Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Say hello to GR-2! With upgrades across hardware, design, and software, GR-2 rides into a new journey to the future of humanoid robotics. Bon voyage! Highlights: - H 175cm; W 63kg; DoF 53 - 12-DoF Dexterous Hand - Peak torque 230N.m - Optimized Tools for Innovative Development

Fourier

2,534 subscribers

19,557 görüntüleme • 1 yıl önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

8 Yorum

Kordel France profil fotoğrafı

Kordel France1 yıl önce

Fantastic work! Do you think there will ever be a need to add the sense of smell to humanoid robots?

Jacob Valdez profil fotoğrafı

Jacob Valdez1 yıl önce

increadible!

Barry Sayer 💻⌨️🖱️☁️🤖🍓 ᯅ 🐙 profil fotoğrafı

Barry Sayer 💻⌨️🖱️☁️🤖🍓 ᯅ 🐙1 yıl önce

Nice work 👍🏻

Risichad 🦾 profil fotoğrafı

Risichad 🦾1 yıl önce

🦾

Neander profil fotoğrafı

Neander1 yıl önce

All these bots are taking such “baby steps”. But really babies are bolder in their steps. Watching them inch around it feels like these bots are being held back in their stride. Like they need to risk a fall and actually try a full step. Otherwise just put ‘em on wheels.

Neo profil fotoğrafı

Neo1 yıl önce

Why is the design of robots going that way then they have to look like humans Isn't it more practical to look like that to be more functional even better than human capabilities

机器人莫非 profil fotoğrafı

机器人莫非1 yıl önce

A Criminal Gang to steal AMBER Robotics technology secrets, what a sham. This is the orgional humanoid he never won.

机器人莫非 profil fotoğrafı

机器人莫非1 yıl önce

The one act like a zombie, because he stole the 1st generation, but no more for further updates.

Benzer Videolar

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Scaling vision-language-action (VLA) models to high-DoF dexterous hands has long been a "holy grail" challenge due to the high-dimensional action space and data scarcity. As a wrap up of the year 2025, we are releasing GR-Dexter, a holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. This is the first VLA system to achieve: ✅ High-DoF Control: Managing a 56-DoF bimanual system (21-DoF per hand). ✅ Long-Horizon Tasks with tool use: Vacuuming, bread serving with tongs, and table decluttering. ✅ Open-World Generalization: Robust performance with unseen objects and abstract instructions. Project page: ArXiv:

Xiao Ma

93,749 görüntüleme • 6 ay önce

Video: China firm to unveil world’s most ‘adorable’ humanoid robot for homes, schools | Christopher McFadden, Interesting Engineering Fourier’s latest humanoid robot, the GR‑3, is designed for domestic and educational environments. Fourier Robotics, the Shanghai-based robotics firm behind the GR-1 and GR-2 models, is preparing to launch its GR-3 humanoid robot on August 6. Early glimpses of the new robot, including a sneak-peek video, reveal a smaller, friendlier design, described as possibly the “most adorable humanoid robot yet.” Concrete information is scarce, but early reports suggest the robot will be smaller than its predecessors. According to some reports, the GR-3 will likely stand at around 4 feet 5 inches (134 cm). This makes it notably smaller than the earlier GR-1 (5.4 feet/165 cm) and GR-2 (5.74 feet/175 cm) models from Fourier. Most notable is its apparent “softer,” almost cuddly aesthetic.” The robot is likely intended for use in homes, schools, hospitals, and public spaces. It also features an integrated large language model (LLM) to enable natural speech engagement with users. To this end, the GR-3 will likely be marked as a companion‑style or caregiver bot (AKA a “Care‑bot”) aimed at friendly human interaction in personal or learning environments. GR-3: Fourier’s cutest robot yet “This softer aesthetic is a nice change compared to the usual designs we see with humanoid robots. The eyes are a much-needed touch,” comments a member on the Companian Robot Forums. “It’s so expressive and draws you in. Can’t wait to see what this looks like. Hopefully it is reasonably priced. Could definitely see myself owning one of these,” they added. The GR-3 is a natural progression of the company’s previous models. The first, the GR-1, was launched by Foureir in 2023 and was its first mass-targeted humanoid, featuring 44 joints and capable of walking at 3.1 mph (5 kph). Capable of carrying around 6.6. pounds (3 kg) of weight, it featured advanced perception via six RGB cameras that formed real-time 3D occupancy grids, an LLM-based emotional interaction system, and modular Fourier Smart Actuators (FSA) delivering around 230 N/m of torque. The GR-2 was debuted in 2024 and raised the bar with a taller frame (~175 cm, 63 kg), 53 degrees of freedom, enhanced 12 degrees of freedom (DoF) dexterous hands with tactile sensors, and power-dense FSA 2.0 actuators (around 380 N/m torque). Given this lineage, the GR-3 is likely to continue innovating in areas such as compact hardware design, featuring a shorter, lighter frame tailored to domestic spaces. It will also build on the company’s focus on friendly user interaction thanks to its softer aesthetic and approachable interface. The GR-3 will also likely feature use-case-specific actuation and sensing, likely simpler than the GR-2’s high-precision hands but optimized for social or light domestic tasks. Scheduled for release in August It will likely also feature an accessible software stack continuing Fourier’s support for developers via pre‑built APIs and possibly integration with LLMs and vision systems. Fourier has confirmed the robot’s official reveal is scheduled for early August, with teaser posts on X and robotics forums generating anticipation among fans and researchers. When formally revealed, the GR‑3 could represent Fourier’s first small-form social humanoid, bridging the gap between research platforms and home or classroom robots. Read more:

Video: China firm to unveil world’s most ‘adorable’ humanoid robot for homes, schools | Christopher McFadden, Interesting Engineering Fourier’s latest humanoid robot, the GR‑3, is designed for domestic and educational environments. Fourier Robotics, the Shanghai-based robotics firm behind the GR-1 and GR-2 models, is preparing to launch its GR-3 humanoid robot on August 6. Early glimpses of the new robot, including a sneak-peek video, reveal a smaller, friendlier design, described as possibly the “most adorable humanoid robot yet.” Concrete information is scarce, but early reports suggest the robot will be smaller than its predecessors. According to some reports, the GR-3 will likely stand at around 4 feet 5 inches (134 cm). This makes it notably smaller than the earlier GR-1 (5.4 feet/165 cm) and GR-2 (5.74 feet/175 cm) models from Fourier. Most notable is its apparent “softer,” almost cuddly aesthetic.” The robot is likely intended for use in homes, schools, hospitals, and public spaces. It also features an integrated large language model (LLM) to enable natural speech engagement with users. To this end, the GR-3 will likely be marked as a companion‑style or caregiver bot (AKA a “Care‑bot”) aimed at friendly human interaction in personal or learning environments. GR-3: Fourier’s cutest robot yet “This softer aesthetic is a nice change compared to the usual designs we see with humanoid robots. The eyes are a much-needed touch,” comments a member on the Companian Robot Forums. “It’s so expressive and draws you in. Can’t wait to see what this looks like. Hopefully it is reasonably priced. Could definitely see myself owning one of these,” they added. The GR-3 is a natural progression of the company’s previous models. The first, the GR-1, was launched by Foureir in 2023 and was its first mass-targeted humanoid, featuring 44 joints and capable of walking at 3.1 mph (5 kph). Capable of carrying around 6.6. pounds (3 kg) of weight, it featured advanced perception via six RGB cameras that formed real-time 3D occupancy grids, an LLM-based emotional interaction system, and modular Fourier Smart Actuators (FSA) delivering around 230 N/m of torque. The GR-2 was debuted in 2024 and raised the bar with a taller frame (~175 cm, 63 kg), 53 degrees of freedom, enhanced 12 degrees of freedom (DoF) dexterous hands with tactile sensors, and power-dense FSA 2.0 actuators (around 380 N/m torque). Given this lineage, the GR-3 is likely to continue innovating in areas such as compact hardware design, featuring a shorter, lighter frame tailored to domestic spaces. It will also build on the company’s focus on friendly user interaction thanks to its softer aesthetic and approachable interface. The GR-3 will also likely feature use-case-specific actuation and sensing, likely simpler than the GR-2’s high-precision hands but optimized for social or light domestic tasks. Scheduled for release in August It will likely also feature an accessible software stack continuing Fourier’s support for developers via pre‑built APIs and possibly integration with LLMs and vision systems. Fourier has confirmed the robot’s official reveal is scheduled for early August, with teaser posts on X and robotics forums generating anticipation among fans and researchers. When formally revealed, the GR‑3 could represent Fourier’s first small-form social humanoid, bridging the gap between research platforms and home or classroom robots. Read more:

Owen Gregorian

64,074 görüntüleme • 11 ay önce

We sat down with AGIBOT, a leader in humanoid manufacturing, to talk about the future of robotics and our strategic partnership: AGIBOT focuses "the majority of R&D on the hardware itself" while OpenMind builds the software to launch apps to create new robot use cases.

We sat down with AGIBOT, a leader in humanoid manufacturing, to talk about the future of robotics and our strategic partnership: AGIBOT focuses "the majority of R&D on the hardware itself" while OpenMind builds the software to launch apps to create new robot use cases.

OpenMind

13,550 görüntüleme • 3 ay önce

U.S. based humanoid robotics company 1X has just unveiled their new tendon-driven robot hands with 25 degrees of freedom (DOF). • Made in USA • Tendon Drive Ratio: 5:1–15:1 • Wrist Dexterity: 3 DOF • Backdrivability: Fully backdrivable • Tactile Sensing: Pressure + location + slip • Finger Force: Up to 45 N • Wrist Torque: 17.75 Nm • Position Accuracy: ±0.2 mm • Waterproof Rating: IP68 • Reliability: >2 million cycles "These hands are designed to do something fundamental: remove the hardware ceiling on what humanoid robots can actually do, and make data the only barrier to capabilities. By matching or surpassing human hands across the dimensions that matter, they ensure our AI models are no longer limited by dexterity. NEO can now perform virtually any task a human can do with their hands– with the precision, adaptability, and gentleness required for real-world environments."

U.S. based humanoid robotics company 1X has just unveiled their new tendon-driven robot hands with 25 degrees of freedom (DOF). • Made in USA • Tendon Drive Ratio: 5:1–15:1 • Wrist Dexterity: 3 DOF • Backdrivability: Fully backdrivable • Tactile Sensing: Pressure + location + slip • Finger Force: Up to 45 N • Wrist Torque: 17.75 Nm • Position Accuracy: ±0.2 mm • Waterproof Rating: IP68 • Reliability: >2 million cycles "These hands are designed to do something fundamental: remove the hardware ceiling on what humanoid robots can actually do, and make data the only barrier to capabilities. By matching or surpassing human hands across the dimensions that matter, they ensure our AI models are no longer limited by dexterity. NEO can now perform virtually any task a human can do with their hands– with the precision, adaptability, and gentleness required for real-world environments."

Sawyer Merritt

737,997 görüntüleme • 5 gün önce

Y-Hand M1:universal hand for intelligent humanoid robots the humanoid dexterous hand with the highest degrees of freedom, developed by Yuequan Bionic Slide the pen, open the bottle, cut the paper, handle the trivial matters like a human, and soon it will be connected to the humanoid robot to become a factory operator, elderly care and home assistant. »38 DOF, 28.7k load capacity »Fingertip repeat positioning accuracy of 0.04 mm »Five-finger closure in just 0.2 seconds »Replicates human finger joints with self-developed magnetoelectric-driven artificial muscles

Y-Hand M1:universal hand for intelligent humanoid robots the humanoid dexterous hand with the highest degrees of freedom, developed by Yuequan Bionic Slide the pen, open the bottle, cut the paper, handle the trivial matters like a human, and soon it will be connected to the humanoid robot to become a factory operator, elderly care and home assistant. »38 DOF, 28.7k load capacity »Fingertip repeat positioning accuracy of 0.04 mm »Five-finger closure in just 0.2 seconds »Replicates human finger joints with self-developed magnetoelectric-driven artificial muscles

CyberRobo

14,341 görüntüleme • 9 ay önce

VLAI Robotics Launches High-Dexterity Dual-Arm Robot Starting at ~$5,500 USD VLAI Robotics, utilizing the open-source design of Japan’s OpenArm team, has introduced a high-dexterity, low-cost bimanual robotic system. The product is priced from 39,900 RMB (approximately 5,500 USD), making high-level research tools accessible to institutions and developers. The robot features a human-scale, arm-hand integrated design with up to 16 DOF (8 DOF per arm, including the gripper). It can handle a dual-arm peak payload of 12 kg while maintaining high precision. A key breakthrough is its ability to replicate human upper limb movement trajectories, which enhances data quality for imitation learning and remote operation. VLAI Robotics handled the domestic engineering, manufacturing, and VLA (Vision-Language-Action) algorithm integration, with quality control organized according to the strict standards of the OpenArm R&D framework. The robot is highly adaptable for research, education, and Physical AI training, supporting easy expansion for features like VR teleoperation.

VLAI Robotics Launches High-Dexterity Dual-Arm Robot Starting at ~$5,500 USD VLAI Robotics, utilizing the open-source design of Japan’s OpenArm team, has introduced a high-dexterity, low-cost bimanual robotic system. The product is priced from 39,900 RMB (approximately 5,500 USD), making high-level research tools accessible to institutions and developers. The robot features a human-scale, arm-hand integrated design with up to 16 DOF (8 DOF per arm, including the gripper). It can handle a dual-arm peak payload of 12 kg while maintaining high precision. A key breakthrough is its ability to replicate human upper limb movement trajectories, which enhances data quality for imitation learning and remote operation. VLAI Robotics handled the domestic engineering, manufacturing, and VLA (Vision-Language-Action) algorithm integration, with quality control organized according to the strict standards of the OpenArm R&D framework. The robot is highly adaptable for research, education, and Physical AI training, supporting easy expansion for features like VR teleoperation.

RoboHub🤖

12,961 görüntüleme • 8 ay önce

Open-source dexterous hands with fingertip sensors! 🪬 ORCA Dexterity just released three dexterous hand models. Their mission: is to democratize robotic hand dexterity. They're sharing progress on exceptional, low-cost hardware and a software layer from low-level control to robotic hand learning. This is the open-source approach to dexterous manipulation. It has 83 taxels per finger with 0.1 N force detection which pretty is impressive for an open-source design. Tactile sensing is critical for dexterous manipulation, knowing contact forces enables gentle grasping, slip detection, and force-controlled assembly. Also 700g weight for the lite version makes it practical for mounting on robot arms without exceeding payload limits. Lower weight means faster movements and lower torque requirements. Open hardware accelerates robotics by letting researchers and builders modify designs for their specific needs without starting from scratch! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Open-source dexterous hands with fingertip sensors! 🪬 ORCA Dexterity just released three dexterous hand models. Their mission: is to democratize robotic hand dexterity. They're sharing progress on exceptional, low-cost hardware and a software layer from low-level control to robotic hand learning. This is the open-source approach to dexterous manipulation. It has 83 taxels per finger with 0.1 N force detection which pretty is impressive for an open-source design. Tactile sensing is critical for dexterous manipulation, knowing contact forces enables gentle grasping, slip detection, and force-controlled assembly. Also 700g weight for the lite version makes it practical for mounting on robot arms without exceeding payload limits. Lower weight means faster movements and lower torque requirements. Open hardware accelerates robotics by letting researchers and builders modify designs for their specific needs without starting from scratch! ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

38,094 görüntüleme • 4 ay önce

🚀 SoloTech breakthrough: NVIDIA Sonic goes beyond the G1. 🌏 We’ve achieved a global first: migrating NVIDIA Sonic to a completely different humanoid morphology, the AGIBOT X2 🥇 This is a massive leap for transferable humanoid intelligence. We are moving away from single-robot controllers toward architectures that generalize across diverse embodiments. The Specs: Hardware: AGIBOT X2 Ultra (31 DoF) Precision: 14-DoF Dexterous Hands Capabilities: - End-to-end whole-body locomotion with manipulation - Single leg balancing and stylized motion - Upper body gestures Big respect to the team fueling this innovation all the way! Sitarama Chekuri Zeeshaan Mohammed samarth shukla Devinder Sodhi pranjal mehta @build Frontier Tower NVIDIA AGIBOT Nebius UFB - Ultimate Fighting Bots Vitaly Bulatov Xenia Bulatov NVIDIA Robotics To learn more about Solo Tech at the frontier of Physical AI: #PhysicalAI #Robotics #Humanoids #NVIDIA #AGIBOT #SoloTech #EmbodiedAI #SoloSeven

🚀 SoloTech breakthrough: NVIDIA Sonic goes beyond the G1. 🌏 We’ve achieved a global first: migrating NVIDIA Sonic to a completely different humanoid morphology, the AGIBOT X2 🥇 This is a massive leap for transferable humanoid intelligence. We are moving away from single-robot controllers toward architectures that generalize across diverse embodiments. The Specs: Hardware: AGIBOT X2 Ultra (31 DoF) Precision: 14-DoF Dexterous Hands Capabilities: - End-to-end whole-body locomotion with manipulation - Single leg balancing and stylized motion - Upper body gestures Big respect to the team fueling this innovation all the way! Sitarama Chekuri Zeeshaan Mohammed samarth shukla Devinder Sodhi pranjal mehta @build Frontier Tower NVIDIA AGIBOT Nebius UFB - Ultimate Fighting Bots Vitaly Bulatov Xenia Bulatov NVIDIA Robotics To learn more about Solo Tech at the frontier of Physical AI: #PhysicalAI #Robotics #Humanoids #NVIDIA #AGIBOT #SoloTech #EmbodiedAI #SoloSeven

Dhruv Diddi

26,494 görüntüleme • 2 ay önce

BCI company BrainCo just released a new dexterous hand: Revo3. But this time, it’s not for humans, it’s built for humanoid robots. ＞21 DOF ＞Full-palm + fingertip tactile sensing ＞Direct drive + backdrivable design ＞33 grasp types ＞20N fingertip pinch force ＞Open-source ecosystem, one-click deployment It looks bigger and heavier than the previous versions, but clearly designed for real robot work:picking up objects, using tools, and performing tasks... btw, what do you think are the real differences between the hands of humanoid robots and the bionic hands used by humans?

BCI company BrainCo just released a new dexterous hand: Revo3. But this time, it’s not for humans, it’s built for humanoid robots. ＞21 DOF ＞Full-palm + fingertip tactile sensing ＞Direct drive + backdrivable design ＞33 grasp types ＞20N fingertip pinch force ＞Open-source ecosystem, one-click deployment It looks bigger and heavier than the previous versions, but clearly designed for real robot work:picking up objects, using tools, and performing tasks... btw, what do you think are the real differences between the hands of humanoid robots and the bionic hands used by humans?

CyberRobo

71,684 görüntüleme • 3 ay önce

Hands full of dexterity! 🪬 It is well known that agile, versatile hands for robots are one of the Holy Grails in robotics today. Grippers and robot hands are often underestimated, and they are the actuators behind correct and accurate picking, or placing. This robotic hand was created at the Korea University of Technology and Education. 🇰🇷 The 5-finger, 12-DoF (degrees of freedom) robotic hand features 3-DoF each for the thumb, index, and middle fingers, while the ring and little fingers share a combined 3 DoF. It uses BLDC motors with ball-screw actuators and includes a clutch mechanism to absorb impacts and prevent overload. Now, a challenge for you - guess the year! Kudos to all gripper/hand-developing companies! WE CAN'T PICK WITHOUT YOU! 🏋🏼 ~~~ ♻️ RT to help 1 robot find a new workplace.

Hands full of dexterity! 🪬 It is well known that agile, versatile hands for robots are one of the Holy Grails in robotics today. Grippers and robot hands are often underestimated, and they are the actuators behind correct and accurate picking, or placing. This robotic hand was created at the Korea University of Technology and Education. 🇰🇷 The 5-finger, 12-DoF (degrees of freedom) robotic hand features 3-DoF each for the thumb, index, and middle fingers, while the ring and little fingers share a combined 3 DoF. It uses BLDC motors with ball-screw actuators and includes a clutch mechanism to absorb impacts and prevent overload. Now, a challenge for you - guess the year! Kudos to all gripper/hand-developing companies! WE CAN'T PICK WITHOUT YOU! 🏋🏼 ~~~ ♻️ RT to help 1 robot find a new workplace.

Lukas Ziegler

33,525 görüntüleme • 1 yıl önce

Dexterous hands are one of the biggest challenges in robotics, with even Elon Musk noting their development accounts for half of a humanoid robot's total work. A new approach from the Y-Hand M1 bionic hand may be a significant step forward. Based on an international first-of-its-kind "bionic tension-compression theory," the M1 replaces traditional rigid hinges with a 6-DoF joint system and uses self-developed magnetic artificial muscles. This design allows it to perform complex, human-like tasks, including: ► Mastering all 33 Feix dexterous grasp categories. ► Precisely twirling playing cards and threading a needle with subtle human-like adjustments. ► Smoothly twisting bottle caps and turning book pages. The team behind the M1 is already working on the next-gen Y-Hand M3, aiming for around 70 degrees of freedom, believing that robotic hands may soon reach or even exceed human-level dexterity.

Dexterous hands are one of the biggest challenges in robotics, with even Elon Musk noting their development accounts for half of a humanoid robot's total work. A new approach from the Y-Hand M1 bionic hand may be a significant step forward. Based on an international first-of-its-kind "bionic tension-compression theory," the M1 replaces traditional rigid hinges with a 6-DoF joint system and uses self-developed magnetic artificial muscles. This design allows it to perform complex, human-like tasks, including: ► Mastering all 33 Feix dexterous grasp categories. ► Precisely twirling playing cards and threading a needle with subtle human-like adjustments. ► Smoothly twisting bottle caps and turning book pages. The team behind the M1 is already working on the next-gen Y-Hand M3, aiming for around 70 degrees of freedom, believing that robotic hands may soon reach or even exceed human-level dexterity.

RoboHub🤖

62,997 görüntüleme • 10 ay önce

We trained a humanoid with 22-DoF dexterous hands to assemble model cars, operate syringes, sort poker cards, fold/roll shirts, all learned primarily from 20,000+ hours of egocentric human video with no robot in the loop. Humans are the most scalable embodiment on the planet. We discovered a near-perfect log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and this loss directly predicts real-robot success rate. Humanoid robots will be the end game, because they are the practical form factor with minimal embodiment gap from humans. Call it the Bitter Lesson of robot hardware: the kinematic similarity lets us simply retarget human finger motion onto dexterous robot hand joints. No learned embeddings, no fancy transfer algorithms needed. Relative wrist motion + retargeted 22-DoF finger actions serve as a unified action space that carries through from pre-training to robot execution. Our recipe is called "EgoScale": - Pre-train GR00T N1.5 on 20K hours of human video, mid-train with only 4 hours (!) of robot play data with Sharpa hands. 54% gains over training from scratch across 5 highly dexterous tasks. - Most surprising result: a *single* teleop demo is sufficient to learn a never-before-seen task. Our recipe enables extreme data efficiency. - Although we pre-train in 22-DoF hand joint space, the policy transfers to a Unitree G1 with 7-DoF tri-finger hands. 30%+ gains over training on G1 data alone. The scalable path to robot dexterity was never more robots. It was always us. Deep dives in thread:

We trained a humanoid with 22-DoF dexterous hands to assemble model cars, operate syringes, sort poker cards, fold/roll shirts, all learned primarily from 20,000+ hours of egocentric human video with no robot in the loop. Humans are the most scalable embodiment on the planet. We discovered a near-perfect log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and this loss directly predicts real-robot success rate. Humanoid robots will be the end game, because they are the practical form factor with minimal embodiment gap from humans. Call it the Bitter Lesson of robot hardware: the kinematic similarity lets us simply retarget human finger motion onto dexterous robot hand joints. No learned embeddings, no fancy transfer algorithms needed. Relative wrist motion + retargeted 22-DoF finger actions serve as a unified action space that carries through from pre-training to robot execution. Our recipe is called "EgoScale": - Pre-train GR00T N1.5 on 20K hours of human video, mid-train with only 4 hours (!) of robot play data with Sharpa hands. 54% gains over training from scratch across 5 highly dexterous tasks. - Most surprising result: a single teleop demo is sufficient to learn a never-before-seen task. Our recipe enables extreme data efficiency. - Although we pre-train in 22-DoF hand joint space, the policy transfers to a Unitree G1 with 7-DoF tri-finger hands. 30%+ gains over training on G1 data alone. The scalable path to robot dexterity was never more robots. It was always us. Deep dives in thread:

Jim Fan

292,967 görüntüleme • 4 ay önce

Say hello to Bear 2!🎉 Packed with over 20 new features and a sparkling new design, we are excited to bring you the Bear-iest version of Bear yet! #Bear2

Say hello to Bear 2!🎉 Packed with over 20 new features and a sparkling new design, we are excited to bring you the Bear-iest version of Bear yet! #Bear2

Bear - Markdown Notes

95,444 görüntüleme • 3 yıl önce

New Episode: Hao Cheng is Founder and CEO of Booster Robotics, a Beijing-based startup focused on affordable humanoid robots. Hao believes, like the personal computer, the availability of affordable and developer-friendly humanoid robots will drive innovation. We sit down at UFB’s San Francisco office to chat about Hao’s story, vision for humanoid robotics, developer ecosystem, geopolitical concerns, and more. Chaoyi Li, Booster Robotics's head of globalization, also joined the conversation. 0:27 Hao's journey 3:31 Affordable hardware is the key 5:12 Discoveries from soccer and fighting bots 6:18 Building developer ecosystem 7:26 Software platform and tools 12:07 Philosophy on robot hands and grippers 15:06 ChatGPT moment for humanoids 23:20 China's rapid advancements in humanoids 24:41 Geopolitical concerns 27:01 Long-term vision for robots 31:26 shout-out to The Humanoid Hub

New Episode: Hao Cheng is Founder and CEO of Booster Robotics, a Beijing-based startup focused on affordable humanoid robots. Hao believes, like the personal computer, the availability of affordable and developer-friendly humanoid robots will drive innovation. We sit down at UFB’s San Francisco office to chat about Hao’s story, vision for humanoid robotics, developer ecosystem, geopolitical concerns, and more. Chaoyi Li, Booster Robotics's head of globalization, also joined the conversation. 0:27 Hao's journey 3:31 Affordable hardware is the key 5:12 Discoveries from soccer and fighting bots 6:18 Building developer ecosystem 7:26 Software platform and tools 12:07 Philosophy on robot hands and grippers 15:06 ChatGPT moment for humanoids 23:20 China's rapid advancements in humanoids 24:41 Geopolitical concerns 27:01 Long-term vision for robots 31:26 shout-out to The Humanoid Hub

The Humanoid Hub

37,219 görüntüleme • 9 ay önce

This perspective will be more intuitive. Fourier is building a data acquisition and training platform that integrates non-invasive brain-computer interfaces and humanoid robots. This wealth of data will enhance the intelligence level of GR-3. The goal is for GR-3 to accurately identify the brain intention signals of stroke patients during future rehabilitation training and respond in real time to guide patients in performing rehabilitation movements. For example, lifting the left hand, picking up a block from the table, etc. Of course, GR-3 can also become a life assistant controlled by a human BCI. Imagine that people with mobility impairments could also issue commands to GR-3 via BCI to open the refrigerator and get a drink.

This perspective will be more intuitive. Fourier is building a data acquisition and training platform that integrates non-invasive brain-computer interfaces and humanoid robots. This wealth of data will enhance the intelligence level of GR-3. The goal is for GR-3 to accurately identify the brain intention signals of stroke patients during future rehabilitation training and respond in real time to guide patients in performing rehabilitation movements. For example, lifting the left hand, picking up a block from the table, etc. Of course, GR-3 can also become a life assistant controlled by a human BCI. Imagine that people with mobility impairments could also issue commands to GR-3 via BCI to open the refrigerator and get a drink.

CyberRobo

18,624 görüntüleme • 5 ay önce

Shanghai MATRIX ROBOTICS has released a video of its new generation general-purpose humanoid robot: MATRIX-3. Much more compact than the first generation, without a protruding "rear end," it features an impressive futuristic design, 27-DOF dexterous hand with tendon-driven joints, 3D soft fabric bionic skin (claimed to have tactile sensing), and incorporates a new neural network that allows for zero-shot learning, enabling it to perform tasks in complex environments. It is planned for use in general scenarios such as manufacturing plants, logistics warehouses, and retail supermarkets. However, this is currently just a video, and its actual performance remains to be seen, especially the rapid, sensitive, and free movements of the hands as shown in the video: this would truly be a huge breakthrough.

Shanghai MATRIX ROBOTICS has released a video of its new generation general-purpose humanoid robot: MATRIX-3. Much more compact than the first generation, without a protruding "rear end," it features an impressive futuristic design, 27-DOF dexterous hand with tendon-driven joints, 3D soft fabric bionic skin (claimed to have tactile sensing), and incorporates a new neural network that allows for zero-shot learning, enabling it to perform tasks in complex environments. It is planned for use in general scenarios such as manufacturing plants, logistics warehouses, and retail supermarkets. However, this is currently just a video, and its actual performance remains to be seen, especially the rapid, sensitive, and free movements of the hands as shown in the video: this would truly be a huge breakthrough.

CyberRobo

192,751 görüntüleme • 6 ay önce

This is just crazy! Clone just introduced the Torso 2, a groundbreaking android that sets a new standard for robotics. This advanced prototype features 910 artificial muscle fibers, 164 degrees of freedom, and 182 sensors for precise feedback control, enabling fluid, human-like movement. With an actuated lumbar spine and a full set of abdominal muscles, Torso 2’s design mimics human anatomy for unprecedented natural motion. Encased in a sleek, white transparent skin, the Torso 2 utilizes pneumatic actuation to animate its muscles, though current off-the-shelf valves create some noise due to air exhaust. Clone plans to return to a quieter hydraulic design with custom liquid valves for future bipedal robots. The current temporary opaque visor will also be replaced with a one-way mirror for a more polished look. The Torso 2 demonstrates Clone’s hardware potential, running hand-coded sequences to control each muscle. With the promise of legs arriving soon, Clone Robotics is inching closer to creating silent, fully humanoid androids—marking a major leap toward lifelike robotic functionality.

This is just crazy! Clone just introduced the Torso 2, a groundbreaking android that sets a new standard for robotics. This advanced prototype features 910 artificial muscle fibers, 164 degrees of freedom, and 182 sensors for precise feedback control, enabling fluid, human-like movement. With an actuated lumbar spine and a full set of abdominal muscles, Torso 2’s design mimics human anatomy for unprecedented natural motion. Encased in a sleek, white transparent skin, the Torso 2 utilizes pneumatic actuation to animate its muscles, though current off-the-shelf valves create some noise due to air exhaust. Clone plans to return to a quieter hydraulic design with custom liquid valves for future bipedal robots. The current temporary opaque visor will also be replaced with a one-way mirror for a more polished look. The Torso 2 demonstrates Clone’s hardware potential, running hand-coded sequences to control each muscle. With the promise of legs arriving soon, Clone Robotics is inching closer to creating silent, fully humanoid androids—marking a major leap toward lifelike robotic functionality.

Ed Krassenstein

29,566 görüntüleme • 1 yıl önce

🚨 Amazon has acquired Fauna Robotics, marking its second robotics acquisition in under a month. The move extends Amazon’s robotics strategy beyond fulfillment and further into the home, where safety, adaptability, and human interaction are central. Fauna’s soft-bodied humanoids are built for shared environments, a clear contrast to industrial systems and a better fit for consumer use cases. Taken together, these moves point to a more coordinated strategy across the humanoid stack, from hardware to deployment. The pace of consolidation is increasing, with strategic buyers moving earlier into the market.

🚨 Amazon has acquired Fauna Robotics, marking its second robotics acquisition in under a month. The move extends Amazon’s robotics strategy beyond fulfillment and further into the home, where safety, adaptability, and human interaction are central. Fauna’s soft-bodied humanoids are built for shared environments, a clear contrast to industrial systems and a better fit for consumer use cases. Taken together, these moves point to a more coordinated strategy across the humanoid stack, from hardware to deployment. The pace of consolidation is increasing, with strategic buyers moving earlier into the market.

XMAQUINA

22,408 görüntüleme • 3 ay önce

🤖 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:

🤖 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

95,196 görüntüleme • 1 yıl önce