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.

🚀Top embodied intelligence competition is back! AGIBOT WORLD CHALLENGE @ ICRA 2026 Reasoning-Action & World Model tracks $530K prize pool Robot finals at ICRA 2026 Win AGIBOT robot purchase vouchers Global teams competing Apply now!

AGIBOT

5,113 subscribers

12,154,864 Aufrufe • vor 5 Monaten •via X (Twitter)

Wissenschaft & Technologie Bildung Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🔥 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 →

🔥 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 Aufrufe • vor 4 Monaten

𝗖𝗵𝗶𝗻𝗮 𝗶𝘀 𝗳𝗶𝗻𝗶𝘀𝗵𝗶𝗻𝗴 𝘁𝗵𝗲 𝗵𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗿𝗼𝗯𝗼𝘁 𝗿𝗮𝗰𝗲 𝗯𝗲𝗳𝗼𝗿𝗲 𝗺𝗼𝘀𝘁 𝗼𝗳 𝘁𝗵𝗲 𝗪𝗲𝘀𝘁 𝗿𝗲𝗮𝗹𝗶𝘇𝗲𝘀 𝗶𝘁 𝗵𝗮𝘀 𝘀𝘁𝗮𝗿𝘁𝗲𝗱. AGIBOT held its Partner Conference in Shanghai last week. The real headline wasn't the new hardware. It was their CTO standing on stage, telling investors that humanoid R&D season is over. 2026, he said, is "Deployment Year One." Not research. Not demos. Deployment into real factories, real warehouses, real stores. The manufacturing ramp is getting faster. 1,000 humanoid robots in the first 2 years. Another 4,000 in the next 12 months. Another 5,000 in just 3 months after that. AGIBOT is now shipping more humanoids per quarter than most US robotics companies have built in their entire existence. Then came the announcements the industry will spend the rest of the year reacting to. AIMA. The first full-stack open architecture for embodied AI. A unified robot operating system called Link-U, three dev platforms for motion, interaction, and task creation, plus an open agent framework. Any developer can build on top of it. This is the Android play for humanoids. GO-2. A vision-language-action foundation model with Action Chain-of-Thought reasoning. Planning and execution collapsed into one model. GE-2. A world model for simulation, strategy testing, and sim-to-real transfer. AGIBOT WORLD 2026. An open-source, production-grade real-world dataset pulled from actual industrial, logistics, hotel, and commercial sites. Seven standardized "productivity packages" covering logistics sorting, retail service, security patrol, commercial cleaning, and more. Plug, deploy, bill. A 5-year, $280 million commitment to seed a global developer and partner ecosystem. Now look at the competition. Boston Dynamics has been building humanoids since 1992. Tesla's Optimus is still climbing its own hype curve. Apptronik and Agility are well-funded but pre-scale on real deployments. AGIBOT has pulled all of this off in three years, with no acquisitions, no legacy platform, and no IPO distractions. While the West is still asking when humanoids will scale, China is already shipping them by the thousand.

𝗖𝗵𝗶𝗻𝗮 𝗶𝘀 𝗳𝗶𝗻𝗶𝘀𝗵𝗶𝗻𝗴 𝘁𝗵𝗲 𝗵𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗿𝗼𝗯𝗼𝘁 𝗿𝗮𝗰𝗲 𝗯𝗲𝗳𝗼𝗿𝗲 𝗺𝗼𝘀𝘁 𝗼𝗳 𝘁𝗵𝗲 𝗪𝗲𝘀𝘁 𝗿𝗲𝗮𝗹𝗶𝘇𝗲𝘀 𝗶𝘁 𝗵𝗮𝘀 𝘀𝘁𝗮𝗿𝘁𝗲𝗱. AGIBOT held its Partner Conference in Shanghai last week. The real headline wasn't the new hardware. It was their CTO standing on stage, telling investors that humanoid R&D season is over. 2026, he said, is "Deployment Year One." Not research. Not demos. Deployment into real factories, real warehouses, real stores. The manufacturing ramp is getting faster. 1,000 humanoid robots in the first 2 years. Another 4,000 in the next 12 months. Another 5,000 in just 3 months after that. AGIBOT is now shipping more humanoids per quarter than most US robotics companies have built in their entire existence. Then came the announcements the industry will spend the rest of the year reacting to. AIMA. The first full-stack open architecture for embodied AI. A unified robot operating system called Link-U, three dev platforms for motion, interaction, and task creation, plus an open agent framework. Any developer can build on top of it. This is the Android play for humanoids. GO-2. A vision-language-action foundation model with Action Chain-of-Thought reasoning. Planning and execution collapsed into one model. GE-2. A world model for simulation, strategy testing, and sim-to-real transfer. AGIBOT WORLD 2026. An open-source, production-grade real-world dataset pulled from actual industrial, logistics, hotel, and commercial sites. Seven standardized "productivity packages" covering logistics sorting, retail service, security patrol, commercial cleaning, and more. Plug, deploy, bill. A 5-year, $280 million commitment to seed a global developer and partner ecosystem. Now look at the competition. Boston Dynamics has been building humanoids since 1992. Tesla's Optimus is still climbing its own hype curve. Apptronik and Agility are well-funded but pre-scale on real deployments. AGIBOT has pulled all of this off in three years, with no acquisitions, no legacy platform, and no IPO distractions. While the West is still asking when humanoids will scale, China is already shipping them by the thousand.

Shruti

214,939 Aufrufe • vor 4 Monaten

At the 2026 World Robot Conference, we saw China's robots in action, from welding cars on factory lines to sorting packages in warehouses, from making coffee to sensing a feather landing on a robotic palm. They're not perfect yet. The real challenge ahead is making these systems reliable, flexible and useful beyond the lab or the show floor. #WRC #robot #dexteroushands #roboticarms

At the 2026 World Robot Conference, we saw China's robots in action, from welding cars on factory lines to sorting packages in warehouses, from making coffee to sensing a feather landing on a robotic palm. They're not perfect yet. The real challenge ahead is making these systems reliable, flexible and useful beyond the lab or the show floor. #WRC #robot #dexteroushands #roboticarms

China Xinhua News

12,009 Aufrufe • vor 2 Tagen

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

I placed 🥈 2nd in the LeHome Challenge (at IEEE ICRA 2026) earlier this month, and before that I was 🥇 1st of 62 teams in the simulation round. Now I am sharing my solution — with a detailed logic walkthrough and open-source code. The task was to teach a cheap two-armed robot to fold different garments in simulation and on a real robot. I trained a VLA policy with an RL loop to make it work. Let's break it down 👇

Ilia

21,948 Aufrufe • vor 1 Monat

This robot knows who won the World Cup! "Xiaozhi, Xiaozhi, who won the 2026 FIFA World Cup?" Alvaro Lago, from Spain, gave this "pop quiz" to a robot at the Embodied AI Robot Experience Center in Changzhou, east China's Jiangsu Province. "The 2026 World Cup Champions are Spain!" the robot blurted out instantly, drawing an enthusiastic thumbs-up from the Spanish native. From understanding football to offering services and interacting with people, what's on display is more than just robots, it's a showcase of China's manufacturing strength. The experience center brings together 36 companies and 104 exhibits, spanning core components, intelligent systems and complete machine integration, offering a full panorama of the embodied intelligence industry chain. The Wujin National Hi-tech Industrial Zone, site of the experience center, is already home to more than 120 robotics companies and is accelerating efforts to build a globally competitive robotics industry hub. As China's robots race toward the future, one thing is clear: when it comes to robotics, Changzhou is a city you don't want to miss.

This robot knows who won the World Cup! "Xiaozhi, Xiaozhi, who won the 2026 FIFA World Cup?" Alvaro Lago, from Spain, gave this "pop quiz" to a robot at the Embodied AI Robot Experience Center in Changzhou, east China's Jiangsu Province. "The 2026 World Cup Champions are Spain!" the robot blurted out instantly, drawing an enthusiastic thumbs-up from the Spanish native. From understanding football to offering services and interacting with people, what's on display is more than just robots, it's a showcase of China's manufacturing strength. The experience center brings together 36 companies and 104 exhibits, spanning core components, intelligent systems and complete machine integration, offering a full panorama of the embodied intelligence industry chain. The Wujin National Hi-tech Industrial Zone, site of the experience center, is already home to more than 120 robotics companies and is accelerating efforts to build a globally competitive robotics industry hub. As China's robots race toward the future, one thing is clear: when it comes to robotics, Changzhou is a city you don't want to miss.

People's Daily, China

28,786 Aufrufe • vor 1 Monat

🏆 Bluwhale Discord World Cup Kicktip Challenge 2026 🏆 Join our official Discord prediction challenge and compete with the community ⚽🌍 🎁 Prize pool worth ~$5,000: • 3x Masternodes • 35x Common Nodes • 13x NFTs • $1,000 in $BLUAI • Top 100 participants receive 1000 XP Participation is FREE. To participate: • Join the Bluwhale Discord: • Reach Discord Level 2 • Complete registration + verification through Discord Good luck to all predictors 🚀

🏆 Bluwhale Discord World Cup Kicktip Challenge 2026 🏆 Join our official Discord prediction challenge and compete with the community ⚽🌍 🎁 Prize pool worth ~$5,000: • 3x Masternodes • 35x Common Nodes • 13x NFTs • $1,000 in $BLUAI • Top 100 participants receive 1000 XP Participation is FREE. To participate: • Join the Bluwhale Discord: • Reach Discord Level 2 • Complete registration + verification through Discord Good luck to all predictors 🚀

Bluwhale

38,480 Aufrufe • vor 3 Monaten

Galbot has unveiled ET1, its first bipedal humanoid, at WRC 2026. The specs are not revealed, but it looks quite similar to Unitree R1. The robot runs Galbot's world-action model, built to drive bipedal, wheeled, and heavy-load robots from a single brain. Founded in 2023 by Peking University professor He Wang, the company is planning a Hong Kong IPO at ~$3-4B.

Galbot has unveiled ET1, its first bipedal humanoid, at WRC 2026. The specs are not revealed, but it looks quite similar to Unitree R1. The robot runs Galbot's world-action model, built to drive bipedal, wheeled, and heavy-load robots from a single brain. Founded in 2023 by Peking University professor He Wang, the company is planning a Hong Kong IPO at ~$3-4B.

The Humanoid Hub

48,816 Aufrufe • vor 3 Tagen

🏯 PCI Grand Finals 🏯 Teams from around the world are gathering in Japan for the PCI Tournament Grand Finals this weekend, following several rounds of fierce competition ⚡ Our Finalists will battle it out on the Global Stage for a piece of the massive ~$65k+ Prize Pool...but only one team will walk away with the title of PARAVOX Champion 🥇 Catch our live broadcasts on Saturday, December 21st, and Sunday, December 22nd — follow our official PARAVOX accounts below now! 👇 A new era of esports is upon us 💥

🏯 PCI Grand Finals 🏯 Teams from around the world are gathering in Japan for the PCI Tournament Grand Finals this weekend, following several rounds of fierce competition ⚡ Our Finalists will battle it out on the Global Stage for a piece of the massive ~$65k+ Prize Pool...but only one team will walk away with the title of PARAVOX Champion 🥇 Catch our live broadcasts on Saturday, December 21st, and Sunday, December 22nd — follow our official PARAVOX accounts below now! 👇 A new era of esports is upon us 💥

PARAVOX

47,383 Aufrufe • vor 1 Jahr

Do you think you could train a robot to fold clothes better than any other robotics team? Now is your chance to prove it...and win actual cash prizes! The 2026 LeHome Challenge is live! Here is the details: Phase 1: Train your best clothes folding policy in simulation with 4 garment types, each presenting unique manipulation challenges. The types of garments include long-sleeved tops, short-sleeved tops, long pants, and shorts. The simulation environment uses Lightwheel's physics accurate deformable assets and built on NVIDIA Omniverse's Isaac Sim/Lab. Submit your code by April 5th for a chance to win up to $2,000 and a SO-101 Arm Kit. Phase 2: The top 8 teams will compete in person at ICRA on June 4th to see who's policy performs best with real clothes. The top place team will take home $20,000! Learn more and sign up for the LeHome Challenge here: Robert Scoble Chris Paxton The Humanoid Hub Harrison Kinsley #Robotics

Do you think you could train a robot to fold clothes better than any other robotics team? Now is your chance to prove it...and win actual cash prizes! The 2026 LeHome Challenge is live! Here is the details: Phase 1: Train your best clothes folding policy in simulation with 4 garment types, each presenting unique manipulation challenges. The types of garments include long-sleeved tops, short-sleeved tops, long pants, and shorts. The simulation environment uses Lightwheel's physics accurate deformable assets and built on NVIDIA Omniverse's Isaac Sim/Lab. Submit your code by April 5th for a chance to win up to $2,000 and a SO-101 Arm Kit. Phase 2: The top 8 teams will compete in person at ICRA on June 4th to see who's policy performs best with real clothes. The top place team will take home $20,000! Learn more and sign up for the LeHome Challenge here: Robert Scoble Chris Paxton The Humanoid Hub Harrison Kinsley #Robotics

Jonathan Stephens

24,003 Aufrufe • vor 6 Monaten

Boston Dynamics just gave its robot dog a brain that reasons about the physical world. Google DeepMind's Gemini Robotics model is now running inside Spot, the four-legged robot already deployed at thousands of facilities worldwide. The upgrade centers on something called embodied reasoning. Basically, instead of following rigid instructions, Spot now interprets what it sees and makes decisions on its own. One standout example: Spot can now look at a pressure gauge, zoom in on the needle, calculate the intervals between tick marks, and deliver an accurate reading. All autonomously. The model also introduces: > Multi-view reasoning, combining feeds from multiple cameras to understand its environment even when objects are blocked from one angle > Built-in success detection, so Spot knows when it's failed and decides whether to retry or move on That last part is a key requirement for true autonomy. Most companies building AI-powered robots are still stuck in the demo phase. Boston Dynamics is one of the few with actual paying customers... which means thousands of Spots collecting real-world data that feeds back into making the AI smarter. That flywheel is hard to compete with.

Boston Dynamics just gave its robot dog a brain that reasons about the physical world. Google DeepMind's Gemini Robotics model is now running inside Spot, the four-legged robot already deployed at thousands of facilities worldwide. The upgrade centers on something called embodied reasoning. Basically, instead of following rigid instructions, Spot now interprets what it sees and makes decisions on its own. One standout example: Spot can now look at a pressure gauge, zoom in on the needle, calculate the intervals between tick marks, and deliver an accurate reading. All autonomously. The model also introduces: > Multi-view reasoning, combining feeds from multiple cameras to understand its environment even when objects are blocked from one angle > Built-in success detection, so Spot knows when it's failed and decides whether to retry or move on That last part is a key requirement for true autonomy. Most companies building AI-powered robots are still stuck in the demo phase. Boston Dynamics is one of the few with actual paying customers... which means thousands of Spots collecting real-world data that feeds back into making the AI smarter. That flywheel is hard to compete with.

Rowan Cheung

54,376 Aufrufe • vor 4 Monaten

NEW: China launches its first humanoid robot soccer league in Beijing. This is way more entertaining than regular soccer. The AI-controlled robots were supplied by Booster Robotics for the tournament and have the skills of 5 to 6 year old children. Robots were seen getting carried off the field on stretchers after falling over. Booster Robotics founder Cheng Hao says the robots' abilities will exponentially increase over time and will eventually challenge adult teams. "We chose the football scenario for robot competition primarily for two reasons: first, to encourage students to apply their algorithmic skills to real-world robotics," Cheng said. "Second, to showcase the robots' ability to walk autonomously and stably, withstand collisions, and demonstrate higher levels of intelligence and safety."

NEW: China launches its first humanoid robot soccer league in Beijing. This is way more entertaining than regular soccer. The AI-controlled robots were supplied by Booster Robotics for the tournament and have the skills of 5 to 6 year old children. Robots were seen getting carried off the field on stretchers after falling over. Booster Robotics founder Cheng Hao says the robots' abilities will exponentially increase over time and will eventually challenge adult teams. "We chose the football scenario for robot competition primarily for two reasons: first, to encourage students to apply their algorithmic skills to real-world robotics," Cheng said. "Second, to showcase the robots' ability to walk autonomously and stably, withstand collisions, and demonstrate higher levels of intelligence and safety."

Collin Rugg

10,121,710 Aufrufe • vor 1 Jahr

X Square Robot just closed its Series C at a valuation above RMB 20 billion, about $2.8 billion 🤖 IDG came into this round. The bigger signal is the cap table. HongShan and Xiaomi were already in across earlier rounds, while Meituan, Alibaba, ByteDance, and Xiaomi have each led rounds at different stages. That puts X Square in a rare position for an embodied AI company: top-tier financial capital on one side, and four of China’s biggest tech platforms on the other. This is not just a money story. Meituan, Alibaba, ByteDance, and Xiaomi bring very different strategic assets: real-world scenarios, cloud infrastructure, consumer traffic, supply chains, and hardware ecosystems. The deployment side is already moving: robot home-cleaning services first, then a “Robots Into Homes” program with the first batch entering real households. The model stack is worth watching too. X Square has open-sourced WALL-OSS-0.5 for robot manipulation and WALL-WM for world modeling. WALL-OSS-0.5 showed strong real-robot performance without post-training, while WALL-WM uses event-level prediction to align language, vision, and action around meaningful physical-world events. They are also building a model-driven data pipeline for large-scale collection, cleaning, annotation, quality control, and augmentation. That matters because home robotics dies in the long tail: weird rooms, messy objects, bad lighting, and tasks that never look the same twice. Founded in 2023, X Square is building general-purpose embodied AI robots and foundation models for real-world environments, tying models, robot hardware, high-precision manipulation, data, and deployment into one system.

X Square Robot just closed its Series C at a valuation above RMB 20 billion, about $2.8 billion 🤖 IDG came into this round. The bigger signal is the cap table. HongShan and Xiaomi were already in across earlier rounds, while Meituan, Alibaba, ByteDance, and Xiaomi have each led rounds at different stages. That puts X Square in a rare position for an embodied AI company: top-tier financial capital on one side, and four of China’s biggest tech platforms on the other. This is not just a money story. Meituan, Alibaba, ByteDance, and Xiaomi bring very different strategic assets: real-world scenarios, cloud infrastructure, consumer traffic, supply chains, and hardware ecosystems. The deployment side is already moving: robot home-cleaning services first, then a “Robots Into Homes” program with the first batch entering real households. The model stack is worth watching too. X Square has open-sourced WALL-OSS-0.5 for robot manipulation and WALL-WM for world modeling. WALL-OSS-0.5 showed strong real-robot performance without post-training, while WALL-WM uses event-level prediction to align language, vision, and action around meaningful physical-world events. They are also building a model-driven data pipeline for large-scale collection, cleaning, annotation, quality control, and augmentation. That matters because home robotics dies in the long tail: weird rooms, messy objects, bad lighting, and tasks that never look the same twice. Founded in 2023, X Square is building general-purpose embodied AI robots and foundation models for real-world environments, tying models, robot hardware, high-precision manipulation, data, and deployment into one system.

RoboHub🤖

12,975 Aufrufe • vor 1 Monat

Beijing hosts world’s first humanoid robot games | Ariana News The world’s inaugural humanoid robot competition is underway in Beijing, drawing more than 500 robots from 280 teams across 16 countries to compete in a uniquely futuristic sporting spectacle. The three-day event, held at the National Speed Skating Oval—once the “Ice Ribbon” of the 2022 Winter Olympics—kicked off on August 15 and runs through to Sunday August 17. The tournament features 26 events spread across athletic, performance, and scenario-based categories. Athletic challenges include sprinting, soccer, and kickboxing, while performance segments showcase robot dance routines and musical instrument displays. Real-world scenarios, such as medication sorting, cleaning tasks, and industrial material handling, are also on the agenda to test practical functionality. Organizers meanwhile emphasize the event’s role in accelerating the integration of humanoid robots into everyday life, from manufacturing and hospitality to healthcare. One Chinese official summed it up: “Every robot that participates is creating history.” The competition has yielded both triumphant strides and technical stumbling blocks. In running events, the robot H1 from Unitree Robotics claimed top honors in the 1,500-meter race, demonstrating promising agility. Yet, many robots struggled with balance, coordination, and task execution, including some collapsing mid-sprint or requiring human help to stand—underscoring the still-developing nature of embodied artificial intelligence.

Beijing hosts world’s first humanoid robot games | Ariana News The world’s inaugural humanoid robot competition is underway in Beijing, drawing more than 500 robots from 280 teams across 16 countries to compete in a uniquely futuristic sporting spectacle. The three-day event, held at the National Speed Skating Oval—once the “Ice Ribbon” of the 2022 Winter Olympics—kicked off on August 15 and runs through to Sunday August 17. The tournament features 26 events spread across athletic, performance, and scenario-based categories. Athletic challenges include sprinting, soccer, and kickboxing, while performance segments showcase robot dance routines and musical instrument displays. Real-world scenarios, such as medication sorting, cleaning tasks, and industrial material handling, are also on the agenda to test practical functionality. Organizers meanwhile emphasize the event’s role in accelerating the integration of humanoid robots into everyday life, from manufacturing and hospitality to healthcare. One Chinese official summed it up: “Every robot that participates is creating history.” The competition has yielded both triumphant strides and technical stumbling blocks. In running events, the robot H1 from Unitree Robotics claimed top honors in the 1,500-meter race, demonstrating promising agility. Yet, many robots struggled with balance, coordination, and task execution, including some collapsing mid-sprint or requiring human help to stand—underscoring the still-developing nature of embodied artificial intelligence.

Owen Gregorian

43,158 Aufrufe • vor 1 Jahr

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,296 Aufrufe • vor 1 Monat

For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from Google DeepMind, the intelligence layer powering the next generation of truly adaptable robots. This major advance unlocks intelligent whole-body control, advanced dexterity, and even multi-robot collaboration 🤯. Ok but... how does a robot actually "think"? Real-world tasks take time and planning. To manage that complexity, our new embodied reasoning model, Gemini Robotics ER 2, acts as the robot’s high-level brain, enhancing the robot’s capabilities to: — Observe the environment — Reason about the actions needed to complete the task — Coordinate with the vision-language-action model to carry out actions — Track progress until the job is done This setup allows robots to execute complex multi-step workflows, self-correct if a step fails, and adapt to completely novel situations. Learn more about Gemini Robotics ER 2 (and our two other brand new models) here:

Google AI

661,070 Aufrufe • vor 25 Tagen

CHINA JUST SOLVED THE PROBLEM THAT'S BEEN BREAKING ROBOT AI FOR A DECADE. and the fix wasn't a smarter model. for years, every robot AI failure got the same diagnosis. the model isn't smart enough. so everyone scaled intelligence. bigger models. more parameters. better reasoning. AGIBOT asked a different question: what if the reasoning was never the problem? there's a gap that runs through every traditional robot AI system. reasoning on one side & motor commands on the other. the brain decides but the body executes something different, because thinking and moving were never actually connected. GO-2 fixes this by reasoning INSIDE the action space, not above it. before moving, it runs a complete mental simulation of every step - like a basketball player mentally tracing the arc of a shot before releasing the ball. watch the demo and you'll see exactly what this means. the robot works through a task queue autonomously. classify toiletries. upright the drink bottle. place headphones in the leather box. mid-execution, a new instruction drops: "my phone's missing. help me find it." it doesn't pause. doesn't reset. it processes the new task and keeps moving. that's not a scripted sequence. that's real-time instruction following on top of an active task queue. that one architectural change is where the numbers come from. > #1 on LIBERO across Spatial, Object, Goal, and Long tasks → 98.5% average success > 86.6% zero-shot accuracy in active disturbance environments > 47.4 on VLABench → best-in-class on objects and textures it's never seen before > 82.9% success trained on simulation only, tested on real hardware sim-to-real is the graveyard of robotics research. models trained in simulation collapse the moment they touch the real world. 82.9% means that graveyard just got a lot smaller. it holds because of how GO-2 trains. deliberately fed imperfect reasoning conditions, then trained to execute robustly anyway. not a researcher assumption. a design decision from a team that ships hardware and knows exactly what breaks. then there's the infrastructure layer. Genie Studio. fleet-wide data collection. cloud training. online post-training in live environments. 10x improvement in training efficiency. task startup reduced to minutes. 2-4x better success rates with 50%+ less data. the model gets smarter every time a robot fails in the field. this isn't a benchmark story. it's a compounding moat. dual CVPR 2026 + ACL 2026 acceptance. computer vision AND natural language processing. top conferences. simultaneously. that doesn't happen with incremental research. the US-China robotics race has been framed as a compute race. a model quality race. it was always an execution race. the robot that wins won't be the smartest one in the lab. it'll be the most reliable one on the floor. full breakdown: is execution reliability the real bottleneck, or are we still underestimating how far reasoning needs to go?

CHINA JUST SOLVED THE PROBLEM THAT'S BEEN BREAKING ROBOT AI FOR A DECADE. and the fix wasn't a smarter model. for years, every robot AI failure got the same diagnosis. the model isn't smart enough. so everyone scaled intelligence. bigger models. more parameters. better reasoning. AGIBOT asked a different question: what if the reasoning was never the problem? there's a gap that runs through every traditional robot AI system. reasoning on one side & motor commands on the other. the brain decides but the body executes something different, because thinking and moving were never actually connected. GO-2 fixes this by reasoning INSIDE the action space, not above it. before moving, it runs a complete mental simulation of every step - like a basketball player mentally tracing the arc of a shot before releasing the ball. watch the demo and you'll see exactly what this means. the robot works through a task queue autonomously. classify toiletries. upright the drink bottle. place headphones in the leather box. mid-execution, a new instruction drops: "my phone's missing. help me find it." it doesn't pause. doesn't reset. it processes the new task and keeps moving. that's not a scripted sequence. that's real-time instruction following on top of an active task queue. that one architectural change is where the numbers come from. > #1 on LIBERO across Spatial, Object, Goal, and Long tasks → 98.5% average success > 86.6% zero-shot accuracy in active disturbance environments > 47.4 on VLABench → best-in-class on objects and textures it's never seen before > 82.9% success trained on simulation only, tested on real hardware sim-to-real is the graveyard of robotics research. models trained in simulation collapse the moment they touch the real world. 82.9% means that graveyard just got a lot smaller. it holds because of how GO-2 trains. deliberately fed imperfect reasoning conditions, then trained to execute robustly anyway. not a researcher assumption. a design decision from a team that ships hardware and knows exactly what breaks. then there's the infrastructure layer. Genie Studio. fleet-wide data collection. cloud training. online post-training in live environments. 10x improvement in training efficiency. task startup reduced to minutes. 2-4x better success rates with 50%+ less data. the model gets smarter every time a robot fails in the field. this isn't a benchmark story. it's a compounding moat. dual CVPR 2026 + ACL 2026 acceptance. computer vision AND natural language processing. top conferences. simultaneously. that doesn't happen with incremental research. the US-China robotics race has been framed as a compute race. a model quality race. it was always an execution race. the robot that wins won't be the smartest one in the lab. it'll be the most reliable one on the floor. full breakdown: is execution reliability the real bottleneck, or are we still underestimating how far reasoning needs to go?

Shruti

18,622 Aufrufe • vor 4 Monaten

The internet was the training set for intelligence Nobody has built the equivalent for the physical world Previously, Lucas Ngoo co-founded Carousell, scaled it $1B+ Now at CortexAI he's collecting the data robotics labs need to train foundation models Cameras, VR headsets, glasses on factory workers, retail workers, everyday people. Recording real-world manipulation work Not building the robot. Not training the model. Collecting what goes in 2026: scale data 2027+: start rolling robots out Initially 90% teleoperation, 10% autonomy While humans step in, the system keeps learning That's the flywheel toward full autonomy 🎙️ Lucas Ngoo, Co-Founder & CEO, CortexAI on Fondo.com Start (full ep in comments)

The internet was the training set for intelligence Nobody has built the equivalent for the physical world Previously, Lucas Ngoo co-founded Carousell, scaled it $1B+ Now at CortexAI he's collecting the data robotics labs need to train foundation models Cameras, VR headsets, glasses on factory workers, retail workers, everyday people. Recording real-world manipulation work Not building the robot. Not training the model. Collecting what goes in 2026: scale data 2027+: start rolling robots out Initially 90% teleoperation, 10% autonomy While humans step in, the system keeps learning That's the flywheel toward full autonomy 🎙️ Lucas Ngoo, Co-Founder & CEO, CortexAI on Fondo.com Start (full ep in comments)

David J Phillips

110,268 Aufrufe • vor 5 Monaten

Most video-action robot models are a content-creation video generator with an action module attached. LingBot-VA 2.0 from Robbyant, a video-action foundation model, throws that starting point out and trains the whole stack natively for control. And it runs closed-loop at a peak 225 Hz. It's so important because A robot cannot move responsively when its controller pauses to imagine the next few frames. LingBot-VA 2.0 predicts during execution, then corrects using each real observation. And it carries only about 13B video parameters while activating roughly 1.9B per token. Bigger robot models usually mean slower reactions, creating a direct conflict between intelligence and control. LingBot-VA 2.0 is trained from scratch for robot control rather than adapted from a video generator built for content creation. Robbyant, an embodied AI company under Ant Group, built it to learn how scenes change under actions, predict what should happen next, and turn those predictions into real-time robot movements. Most video-action systems inherit a tokenizer and video backbone trained mainly to reproduce visual appearance. LingBot-VA 2.0 rebuilds both parts around physical control. Its semantic visual-action tokenizer maps observations toward features from a frozen vision foundation model and learns compact latent actions from frame-to-frame changes using self-supervised inverse and forward dynamics. Unlabeled web video can therefore carry action-relevant training signals without robot action labels. The policy is causal from the start, so every prediction can use only past observations. Its sparse Mixture-of-Experts video backbone has about 13B total parameters, while about 1.9B are active per token, keeping the compute lower during each step. A high-level vision-language planner breaks long tasks into smaller instructions, while the low-level video-action policy handles continuous movement. Foresight Reasoning predicts future visual states while the robot is already acting, then replaces imagined states with every new real observation. Combined with few-step distillation and systems acceleration, the paper reports a peak asynchronous execution frequency of 225 Hz. The model adapts from 10–15 demonstrations, transfers across robot embodiments, and handles some new tasks zero-shot. In the paper’s own evaluations, it reaches 93.6 average on RoboTwin 2.0 and reports stronger real-world results than LingBot-VA and π0.5 across the tested tasks. 🧵 1.

Most video-action robot models are a content-creation video generator with an action module attached. LingBot-VA 2.0 from Robbyant, a video-action foundation model, throws that starting point out and trains the whole stack natively for control. And it runs closed-loop at a peak 225 Hz. It's so important because A robot cannot move responsively when its controller pauses to imagine the next few frames. LingBot-VA 2.0 predicts during execution, then corrects using each real observation. And it carries only about 13B video parameters while activating roughly 1.9B per token. Bigger robot models usually mean slower reactions, creating a direct conflict between intelligence and control. LingBot-VA 2.0 is trained from scratch for robot control rather than adapted from a video generator built for content creation. Robbyant, an embodied AI company under Ant Group, built it to learn how scenes change under actions, predict what should happen next, and turn those predictions into real-time robot movements. Most video-action systems inherit a tokenizer and video backbone trained mainly to reproduce visual appearance. LingBot-VA 2.0 rebuilds both parts around physical control. Its semantic visual-action tokenizer maps observations toward features from a frozen vision foundation model and learns compact latent actions from frame-to-frame changes using self-supervised inverse and forward dynamics. Unlabeled web video can therefore carry action-relevant training signals without robot action labels. The policy is causal from the start, so every prediction can use only past observations. Its sparse Mixture-of-Experts video backbone has about 13B total parameters, while about 1.9B are active per token, keeping the compute lower during each step. A high-level vision-language planner breaks long tasks into smaller instructions, while the low-level video-action policy handles continuous movement. Foresight Reasoning predicts future visual states while the robot is already acting, then replaces imagined states with every new real observation. Combined with few-step distillation and systems acceleration, the paper reports a peak asynchronous execution frequency of 225 Hz. The model adapts from 10–15 demonstrations, transfers across robot embodiments, and handles some new tasks zero-shot. In the paper’s own evaluations, it reaches 93.6 average on RoboTwin 2.0 and reports stronger real-world results than LingBot-VA and π0.5 across the tested tasks. 🧵 1.

Rohan Paul

11,253 Aufrufe • vor 1 Monat