正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Boston Dynamics has released a new video of their next-generation humanoid robot, Atlas. "We are excited to share some of our progress on developing Large Behavior Models for Atlas. This work is part of a collaboration between AI research teams at Toyota Research Institute (TRI) and Boston Dynamics. We... show more

Sawyer Merritt

1,092,733 subscribers

200,744 次观看 • 10 个月前 •via X (Twitter)

健康养生科学技术艺术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Boston Dynamics has released a new video of their next-generation humanoid robot, Atlas, walking, running, crawling, breakdancing, somersaulting, and more.

Boston Dynamics has released a new video of their next-generation humanoid robot, Atlas, walking, running, crawling, breakdancing, somersaulting, and more.

Sawyer Merritt

1,116,705 次观看 • 1 年前

Boston Dynamics has shared a new video of its humanoid robot, Atlas. "Our engineers made one final push to test the limits of full-body control and mobility, with help from the RAI Institute."

Boston Dynamics has shared a new video of its humanoid robot, Atlas. "Our engineers made one final push to test the limits of full-body control and mobility, with help from the RAI Institute."

Sawyer Merritt

1,278,189 次观看 • 5 个月前

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

Reinforcement learning is used to speed the production of behavior for the Boston Dynamics Atlas humanoid robot. At the heart of the learning process is a physics-based simulator that generates training data for a variety of maneuvers.

RAI Institute

76,595 次观看 • 1 年前

Boston Dynamics has released a new video about humanoid robot hands. "Grippers are one of the most intricate parts of a humanoid robot, packed with actuation and sensing; they need to be durable enough to handle tough jobs, but precise enough to handle fragile items. Our engineers share how the Atlas gripper has evolved as our manipulation capabilities expand and the principles that will guide future iterations."

Boston Dynamics has released a new video about humanoid robot hands. "Grippers are one of the most intricate parts of a humanoid robot, packed with actuation and sensing; they need to be durable enough to handle tough jobs, but precise enough to handle fragile items. Our engineers share how the Atlas gripper has evolved as our manipulation capabilities expand and the principles that will guide future iterations."

Sawyer Merritt

230,726 次观看 • 9 个月前

Boston Dynamics has unveiled a new electric version of its Atlas humanoid robot that can do push-ups 🤖 While this is in no way an indicator of real-world use, it’s a great demonstration of Atlas’ extremely robust and powerful actuators

Boston Dynamics has unveiled a new electric version of its Atlas humanoid robot that can do push-ups 🤖 While this is in no way an indicator of real-world use, it’s a great demonstration of Atlas’ extremely robust and powerful actuators

TechCrunch

74,303 次观看 • 1 年前

The former American company Robot company, Boston Dynamics many folks, even informed folks have no idea is now part of South Korean Hyundai. They are putting Atlas bipedal humanoid robot to work on the auto production line.

The former American company Robot company, Boston Dynamics many folks, even informed folks have no idea is now part of South Korean Hyundai. They are putting Atlas bipedal humanoid robot to work on the auto production line.

Brian Roemmele

283,889 次观看 • 6 个月前

Boston Dynamics gave a glimpse at the next version of its Atlas robot at #CES2026, and its predecessor made up for its lack of movement. And now, we know they'll be powered by Google DeepMind AI:

Boston Dynamics gave a glimpse at the next version of its Atlas robot at #CES2026, and its predecessor made up for its lack of movement. And now, we know they'll be powered by Google DeepMind AI:

TechCrunch

44,836 次观看 • 6 个月前

🚨 BREAKING: Hyundai Worldwide to deploy tens of thousands of robots! Hyundai is scaling up its robotics strategy with a major investment in Boston Dynamics ' robotic platforms. The company plans to deploy tens of thousands of units — including the Atlas humanoid, Spot quadruped, and Stretch trailer-unloading robots—across its manufacturing and logistics operations in the coming years. Spot is already in use at Hyundai’s facilities, performing industrial inspection and predictive maintenance tasks. Atlas, Boston Dynamics’ bipedal robot, is next in line for factory deployment, aimed at addressing physically demanding and repetitive jobs. Beyond deployment, Hyundai will support Boston Dynamics’ growth by integrating the automaker’s manufacturing capabilities to boost robot production. The move is part of Hyundai’s broader ambition to lead in robotics and “physical AI”. That's so cool to see the scale-up phase with humanoids. Looking forward to seeing Atlas live in Boston this month. 🔥

🚨 BREAKING: Hyundai Worldwide to deploy tens of thousands of robots! Hyundai is scaling up its robotics strategy with a major investment in Boston Dynamics ' robotic platforms. The company plans to deploy tens of thousands of units — including the Atlas humanoid, Spot quadruped, and Stretch trailer-unloading robots—across its manufacturing and logistics operations in the coming years. Spot is already in use at Hyundai’s facilities, performing industrial inspection and predictive maintenance tasks. Atlas, Boston Dynamics’ bipedal robot, is next in line for factory deployment, aimed at addressing physically demanding and repetitive jobs. Beyond deployment, Hyundai will support Boston Dynamics’ growth by integrating the automaker’s manufacturing capabilities to boost robot production. The move is part of Hyundai’s broader ambition to lead in robotics and “physical AI”. That's so cool to see the scale-up phase with humanoids. Looking forward to seeing Atlas live in Boston this month. 🔥

Lukas Ziegler

64,247 次观看 • 1 年前

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Boston Dynamics has demonstrated its new Atlas humanoid robot lifting and carrying a 50-pound fridge. The robot uses its whole body to balance and move the heavy object in a natural, human-like way. Before doing it in the real world, Atlas practiced the task for millions of hours in a virtual simulation.

Space and Technology

180,041 次观看 • 1 个月前

Excited to share our work on STEERing robot behavior! With structured language annotation of offline data, STEER exposes fundamental manipulation skills that can be modulated and combined to enable zero-shot adaptation to new situations and tasks.

Excited to share our work on STEERing robot behavior! With structured language annotation of offline data, STEER exposes fundamental manipulation skills that can be modulated and combined to enable zero-shot adaptation to new situations and tasks.

Laura Smith

25,259 次观看 • 1 年前

Boston Dynamics will begin production of the new Atlas robots at its Boston headquarters immediately. All Atlas deployments are already fully committed for 2026, with fleets scheduled to ship to Hyundai and Google DeepMind in the coming months. The company plans to add additional customers in early 2027 and also plans to build a new robotics factory by 2028 that is capable of producing 30,000 robots per year.

Boston Dynamics will begin production of the new Atlas robots at its Boston headquarters immediately. All Atlas deployments are already fully committed for 2026, with fleets scheduled to ship to Hyundai and Google DeepMind in the coming months. The company plans to add additional customers in early 2027 and also plans to build a new robotics factory by 2028 that is capable of producing 30,000 robots per year.

The Humanoid Hub

349,504 次观看 • 6 个月前

Boston Dynamics has built the most iconic robots of the past years. But behind the viral clips lies a 30-year journey. From an MIT research lab to BigDog, Alphabet, Spot and Stretch, and now electric Atlas. 🧵 This is the real story.

Boston Dynamics has built the most iconic robots of the past years. But behind the viral clips lies a 30-year journey. From an MIT research lab to BigDog, Alphabet, Spot and Stretch, and now electric Atlas. 🧵 This is the real story.

Lukas Ziegler

56,351 次观看 • 6 个月前

We have been hard at work at the studio and are excited to share a reel of some of our web work. Excited for 2025!

We have been hard at work at the studio and are excited to share a reel of some of our web work. Excited for 2025!

Studio Null

27,283 次观看 • 1 年前

.Mario Bollini leads the Atlas product team at Boston Dynamics. Mario sees humanoid robots as the next-level tools embodying generalizable AI that could deliver meaningful commercial value. We discuss Mario’s journey in robotics, product lessons from Spot applied to Atlas, the hardware approach for Atlas, AI, potential commercial applications, home robots, the competition from China, and more. 00:17 Personal journey into robotics 02:20 Learnings from Spot 04:09 Atlas actuation - hydraulic to electric 05:36 Evolution of Atlas' movement control 07:55 Actuator design trade-offs 09:35 Design decision for Atlas' leg rotation 11:21 Stance on humanoid form factor 13:13 Customer skepticism; adoption hurdles 14:49 Atlas applications; current pilots 17:14 Atlas' readiness for human collaboration 19:46 Why not a five-finger hand 21:10 Explaining Large Behavior Models 22:26 Why is RAI a separate entity 24:04 Chicken-and-egg problem of robotics 27:09 Home use humanoids 29:14 Preventing weaponization 31:00 Competition from China 32:13 Long term future vision 33:55 Reason for Atlas's round head 35:27 Any final thoughts?

.Mario Bollini leads the Atlas product team at Boston Dynamics. Mario sees humanoid robots as the next-level tools embodying generalizable AI that could deliver meaningful commercial value. We discuss Mario’s journey in robotics, product lessons from Spot applied to Atlas, the hardware approach for Atlas, AI, potential commercial applications, home robots, the competition from China, and more. 00:17 Personal journey into robotics 02:20 Learnings from Spot 04:09 Atlas actuation - hydraulic to electric 05:36 Evolution of Atlas' movement control 07:55 Actuator design trade-offs 09:35 Design decision for Atlas' leg rotation 11:21 Stance on humanoid form factor 13:13 Customer skepticism; adoption hurdles 14:49 Atlas applications; current pilots 17:14 Atlas' readiness for human collaboration 19:46 Why not a five-finger hand 21:10 Explaining Large Behavior Models 22:26 Why is RAI a separate entity 24:04 Chicken-and-egg problem of robotics 27:09 Home use humanoids 29:14 Preventing weaponization 31:00 Competition from China 32:13 Long term future vision 33:55 Reason for Atlas's round head 35:27 Any final thoughts?

The Humanoid Hub

21,372 次观看 • 9 个月前

Excited to share our new work on building a multimodal atlas of human skin in health and inflammatory disease — a project I’m especially proud of, bringing together AI, high-throughput genomics, and clinical science to accelerate discovery. Over the past decade, single-cell genomics has transformed how we map cells in human tissues. But a major challenge remains: can we systematically decode how cells organize into functional niches in situ — including those invisible to standard histopathology? To address this, we integrated large-scale scRNA-seq, spatial transcriptomics, histopathology, and AI-driven modeling frameworks to build an in situ atlas of human skin across health and disease. Led by Lloyd Steele, an MD/PhD student working between Haniffa Lab and my lab at Wellcome Sanger Institute and Cambridge University . Another amazing collaboration with Muzz Haniffa, the mastermind behind the work as part of Human Cell Atlas. A key part of this study is that we didn’t build everything from scratch — we leveraged and combined AI methods that actually work! and showed how they can be used together to extract biological insight at scale. We used: • scArches to build and map into a reference scRNA-seq atlas of human skin: • NicheCompass to identify and characterize spatial niches: • MINT-Flow to extract microenvironment-induced cell states and gene programs: Together, these enabled an end-to-end workflow from atlas construction to spatial mapping, niche discovery, and cell state decoding. At scale, we integrated ~5 million cells and 100+ spatial sections, enabling a systematic view of tissue organization. Using this framework, we identified 26 niches in skin, including known histopathologic structures as well as hidden disease-associated niches not visible on H&E. Among the most striking findings were a resident memory T cell-rich sebaceous gland niche and a plasma cell-rich sweat gland niche, suggesting that appendageal structures act as active immunological microenvironments and may contribute to inflammatory memory and disease persistence. Importantly, this atlas is not just descriptive — it is usable. It can support mapping of new datasets, resolve finer cell types and niches, extract microenvironment-driven programs, and enable predictive analyses at scale. More broadly, this work shows what becomes possible when AI, spatial genomics, and atlas-scale data are integrated end-to-end: not just mapping tissues, but systematically decoding them. This was a massive collaboration, and I’m very grateful to the amazing scientists April Foster, Kenny Roberts, and Chloe Admane. Lloyd is an amazing scientist, and I’m especially excited for the community to see more of his work soon — stay tuned. The data and pre-trained models will be released soon. Preprint:

Excited to share our new work on building a multimodal atlas of human skin in health and inflammatory disease — a project I’m especially proud of, bringing together AI, high-throughput genomics, and clinical science to accelerate discovery. Over the past decade, single-cell genomics has transformed how we map cells in human tissues. But a major challenge remains: can we systematically decode how cells organize into functional niches in situ — including those invisible to standard histopathology? To address this, we integrated large-scale scRNA-seq, spatial transcriptomics, histopathology, and AI-driven modeling frameworks to build an in situ atlas of human skin across health and disease. Led by Lloyd Steele, an MD/PhD student working between Haniffa Lab and my lab at Wellcome Sanger Institute and Cambridge University . Another amazing collaboration with Muzz Haniffa, the mastermind behind the work as part of Human Cell Atlas. A key part of this study is that we didn’t build everything from scratch — we leveraged and combined AI methods that actually work! and showed how they can be used together to extract biological insight at scale. We used: • scArches to build and map into a reference scRNA-seq atlas of human skin: • NicheCompass to identify and characterize spatial niches: • MINT-Flow to extract microenvironment-induced cell states and gene programs: Together, these enabled an end-to-end workflow from atlas construction to spatial mapping, niche discovery, and cell state decoding. At scale, we integrated ~5 million cells and 100+ spatial sections, enabling a systematic view of tissue organization. Using this framework, we identified 26 niches in skin, including known histopathologic structures as well as hidden disease-associated niches not visible on H&E. Among the most striking findings were a resident memory T cell-rich sebaceous gland niche and a plasma cell-rich sweat gland niche, suggesting that appendageal structures act as active immunological microenvironments and may contribute to inflammatory memory and disease persistence. Importantly, this atlas is not just descriptive — it is usable. It can support mapping of new datasets, resolve finer cell types and niches, extract microenvironment-driven programs, and enable predictive analyses at scale. More broadly, this work shows what becomes possible when AI, spatial genomics, and atlas-scale data are integrated end-to-end: not just mapping tissues, but systematically decoding them. This was a massive collaboration, and I’m very grateful to the amazing scientists April Foster, Kenny Roberts, and Chloe Admane. Lloyd is an amazing scientist, and I’m especially excited for the community to see more of his work soon — stay tuned. The data and pre-trained models will be released soon. Preprint:

Mo Lotfollahi

11,759 次观看 • 3 个月前

Excited to announce Hi👋3DGen v0.1 - my first 3D generation project! Released at Huge thanks to the teams of Hyper3D by Deemos, VAST AI Research, and ByteDance for their guidance. We sincerely believe open collaboration drives AI innovation forward!

Excited to announce Hi👋3DGen v0.1 - my first 3D generation project! Released at Huge thanks to the teams of Hyper3D by Deemos, VAST AI Research, and ByteDance for their guidance. We sincerely believe open collaboration drives AI innovation forward!

Chongjie Ye

136,643 次观看 • 1 年前

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

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 次观看 • 6 个月前

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Roberta Raileanu

105,030 次观看 • 1 年前

Wrapping up the year and coinciding with #NeurIPS2024, today at Meta FAIR we’re releasing a collection of nine new open source AI research artifacts across our work in developing agents, robustness & safety and new architectures. More in the video from Joelle Pineau. All of this work is part of FAIR’s continued work towards the goal of achieving advanced machine intelligence A few highlights from what we’re releasing today: • Meta Motivo: A first-of-its-kind behavioral foundation model that controls the movements of a virtual embodied humanoid agent to perform complex tasks. • Meta Video Seal: a state-of-the art comprehensive framework for neural video watermarking. • Meta Explore Theory-of-Mind: A program-guided adversarial data generation for theory of mind reasoning. • Meta Large Concept Models: A fundamentally different training paradigm for language modeling that decouples reasoning from language representation. And much more! We’re excited to share this work with the research community and look forward to seeing how it inspires new innovation across the field. Details and access to everything released by FAIR today ➡️

Wrapping up the year and coinciding with #NeurIPS2024, today at Meta FAIR we’re releasing a collection of nine new open source AI research artifacts across our work in developing agents, robustness & safety and new architectures. More in the video from Joelle Pineau. All of this work is part of FAIR’s continued work towards the goal of achieving advanced machine intelligence A few highlights from what we’re releasing today: • Meta Motivo: A first-of-its-kind behavioral foundation model that controls the movements of a virtual embodied humanoid agent to perform complex tasks. • Meta Video Seal: a state-of-the art comprehensive framework for neural video watermarking. • Meta Explore Theory-of-Mind: A program-guided adversarial data generation for theory of mind reasoning. • Meta Large Concept Models: A fundamentally different training paradigm for language modeling that decouples reasoning from language representation. And much more! We’re excited to share this work with the research community and look forward to seeing how it inspires new innovation across the field. Details and access to everything released by FAIR today ➡️

AI at Meta

156,123 次观看 • 1 年前