work before you place a trade, minimizing errors and boosting confidence ensuring that you are sticking to the rules. Daily Live Trading: Trade alongside us and see the strategies in action. Monitor our month over month performance. We aren't in the game of buy 15 prop accounts and shuffling through the ones that is up. You get to see the account # of live and props and we expect the same professionalism out of our traders Don’t miss out! Only 14 spots remain for this game-changing bootcamp. Signup in the comments. Austin Clark

Aligning historical data with live price (live price always gets to trump historical data, your job is to be able to id where that line in the sand is and adjust your trades and risk) What the Daily Profiler is? It is a 3-month Trading Bootcamp for just $100—only 14 slots left! Class starts in a week Learn to dominate the markets with a proven, repeatable workflow designed for intraday trading success. Here’s what you get: Master your performance by understanding the intraday market conditions & volatility: We teach you how to analyze statistical market conditions and volatility and aligning it with live price daily to turn your trading system ON or OFF. Assign expected values to trades and calculate precise risk per trade. Our hybrid Daily Profiler indicator, paired with our statistical dashboard (#NQ_F, #ES_F, #YM_F, #BTC, #Copper, #Bond, #Euro, #Gold, #CrudeOil), helps you decide whether to buy the dip or sell the rip with confidence. coming soon this class our own trade journaling software that sync our data with your trades to allow you focus on mastering your performance. Live Trading & Education Phases: Over 3 months, progress through education, risk profiling, and active trading phases. Master position sizing, taking partials, and adding to winning positions—all backed by robust backtest data. Coming soon this next three months ALGO Trading. Coded by a professional LLC who has done it for multiple capitals so no nonsense glitches. Ranger Buddy AI: Your personal trading assistant checks your work before you place a trade, minimizing errors and boosting confidence ensuring that you are sticking to the rules. Daily Live Trading: Trade alongside us and see the strategies in action. Monitor our month over month performance. We aren't in the game of buy 15 prop accounts and shuffling through the ones that is up. You get to see the account # of live and props and we expect the same professionalism out of our traders Don’t miss out! Only 14 spots remain for this game-changing bootcamp. Signup in the comments. Austin Clark

Random Mick

15,649 Aufrufe • vor 1 Jahr