Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

AgiBot has formally unveiled its G2 humanoid robot, a system designed to transition into various industries and liberate humans from repetitive labor. G2 features high-performance joints, precision torque sensors, and an advanced spatial perception system, supporting quick deployment and multi-modal voice interaction. ► Factory Floor Performance: The G2 is...

XRoboHub's profile picture

RoboHub🤖

10,996 subscribers

46,733 görüntüleme • 10 ay önce •via X (Twitter)

Bilim & TeknolojiEğitimSanat
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

AgiBot’s new generation of industrial-grade interactive embodied robot, AgiBot G2, has officially launched! The G2 has already secured orders worth hundreds of millions of RMB, including two separate contracts each exceeding 100 million RMB, and has begun its first commercial deliveries. The AgiBot G2 is built to industrial standards, featuring high-performance joints, precision torque sensors, and an advanced spatial perception system. It supports rapid learning and deployment, offers strong multimodal voice interaction, and is designed for general use in industrial, logistics, and guidance scenarios. Inheriting the successful "Collect-Train-Deploy" model of its predecessor, the G1, the G2 brings significant upgrades, including a high-performance AI computing platform and actuators that enable omnidirectional obstacle avoidance and high-precision force-control tasks. Its 3-DOF waist allows for human-like bending and lateral body movement. A key feature is the G2's globally first-of-its-kind cross-shaped wrist force-control arm, which uses precision joint torque sensors and joint impedance control to delicately perceive external forces and respond smoothly. For continuous operation, the G2 supports autonomous charging and features a dual-battery hot-swapping system, meeting the 24-hour cycle demands of factory production lines. During the launch event, AgiBot demonstrated the G2’s ultra-low latency remote operation (teleoperation) capabilities. Operators successfully demonstrated precision shots (like hitting a floating balloon in Shanghai while operating from Beijing), showcasing the robot's high accuracy and low latency in both line-of-sight and beyond-line-of-sight scenarios. The G2 is already being deployed across four key real-world scenarios: In automotive parts production, it assists humans with tasks like safety belt lock core pressing and material handling. In precision operations, it used reinforcement learning to master delicate tasks like inserting memory sticks in just one hour. In logistics, the G2, enhanced by AgiBot's OmniHand dexterous hand, efficiently handles various package types for sorting and loading. Its strong mobility allows it to adapt to over 95% of factory floors. AgiBot is also commencing the first batch of commercial deliveries under an over 100 million RMB procurement contract with Joyson Electronic, formally landing the G2 in the automotive parts manufacturing sector.
2:28

AgiBot’s new generation of industrial-grade interactive embodied robot, AgiBot G2, has officially launched! The G2 has already secured orders worth hundreds of millions of RMB, including two separate contracts each exceeding 100 million RMB, and has begun its first commercial deliveries. The AgiBot G2 is built to industrial standards, featuring high-performance joints, precision torque sensors, and an advanced spatial perception system. It supports rapid learning and deployment, offers strong multimodal voice interaction, and is designed for general use in industrial, logistics, and guidance scenarios. Inheriting the successful "Collect-Train-Deploy" model of its predecessor, the G1, the G2 brings significant upgrades, including a high-performance AI computing platform and actuators that enable omnidirectional obstacle avoidance and high-precision force-control tasks. Its 3-DOF waist allows for human-like bending and lateral body movement. A key feature is the G2's globally first-of-its-kind cross-shaped wrist force-control arm, which uses precision joint torque sensors and joint impedance control to delicately perceive external forces and respond smoothly. For continuous operation, the G2 supports autonomous charging and features a dual-battery hot-swapping system, meeting the 24-hour cycle demands of factory production lines. During the launch event, AgiBot demonstrated the G2’s ultra-low latency remote operation (teleoperation) capabilities. Operators successfully demonstrated precision shots (like hitting a floating balloon in Shanghai while operating from Beijing), showcasing the robot's high accuracy and low latency in both line-of-sight and beyond-line-of-sight scenarios. The G2 is already being deployed across four key real-world scenarios: In automotive parts production, it assists humans with tasks like safety belt lock core pressing and material handling. In precision operations, it used reinforcement learning to master delicate tasks like inserting memory sticks in just one hour. In logistics, the G2, enhanced by AgiBot's OmniHand dexterous hand, efficiently handles various package types for sorting and loading. Its strong mobility allows it to adapt to over 95% of factory floors. AgiBot is also commencing the first batch of commercial deliveries under an over 100 million RMB procurement contract with Joyson Electronic, formally landing the G2 in the automotive parts manufacturing sector.

RoboHub🤖

33,831 görüntüleme • 10 ay önce

🔥 JUST IN: Open-source robotics dataset from 100% real-world scenarios! 🤯 Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳 Learn more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →
0:26

🔥 JUST IN: Open-source robotics dataset from 100% real-world scenarios! 🤯 Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. 🇨🇳 Learn more here: ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

40,583 görüntüleme • 4 ay önce

Holy…S😳 Xiaomi's New CyberOne is so human-like Although this update features a bionic hand, I was immediately drawn to it. Let's look at the changes in the hand： It can handle industrial precision tasks like turning screws, plus delicate operations such as pinching feathers and throwing balloons. Behind the performance: >Volume cut by 60%:now almost identical in size/shape to a real human hand >Big leap in degrees of freedom (+50% total, +83% active:22-27DOF) >Full-palm tactile sensors over 8200 mm² for precise grip even without vision >150,000+ grip cycles durability (61-hour test) And a major innovation:Smart bionic sweat gland cooling: evaporates water for ~10W active heat dissipation Using tactile gloves to capture real human data, they’re training smoother, human-like grasps with imitation and reinforcement learning. Elon has said that humanoid hands and true AI are the most difficult aspects of building humanoid robots. It seems that Xiaomi is also getting close.
0:41

Holy…S😳 Xiaomi's New CyberOne is so human-like Although this update features a bionic hand, I was immediately drawn to it. Let's look at the changes in the hand： It can handle industrial precision tasks like turning screws, plus delicate operations such as pinching feathers and throwing balloons. Behind the performance: >Volume cut by 60%:now almost identical in size/shape to a real human hand >Big leap in degrees of freedom (+50% total, +83% active:22-27DOF) >Full-palm tactile sensors over 8200 mm² for precise grip even without vision >150,000+ grip cycles durability (61-hour test) And a major innovation:Smart bionic sweat gland cooling: evaporates water for ~10W active heat dissipation Using tactile gloves to capture real human data, they’re training smoother, human-like grasps with imitation and reinforcement learning. Elon has said that humanoid hands and true AI are the most difficult aspects of building humanoid robots. It seems that Xiaomi is also getting close.

CyberRobo

111,430 görüntüleme • 5 ay önce

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. “We believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,” said the company in a statement. Reports revealed that to avoid the “uncanny valley” effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their users’ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims it’s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. It’s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robots’ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.
1:06

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. “We believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,” said the company in a statement. Reports revealed that to avoid the “uncanny valley” effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their users’ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims it’s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. It’s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robots’ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.

Owen Gregorian

179,005 görüntüleme • 10 ay önce

Humanoid Marathon Champion "TienKung" Enters the Factory At IROS 2025, the Beijing Humanoid Robot Innovation Center (BHRIC) and UBTECH officially launched the Software Development Kit (SDK) for their general-purpose embodied intelligence platform, "HuiSiKaiWu." This move signals a significant step towards an open-source embodied AI ecosystem. The HuiSiKaiWu platform is designed for ease of use and low-threshold deployment, enabling multi-agent collaboration (one brain, multiple functions/robots). The core "brain" uses a dual-model architecture: the Pelican VLM and the WoW World Model, driving autonomous learning and decision-making. The "cerebellum" includes the cross-body XR-1 VLA Model, which has shown strong performance in rapid, few-shot skill transfer across tasks. BHRIC simultaneously announced its first industrial application: since September 2025, the "TienKung 2.0" and "Tianyi 2.0" humanoids have been deployed at the Foton Cummins engine factory. They autonomously handle material bin fetching and transportation on the "unmanned production line," adapting to various goods and shelf heights. Foton Cummins highlighted the robots' high stability and generalization potential in complex industrial processes. Beyond industrial work, BHRIC showcased other applications: the high-performance "TienKung Ultra" is being used at the Li-Ning Sports Science Lab for running shoe tests, precisely simulating human gaits. The platform is expanding applications across manufacturing, logistics, and sports science. The HuiSiKaiWu SDK is now available for collaborative trials by research institutions and development teams, offering a full toolchain for skill calling and scene deployment. BHRIC plans to gradually open-source its core algorithms, including VLM and VLA models, and hosted the "X-Humanoid Young Talent Meetup" and the "2026 Re-Action Humanoid Robot Challenge" to build a comprehensive developer ecosystem.
3:22

Humanoid Marathon Champion "TienKung" Enters the Factory At IROS 2025, the Beijing Humanoid Robot Innovation Center (BHRIC) and UBTECH officially launched the Software Development Kit (SDK) for their general-purpose embodied intelligence platform, "HuiSiKaiWu." This move signals a significant step towards an open-source embodied AI ecosystem. The HuiSiKaiWu platform is designed for ease of use and low-threshold deployment, enabling multi-agent collaboration (one brain, multiple functions/robots). The core "brain" uses a dual-model architecture: the Pelican VLM and the WoW World Model, driving autonomous learning and decision-making. The "cerebellum" includes the cross-body XR-1 VLA Model, which has shown strong performance in rapid, few-shot skill transfer across tasks. BHRIC simultaneously announced its first industrial application: since September 2025, the "TienKung 2.0" and "Tianyi 2.0" humanoids have been deployed at the Foton Cummins engine factory. They autonomously handle material bin fetching and transportation on the "unmanned production line," adapting to various goods and shelf heights. Foton Cummins highlighted the robots' high stability and generalization potential in complex industrial processes. Beyond industrial work, BHRIC showcased other applications: the high-performance "TienKung Ultra" is being used at the Li-Ning Sports Science Lab for running shoe tests, precisely simulating human gaits. The platform is expanding applications across manufacturing, logistics, and sports science. The HuiSiKaiWu SDK is now available for collaborative trials by research institutions and development teams, offering a full toolchain for skill calling and scene deployment. BHRIC plans to gradually open-source its core algorithms, including VLM and VLA models, and hosted the "X-Humanoid Young Talent Meetup" and the "2026 Re-Action Humanoid Robot Challenge" to build a comprehensive developer ecosystem.

RoboHub🤖

39,337 görüntüleme • 10 ay önce

Leju Robotics has launched the upgraded KUAVO 5/5-W humanoid and wheeled robots, designed to meet the rigorous demands of industrial automation. The robots feature a modular design that is key to flexibility: the legs are quickly replaceable with bipedal configurations (for complex terrain) or wheeled setups (for long-distance stability). The hands are also modular, supporting dexterous hands, grippers, or claws. This adaptability, combined with a rotatable and height-adjustable body, allows the robot to handle a vast range of factory tasks. Built for industrial stamina, the KUAVO series supports a 20kg maximum payload and an upper-body dual-arm payload of 10kg. It is engineered for continuous operation, boasting a battery life of over 8 hours. The control system achieves "silky-smooth" precision via doubled joint communication frequency. To drive high generalizability, Leju relies on a data-driven model. It established China's largest data acquisition center in Beijing (referred to as the "largest humanoid robot skill school") to collect over 6 million data points annually from 1:1 replications of real industrial scenes. This data feeds a universal multi-modal dataset, enabling the robot's "intelligent brain" to continuously learn complex tasks through closed-loop feedback in client factory environments.
3:24

Leju Robotics has launched the upgraded KUAVO 5/5-W humanoid and wheeled robots, designed to meet the rigorous demands of industrial automation. The robots feature a modular design that is key to flexibility: the legs are quickly replaceable with bipedal configurations (for complex terrain) or wheeled setups (for long-distance stability). The hands are also modular, supporting dexterous hands, grippers, or claws. This adaptability, combined with a rotatable and height-adjustable body, allows the robot to handle a vast range of factory tasks. Built for industrial stamina, the KUAVO series supports a 20kg maximum payload and an upper-body dual-arm payload of 10kg. It is engineered for continuous operation, boasting a battery life of over 8 hours. The control system achieves "silky-smooth" precision via doubled joint communication frequency. To drive high generalizability, Leju relies on a data-driven model. It established China's largest data acquisition center in Beijing (referred to as the "largest humanoid robot skill school") to collect over 6 million data points annually from 1:1 replications of real industrial scenes. This data feeds a universal multi-modal dataset, enabling the robot's "intelligent brain" to continuously learn complex tasks through closed-loop feedback in client factory environments.

RoboHub🤖

34,676 görüntüleme • 10 ay önce

A Breakthrough in Robotics: Spherical Gears Enter Mass Production Spherical gears, the kind of joint that would allow a robot to move like a human shoulder, have been notoriously difficult to manufacture with high precision. That's changing, thanks to a new design and a path to mass production that could have a huge impact on robotics. The breakthrough comes from a new design called the ABENICS spherical gear, developed by researchers at Yamagata University. This innovative mechanism enables a joint to move in three degrees of freedom without the slippage issues of earlier designs. It achieves this by using a "cross-spherical gear" that meshes with one or more "monopole gears." Mass production is now on the horizon. Although the initial manufacturing of the gears was inefficient, Nissei Corporation improved the process and established the necessary technology. The companies Kanematsu and Nissei have now entered the marketing phase, with production expected to begin in 2027. The impact of this technology is significant. Mass-produced spherical gears are expected to enable highly versatile and efficient robotic limbs. ► Humanoid and Mobile Robots: The design allows for compact, high-torque ball joints ideal for creating versatile and efficient robotic limbs. ► Aerospace: Potential applications include deployment mechanisms for satellite solar panels. ► Other Industries: The technology is also being explored for its potential to enhance productivity in healthcare, nursing care, and restaurants.
2:01

A Breakthrough in Robotics: Spherical Gears Enter Mass Production Spherical gears, the kind of joint that would allow a robot to move like a human shoulder, have been notoriously difficult to manufacture with high precision. That's changing, thanks to a new design and a path to mass production that could have a huge impact on robotics. The breakthrough comes from a new design called the ABENICS spherical gear, developed by researchers at Yamagata University. This innovative mechanism enables a joint to move in three degrees of freedom without the slippage issues of earlier designs. It achieves this by using a "cross-spherical gear" that meshes with one or more "monopole gears." Mass production is now on the horizon. Although the initial manufacturing of the gears was inefficient, Nissei Corporation improved the process and established the necessary technology. The companies Kanematsu and Nissei have now entered the marketing phase, with production expected to begin in 2027. The impact of this technology is significant. Mass-produced spherical gears are expected to enable highly versatile and efficient robotic limbs. ► Humanoid and Mobile Robots: The design allows for compact, high-torque ball joints ideal for creating versatile and efficient robotic limbs. ► Aerospace: Potential applications include deployment mechanisms for satellite solar panels. ► Other Industries: The technology is also being explored for its potential to enhance productivity in healthcare, nursing care, and restaurants.

RoboHub🤖

384,888 görüntüleme • 11 ay önce

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

466,610 görüntüleme • 1 yıl önce

Xpeng unveiled its next-generation IRON humanoid robot at the 2025 Xpeng Tech Day. This version emphasizes a "born from within" bionic design philosophy, featuring a human-like spine structure, full flexible skin, and customizable physique, including the option for male and female forms. CEO He Xiaopeng confirmed this is the final pre-research version, with the mass-production model standing no taller than 170cm. IRON’s technical specs are aggressive: 🦾 Hardware: 82 total Degrees of Freedom (DoF), far above the average. Its hand boasts 22 DoF with industry-smallest harmonic joints for 1:1 human hand scale, enabling delicate tasks (grabbing eggs, unscrewing caps). 🧠 Intelligence: Runs on three Turing AI chips with 2,250 TOPS of effective computing power, currently the highest in humanoids. It debuts Xpeng's first-gen Physical World Large Model (VLT + VLA + VLM) for high-level dialogue and control. 🔋 Solid-State Power: IRON is the first to use full solid-state batteries, boosting power by 30% and reducing weight by 30%. Xpeng aims for this safety-critical sector to drive SS battery mass production. 🚀 Commercialization Plan: Xpeng will prioritize commercial scenarios like guidance, sales assistance, and inspection (jointly developing complex applications with partners like Baosteel Group). CEO He Xiaopeng plans aggressive scaled mass production of advanced humanoids by the end of 2026. The robot team is over 1,000 people.
3:46

Xpeng unveiled its next-generation IRON humanoid robot at the 2025 Xpeng Tech Day. This version emphasizes a "born from within" bionic design philosophy, featuring a human-like spine structure, full flexible skin, and customizable physique, including the option for male and female forms. CEO He Xiaopeng confirmed this is the final pre-research version, with the mass-production model standing no taller than 170cm. IRON’s technical specs are aggressive: 🦾 Hardware: 82 total Degrees of Freedom (DoF), far above the average. Its hand boasts 22 DoF with industry-smallest harmonic joints for 1:1 human hand scale, enabling delicate tasks (grabbing eggs, unscrewing caps). 🧠 Intelligence: Runs on three Turing AI chips with 2,250 TOPS of effective computing power, currently the highest in humanoids. It debuts Xpeng's first-gen Physical World Large Model (VLT + VLA + VLM) for high-level dialogue and control. 🔋 Solid-State Power: IRON is the first to use full solid-state batteries, boosting power by 30% and reducing weight by 30%. Xpeng aims for this safety-critical sector to drive SS battery mass production. 🚀 Commercialization Plan: Xpeng will prioritize commercial scenarios like guidance, sales assistance, and inspection (jointly developing complex applications with partners like Baosteel Group). CEO He Xiaopeng plans aggressive scaled mass production of advanced humanoids by the end of 2026. The robot team is over 1,000 people.

RoboHub🤖

23,275 görüntüleme • 9 ay önce

We believe we’re the first robotics company to demonstrate a robot peeling an apple with dual dexterous human-like hands. This breakthrough closes a key gap in robotics, achieving bimanual, contact-rich manipulation and moving far beyond the limits of simple grippers. 🧵↓ Today’s AI models (VLMs) are excellent at perception but struggle with action. Controlling high-degree-of-freedom hands for tasks like this is incredibly complex, and precise finger-level teleoperation is nearly impossible for humans. Our first step was a shared-autonomy system: rather than controlling every finger, the operator triggers pre-learned skills like a “rotate apple or tennis ball” primitive via a keyboard press or pedal. This makes scalable data collection and RL training possible. How does the AI manage this? We created "MoDE-VLA" (Mixture of Dexterous Experts). It fuses vision, language, force, and touch data by using a team of specialist "experts," making control in high-dimensional spaces stable and effective. The combination of these two innovations allows for seamless, contact-rich manipulation. The human provides high-level guidance, and the robot executes the complex in-hand coordination required. This work paves the way for robots that can safely handle delicate tasks in human environments. Want the full technical details? 📄 Read the full research paper: Visit us at NVIDIA GTC Booth #1838, Hall 3 to learn more! #Robotics #AI #DexterousManipulation #VLA #NVIDIAGTC Nancy Villicaña NVIDIA GTC
2:51

We believe we’re the first robotics company to demonstrate a robot peeling an apple with dual dexterous human-like hands. This breakthrough closes a key gap in robotics, achieving bimanual, contact-rich manipulation and moving far beyond the limits of simple grippers. 🧵↓ Today’s AI models (VLMs) are excellent at perception but struggle with action. Controlling high-degree-of-freedom hands for tasks like this is incredibly complex, and precise finger-level teleoperation is nearly impossible for humans. Our first step was a shared-autonomy system: rather than controlling every finger, the operator triggers pre-learned skills like a “rotate apple or tennis ball” primitive via a keyboard press or pedal. This makes scalable data collection and RL training possible. How does the AI manage this? We created "MoDE-VLA" (Mixture of Dexterous Experts). It fuses vision, language, force, and touch data by using a team of specialist "experts," making control in high-dimensional spaces stable and effective. The combination of these two innovations allows for seamless, contact-rich manipulation. The human provides high-level guidance, and the robot executes the complex in-hand coordination required. This work paves the way for robots that can safely handle delicate tasks in human environments. Want the full technical details? 📄 Read the full research paper: Visit us at NVIDIA GTC Booth #1838, Hall 3 to learn more! #Robotics #AI #DexterousManipulation #VLA #NVIDIAGTC Nancy Villicaña NVIDIA GTC

Sharpa

20,429 görüntüleme • 5 ay önce

Boston Dynamics just dropped the production-ready Atlas at CES 2026, and the specs are next-level. This isn't just a prototype; it's a rugged, enterprise-grade worker built for the grind of real-world factories.🤖🦾 With 56 degrees of freedom and fully rotational joints, Atlas moves with "superhuman" flexibility. It features human-scale hands with tactile sensing in every finger and palm, allowing for high-precision manipulation. Plus, its 360-degree vision system ensures it always knows who's approaching, keeping human-robot collaboration safe. ➤ Rugged Performance: Lifts up to 110 lbs (approx. 50kg) and operates in extreme temps from -4°F to 104°F (-20°C to 40°C). It’s even water-resistant for industrial wash-downs. ➤ Smart Endurance: Runs for 4 hours on dual swappable batteries. When power gets low, it autonomously heads back to the station to swap its own batteries and get right back to work. ➤ Cloud Intelligence: New tasks can be trained in less than a day. Thanks to the Orbit platform, once one Atlas learns a skill, it’s instantly shared across the entire fleet. The scale is massive: the entire 2026 supply is already spoken for by Hyundai and a new AI partner. Hyundai is also building a specialized "Robotics Metal Plant" and a new factory capable of churning out 30,000 Atlas units annually. We’re officially watching the birth of a humanoid workforce at scale. Source: Boston Dynamics & Hyundai Group
3:47

Boston Dynamics just dropped the production-ready Atlas at CES 2026, and the specs are next-level. This isn't just a prototype; it's a rugged, enterprise-grade worker built for the grind of real-world factories.🤖🦾 With 56 degrees of freedom and fully rotational joints, Atlas moves with "superhuman" flexibility. It features human-scale hands with tactile sensing in every finger and palm, allowing for high-precision manipulation. Plus, its 360-degree vision system ensures it always knows who's approaching, keeping human-robot collaboration safe. ➤ Rugged Performance: Lifts up to 110 lbs (approx. 50kg) and operates in extreme temps from -4°F to 104°F (-20°C to 40°C). It’s even water-resistant for industrial wash-downs. ➤ Smart Endurance: Runs for 4 hours on dual swappable batteries. When power gets low, it autonomously heads back to the station to swap its own batteries and get right back to work. ➤ Cloud Intelligence: New tasks can be trained in less than a day. Thanks to the Orbit platform, once one Atlas learns a skill, it’s instantly shared across the entire fleet. The scale is massive: the entire 2026 supply is already spoken for by Hyundai and a new AI partner. Hyundai is also building a specialized "Robotics Metal Plant" and a new factory capable of churning out 30,000 Atlas units annually. We’re officially watching the birth of a humanoid workforce at scale. Source: Boston Dynamics & Hyundai Group

RoboHub🤖

28,554 görüntüleme • 7 ay önce

NEWS: Figure has unveiling its 3rd generation humanoid robot. • Features a completely redesigned sensory suite and hand system. Wireless charging in feet. • Next-generation vision system engineered for high-frequency visuomotor control. Its new camera architecture delivers twice the frame rate, one-quarter the latency, and a 60% wider field of view per camera within a more compact form factor • Soft goods, wireless charging, improved audio system for voice reasoning, and battery safety advancements • "Engineered from the ground-up for high-volume manufacturing. In order to scale, we established a new supply chain and entirely new process for manufacturing humanoid robots at BotQ." • Lower manufacturing cost • Softer, more adaptive fingertips increase surface contact area, enabling more stable grasps across objects of varied shapes and sizes. Each fingertip sensor can detect forces as small as three grams of pressure - sensitive enough to register the weight of a paperclip resting on your finger. • Multi-density foam to protect against pinch points, and is covered in soft textiles rather than hard machined parts. 9% less mass and less volume than Figure 02 • 10 Gbps mmWave data offload capability, allowing the entire fleet to upload terabytes of data • Upgraded audio hardware system for better real time speech-to-speech. Its speaker is twice the size and nearly four times more powerful, while the microphone has been repositioned for improved performance and clarity. • Charging coils in the robot’s feet allow it to simply step onto a wireless stand and charge at 2 kW Figure: "BotQ is Figure’s dedicated manufacturing facility designed to scale robot production. BotQ’s first-generation manufacturing line will initially be capable of producing up to 12,000 humanoid robots per year, with the goal of producing a total of 100,000 robots over the next four years. Instead of relying on contract manufacturers, Figure brought production of its most critical systems in-house to maintain tight control over quality, iteration, and speed."
6:00

NEWS: Figure has unveiling its 3rd generation humanoid robot. • Features a completely redesigned sensory suite and hand system. Wireless charging in feet. • Next-generation vision system engineered for high-frequency visuomotor control. Its new camera architecture delivers twice the frame rate, one-quarter the latency, and a 60% wider field of view per camera within a more compact form factor • Soft goods, wireless charging, improved audio system for voice reasoning, and battery safety advancements • "Engineered from the ground-up for high-volume manufacturing. In order to scale, we established a new supply chain and entirely new process for manufacturing humanoid robots at BotQ." • Lower manufacturing cost • Softer, more adaptive fingertips increase surface contact area, enabling more stable grasps across objects of varied shapes and sizes. Each fingertip sensor can detect forces as small as three grams of pressure - sensitive enough to register the weight of a paperclip resting on your finger. • Multi-density foam to protect against pinch points, and is covered in soft textiles rather than hard machined parts. 9% less mass and less volume than Figure 02 • 10 Gbps mmWave data offload capability, allowing the entire fleet to upload terabytes of data • Upgraded audio hardware system for better real time speech-to-speech. Its speaker is twice the size and nearly four times more powerful, while the microphone has been repositioned for improved performance and clarity. • Charging coils in the robot’s feet allow it to simply step onto a wireless stand and charge at 2 kW Figure: "BotQ is Figure’s dedicated manufacturing facility designed to scale robot production. BotQ’s first-generation manufacturing line will initially be capable of producing up to 12,000 humanoid robots per year, with the goal of producing a total of 100,000 robots over the next four years. Instead of relying on contract manufacturers, Figure brought production of its most critical systems in-house to maintain tight control over quality, iteration, and speed."

Sawyer Merritt

140,241 görüntüleme • 10 ay önce

Reinforcement Learning from Human Feedback (RLHF) is gaining traction. This field aims to make AI more responsible by including human values and preferences. In this video, Nathan Lambert, a research scientist and RLHF team lead at Hugging Face explores its inner workings, applications and industry impact. RLHF has gained the spotlight in recent years. The growth of language models like Anthropic’s Claude and OpenAI's ChatGPT have increased interest in human-feedback integration. "There are some rumors that Open AI had two teams; one was doing RLHF and the other instruction fine-tuning. And the RLHF team kept getting more and more performance." Understanding RLHF The RLHF process has three main steps: Pre-training: Much like with GPT models, the journey starts with pre-training on a large corpus of data. This can range from text data, web scrapes, to specialized datasets. Reward Modeling: This is the RLHF counterpart of supervised fine-tuning in large language models. This stage involves creating a reward model that resonates with human values and preferences. RL Optimization: This stage parallels reward modeling and reinforcement learning in traditional AI models. The AI system fine-tunes itself based on the reward model, employing reinforcement learning algorithms for that extra layer of optimization. The Data Challenge Data collection and curation in RLHF closely resemble the challenges you'd encounter in large language model training. Datasets from organizations like OpenAI can serve as a useful foundation. However, the need for high-quality, task-specific data cannot be overstated. Implementing RLHF: A Practical Guide If you’re someone who loves getting hands-on with AI libraries like Hugging Face, implementing RLHF is right way to do. It’s essential to understand its limitations. Think about model stability, over-optimization, and exploration strategies, much like you would when prompt engineering. Ongoing Research and Next Steps While he suggests that some basics figured out, there are layers of complexity that still need to be unraveled: 1. New Benchmarks: How do we measure the effectiveness of RLHF? 2. Preference Modeling: How can the model be made to understand human preferences better? 3. Interpreting RLHF: Much like explainability in traditional models, how do we make RLHF more interpretable? 4. System-Wide Evaluation: Going beyond individual performance, how does RLHF affect an entire system? The Transformative Power of RLHF Whether you're an AI developer, a business analyst, or a marketer, RLHF promises to revolutionize your domain. Imagine customer service chatbots that understand human emotions better, or content generators that align more closely with human values. RLHF is an emerging field that focuses on enhancing machine learning models through human feedback. While it tackles important issues like bias and ethics, its broader goal is to improve system performance across various applications. Whether you're deeply invested in the ethics of AI or simply curious about advancements in machine learning, RLHF offers valuable insights. If you're interested in the next wave of AI development, this area is definitely one to watch.
2:00

Reinforcement Learning from Human Feedback (RLHF) is gaining traction. This field aims to make AI more responsible by including human values and preferences. In this video, Nathan Lambert, a research scientist and RLHF team lead at Hugging Face explores its inner workings, applications and industry impact. RLHF has gained the spotlight in recent years. The growth of language models like Anthropic’s Claude and OpenAI's ChatGPT have increased interest in human-feedback integration. "There are some rumors that Open AI had two teams; one was doing RLHF and the other instruction fine-tuning. And the RLHF team kept getting more and more performance." Understanding RLHF The RLHF process has three main steps: Pre-training: Much like with GPT models, the journey starts with pre-training on a large corpus of data. This can range from text data, web scrapes, to specialized datasets. Reward Modeling: This is the RLHF counterpart of supervised fine-tuning in large language models. This stage involves creating a reward model that resonates with human values and preferences. RL Optimization: This stage parallels reward modeling and reinforcement learning in traditional AI models. The AI system fine-tunes itself based on the reward model, employing reinforcement learning algorithms for that extra layer of optimization. The Data Challenge Data collection and curation in RLHF closely resemble the challenges you'd encounter in large language model training. Datasets from organizations like OpenAI can serve as a useful foundation. However, the need for high-quality, task-specific data cannot be overstated. Implementing RLHF: A Practical Guide If you’re someone who loves getting hands-on with AI libraries like Hugging Face, implementing RLHF is right way to do. It’s essential to understand its limitations. Think about model stability, over-optimization, and exploration strategies, much like you would when prompt engineering. Ongoing Research and Next Steps While he suggests that some basics figured out, there are layers of complexity that still need to be unraveled: 1. New Benchmarks: How do we measure the effectiveness of RLHF? 2. Preference Modeling: How can the model be made to understand human preferences better? 3. Interpreting RLHF: Much like explainability in traditional models, how do we make RLHF more interpretable? 4. System-Wide Evaluation: Going beyond individual performance, how does RLHF affect an entire system? The Transformative Power of RLHF Whether you're an AI developer, a business analyst, or a marketer, RLHF promises to revolutionize your domain. Imagine customer service chatbots that understand human emotions better, or content generators that align more closely with human values. RLHF is an emerging field that focuses on enhancing machine learning models through human feedback. While it tackles important issues like bias and ethics, its broader goal is to improve system performance across various applications. Whether you're deeply invested in the ethics of AI or simply curious about advancements in machine learning, RLHF offers valuable insights. If you're interested in the next wave of AI development, this area is definitely one to watch.

Muratcan Koylan

27,168 görüntüleme • 2 yıl önce

🚨 BREAKING: Swiss startup mimic just raised €13.8M to teach robots the one thing they still struggle with human-like dexterity. 🇨🇭 The Zurich-based company is developing physical AI systems that allow robots to learn directly from human demonstrations. Skilled operators wear custom motion-tracking gear on real factory floors, generating data that trains robots to grasp, move, and adapt with human precision. Founded in 2024 as a spin-off from ETH Zurich, mimic pairs AI-driven dexterous robotic hands with standard industrial robot arms, skipping the humanoid form factor in favor of practical, deployable automation. The oversubscribed seed round was led by Elaia with participation from Speedinvest, Founderful, 1st Kind, 10x Founders, 2100 Ventures, and the Sequoia Scout Fund, bringing total funding to over $20M. Their technology is already being piloted with Fortune 500 manufacturers and logistics operators, where robots are learning complex manipulation tasks once reserved for humans. Why it matters: Europe is stepping up in the AI robotics race. By making dexterity scalable, mimic bridges the gap between lab breakthroughs and real factory deployment, where automation still meets its hardest challenges. As CEO Stefan Weirich put it: “We make dexterity deployable at scale, closing the gap between what AI can do in the lab and what factories actually need.” Let's go robotics in Europe! 🔥
0:26

🚨 BREAKING: Swiss startup mimic just raised €13.8M to teach robots the one thing they still struggle with human-like dexterity. 🇨🇭 The Zurich-based company is developing physical AI systems that allow robots to learn directly from human demonstrations. Skilled operators wear custom motion-tracking gear on real factory floors, generating data that trains robots to grasp, move, and adapt with human precision. Founded in 2024 as a spin-off from ETH Zurich, mimic pairs AI-driven dexterous robotic hands with standard industrial robot arms, skipping the humanoid form factor in favor of practical, deployable automation. The oversubscribed seed round was led by Elaia with participation from Speedinvest, Founderful, 1st Kind, 10x Founders, 2100 Ventures, and the Sequoia Scout Fund, bringing total funding to over $20M. Their technology is already being piloted with Fortune 500 manufacturers and logistics operators, where robots are learning complex manipulation tasks once reserved for humans. Why it matters: Europe is stepping up in the AI robotics race. By making dexterity scalable, mimic bridges the gap between lab breakthroughs and real factory deployment, where automation still meets its hardest challenges. As CEO Stefan Weirich put it: “We make dexterity deployable at scale, closing the gap between what AI can do in the lab and what factories actually need.” Let's go robotics in Europe! 🔥

Lukas Ziegler

77,152 görüntüleme • 9 ay önce