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.

Can we teach a robot its limits to do chores safely & correctly? 🧵 To help robots execute open-ended, multi-step tasks, MIT CSAIL researchers used vision models to see what’s near the machine & model its constraints. An LLM sketches up a plan that’s checked in a simulator to... show more

MIT CSAIL

346,761 subscribers

28,315 Aufrufe • vor 1 Jahr •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von MIT CSAIL

MIT CSAILvor 1 Jahr

Their trial-&-error method is called "Planning for Robots via Code for Continuous Constraint Satisfaction" (PRoC3S). It tests long-horizon plans to ensure they satisfy all constraints & enables a robot to perform diverse tasks, like writing individual letters, drawing a star, & sorting & placing blocks in different positions.

Profilbild von MIT CSAIL

MIT CSAILvor 1 Jahr

The researchers’ method uses an LLM pre-trained on text from across the Internet. Before asking PRoC3S to do a task, the team provided their language model w/a sample task (like drawing a square) that’s related to the target one (drawing a star). The sample task includes a description of the activity, a long-horizon plan, & relevant details about the robot’s environment.

Profilbild von MIT CSAIL

MIT CSAILvor 1 Jahr

In simulations, PRoC3S successfully drew stars & letters 8/10 times each. It also could stack digital blocks in pyramids & lines, & place items w/accuracy, like fruits on a plate. Across each of these digital demos, the CSAIL method completed the requested task more consistently than comparable approaches like "Code as Policies."

Profilbild von MIT CSAIL

MIT CSAILvor 1 Jahr

Next, the CSAIL engineers brought their approach to the real world. Their method developed & executed plans on a robotic arm, teaching it to put blocks in straight lines. PRoC3S also enabled the machine to place blue & red blocks into matching bowls & move all objects near the center of a table.

Profilbild von MIT CSAIL

MIT CSAILvor 1 Jahr

In the future, PRoC3S could help robots complete more intricate chores in dynamic environments like houses, where they may be prompted to do a general chore composed of many steps (like "make me breakfast").

Profilbild von MIT CSAIL

MIT CSAILvor 1 Jahr

For future work, the researchers aim to improve results using a more advanced physics simulator, & to expand to more elaborate longer-horizon tasks via more scalable data-search techniques. They also plan to apply PRoC3S to mobile robots (such as quadrupeds) for tasks that include walking & scanning surroundings.

Profilbild von MIT CSAIL

MIT CSAILvor 1 Jahr

Authors: Aidan Curtis (@AidanCurtis3), Nishanth Kumar (@nishanthkumar23), Jing Cao, Tomás Lozano-Pérez, & Leslie Pack Kaelbling (@MIT_LISLab) Website: Full video:

Profilbild von Yang

Yangvor 1 Jahr

Want to learn how practical AI skills and automations for your business and work? Check out our 50+ step-by-step video tutorials 100% FREE 20+ hours of Ai and Automation goodness absolutely free 🥳

Profilbild von freaky fresh

freaky freshvor 1 Jahr

ew! no, no you can’t. you can do other things, but, no - the word ‘teach’ doesn’t actually apply in this context. its usage is an annoying misuse of language that shouldn’t be coming out an academic institution of your standing. Pedagogy has a long history. who’s your audience?

Profilbild von Reza Sayar

Reza Sayarvor 1 Jahr

I understood exactly none of that

Profilbild von Rémy Dumas

Rémy Dumasvor 1 Jahr

C'est vraiment intéressant! Les applications potentielles pour l'apprentissage automatique et la robotique sont énormes

Ähnliche Videos

California startup announces breakthrough in general-purpose robotics with π0.5 AI — a vision-language-action model. Everything the robot sees, it sees for the first time. The robot has not been trained to recognize its surroundings. We are getting there! Only a few more years until we finally have household robots. A dream is coming true!

California startup announces breakthrough in general-purpose robotics with π0.5 AI — a vision-language-action model. Everything the robot sees, it sees for the first time. The robot has not been trained to recognize its surroundings. We are getting there! Only a few more years until we finally have household robots. A dream is coming true!

Chubby♨️

218,435 Aufrufe • vor 1 Jahr

LG has unveiled the LG Cloid home robot at CES 2026 as part of its vision for a Zero Labor Home, where robots handle everyday household tasks. The robot can assist with cooking, laundry, and control smart home devices through LG ThinQ while using AI to understand and interact with its surroundings. LG also introduced its new Axium robotic actuator, aiming to make AI-powered homes more capable and reduce household work.

LG has unveiled the LG Cloid home robot at CES 2026 as part of its vision for a Zero Labor Home, where robots handle everyday household tasks. The robot can assist with cooking, laundry, and control smart home devices through LG ThinQ while using AI to understand and interact with its surroundings. LG also introduced its new Axium robotic actuator, aiming to make AI-powered homes more capable and reduce household work.

Space and Technology

12,917 Aufrufe • vor 1 Monat

1X Technologies has started mass production of its NEO humanoid robot at a factory in California. The factory can build up to 10,000 robots each year and aims to exceed 100,000 units annually by 2027. Some NEO robots are already working in the factory, helping with tasks like moving parts and handling logistics.

1X Technologies has started mass production of its NEO humanoid robot at a factory in California. The factory can build up to 10,000 robots each year and aims to exceed 100,000 units annually by 2027. Some NEO robots are already working in the factory, helping with tasks like moving parts and handling logistics.

Space and Technology

95,398 Aufrufe • vor 1 Monat

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: 🧵

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

466,261 Aufrufe • vor 1 Jahr

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️

Additionally, looking towards the future, we’re releasing PARTNR: a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration. Built on Habitat 3.0, it’s the largest benchmark of its kind to study and evaluate human-robot collaboration in household activities By providing a standardized benchmark and dataset we hope to enable new research on robots that can not only operate in isolation, but in collaboration with people. Details and code ➡️

AI at Meta

20,244 Aufrufe • vor 1 Jahr

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

179,497 Aufrufe • vor 11 Stunden

A robot that works with 1 to 6 legs? This reconfigurable robot adapts like a spider, switching between different movement styles on the fly. SnapBot isn’t just a legged robot: it’s a shape-shifting machine. With up to 700 configurations, it can walk, crawl, or row its way through any terrain. Why this is exciting: ✅ Changes its setup from one to six legs for different tasks ✅ Moves in multiple ways, including walking, rowing, and crawling ✅ Adapts to its environment like nature’s best climbers and crawlers ✅ A step toward robots that adjust to real-world challenges instantly Nature-inspired robotics is unlocking new ways to move. SnapBot proves that flexibility is key to the future of locomotion.

A robot that works with 1 to 6 legs? This reconfigurable robot adapts like a spider, switching between different movement styles on the fly. SnapBot isn’t just a legged robot: it’s a shape-shifting machine. With up to 700 configurations, it can walk, crawl, or row its way through any terrain. Why this is exciting: ✅ Changes its setup from one to six legs for different tasks ✅ Moves in multiple ways, including walking, rowing, and crawling ✅ Adapts to its environment like nature’s best climbers and crawlers ✅ A step toward robots that adjust to real-world challenges instantly Nature-inspired robotics is unlocking new ways to move. SnapBot proves that flexibility is key to the future of locomotion.

Ilir Aliu

78,016 Aufrufe • vor 1 Jahr

Elon just dropped a MAJOR nugget on how Tesla is going to be training Optimus to do real world tasks. They are building an Optimus Academy, which is a large scale, dedicated real-world training facility to accelerate the development of Optimus. The Academy will deploy thousands of Optimus units, potentially 10,000 to 30,000 robots, in a controlled realistic environment where they perform self-play, experiment with tasks, iterate on behaviors, and continuously generate training data through trial and error. The Tesla bots will also run millions of simulations in Tesla’s high-fidelity physics-accurate engine, allowing Optimus to close the “sim-to-real gap” by using these real-world observations to refine and validate the simulations! “You’re actually highlighting an important limitation and difference from cars. We’ll soon have 10 million cars on the road. It’s hard to duplicate that massive training flywheel. For the robot, what we’re going to need to do is build a lot of robots and put them in kind of an Optimus Academy so they can do self-play in reality. We’re actually building that out. We can have at least 10,000 Optimus robots, maybe 20-30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator, a physics-accurate reality generator, that we made for the cars. We’ll do the same thing for the robots. We actually have done that for the robots. So you have a few tens of thousands of humanoid robots doing different tasks. You can do millions of simulated robots in the simulated world. You use the tens of thousands of robots in the real world to close the simulation to reality gap. Close the sim-to-real gap.”

Elon just dropped a MAJOR nugget on how Tesla is going to be training Optimus to do real world tasks. They are building an Optimus Academy, which is a large scale, dedicated real-world training facility to accelerate the development of Optimus. The Academy will deploy thousands of Optimus units, potentially 10,000 to 30,000 robots, in a controlled realistic environment where they perform self-play, experiment with tasks, iterate on behaviors, and continuously generate training data through trial and error. The Tesla bots will also run millions of simulations in Tesla’s high-fidelity physics-accurate engine, allowing Optimus to close the “sim-to-real gap” by using these real-world observations to refine and validate the simulations! “You’re actually highlighting an important limitation and difference from cars. We’ll soon have 10 million cars on the road. It’s hard to duplicate that massive training flywheel. For the robot, what we’re going to need to do is build a lot of robots and put them in kind of an Optimus Academy so they can do self-play in reality. We’re actually building that out. We can have at least 10,000 Optimus robots, maybe 20-30,000, that are doing self-play and testing different tasks. Tesla has quite a good reality generator, a physics-accurate reality generator, that we made for the cars. We’ll do the same thing for the robots. We actually have done that for the robots. So you have a few tens of thousands of humanoid robots doing different tasks. You can do millions of simulated robots in the simulated world. You use the tens of thousands of robots in the real world to close the simulation to reality gap. Close the sim-to-real gap.”

Teslaconomics

42,563 Aufrufe • vor 5 Monaten

🇨🇳 It has started. A new home service in China pairs human cleaners with autonomous AI robots to tackle household chores. Residents in Shenzhen can now book a service where a human professional and an autonomous robot arrive together to clean their home. Real houses present a chaotic mess of dropped toys and random furniture that confuse traditional machines. X Square Robot and a major service platform named 58[.]com decided to tackle this chaos by launching China's first robot cleaner service in March-26. Customers use an application to hire a cleaning crew that consists of 1 human worker and 1 robot. The human takes care of the tricky chores that require complex judgment. The robot handles the repetitive physical work like picking up trash and wiping down flat surfaces. This machine runs on a system called WALL-A, which acts as a single continuous AI brain rather than a list of pre-written rules. They built this AI foundation model to perceive its surroundings and make its own decisions without human guidance. It processes visual data and plans multi-step actions. And deploying these robots into actual homes now provides the massive amounts of extremely important training data to improve it continuously. Alibaba and ByteDance backed this project. IMO, if the foundational model behind it figures out how to navigate a messy living room without getting stuck, it can learn to operate in almost any other physical environment.

🇨🇳 It has started. A new home service in China pairs human cleaners with autonomous AI robots to tackle household chores. Residents in Shenzhen can now book a service where a human professional and an autonomous robot arrive together to clean their home. Real houses present a chaotic mess of dropped toys and random furniture that confuse traditional machines. X Square Robot and a major service platform named 58[.]com decided to tackle this chaos by launching China's first robot cleaner service in March-26. Customers use an application to hire a cleaning crew that consists of 1 human worker and 1 robot. The human takes care of the tricky chores that require complex judgment. The robot handles the repetitive physical work like picking up trash and wiping down flat surfaces. This machine runs on a system called WALL-A, which acts as a single continuous AI brain rather than a list of pre-written rules. They built this AI foundation model to perceive its surroundings and make its own decisions without human guidance. It processes visual data and plans multi-step actions. And deploying these robots into actual homes now provides the massive amounts of extremely important training data to improve it continuously. Alibaba and ByteDance backed this project. IMO, if the foundational model behind it figures out how to navigate a messy living room without getting stuck, it can learn to operate in almost any other physical environment.

Rohan Paul

52,996 Aufrufe • vor 4 Monaten

Another home-use humanoid robot The cute and friendly Onero H1 comes from Switchbot. It looks like a wheeled humanoid robot that grew out of a robotic vacuum cleaner base. It can perform tasks such as making coffee, doing laundry, folding clothes, tidying up, and acting as a life assistant. Its embedded OmniSense VLA model allows it to adapt to complex household tasks. Notably, smart home brands such as LG, Samsung, Haier, Midea, and Xiaomi are all launching home-use humanoid robots, marking a new stage in smart home living.

Another home-use humanoid robot The cute and friendly Onero H1 comes from Switchbot. It looks like a wheeled humanoid robot that grew out of a robotic vacuum cleaner base. It can perform tasks such as making coffee, doing laundry, folding clothes, tidying up, and acting as a life assistant. Its embedded OmniSense VLA model allows it to adapt to complex household tasks. Notably, smart home brands such as LG, Samsung, Haier, Midea, and Xiaomi are all launching home-use humanoid robots, marking a new stage in smart home living.

CyberRobo

21,147 Aufrufe • vor 6 Monaten

Can GPT-4 teach a robot hand to do pen spinning tricks better than you do? I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API! Eureka bridges the gap between high-level reasoning (coding) and low-level motor control. It is a “hybrid-gradient architecture”: a black box, inference-only LLM instructs a white box, learnable neural network. The outer loop runs GPT-4 to refine the reward function (gradient-free), while the inner loop runs reinforcement learning to train a robot controller (gradient-based). We are able to scale up Eureka thanks to IsaacGym, a GPU-accelerated physics simulator that speeds up reality by 1000x. On a benchmark suite of 29 tasks across 10 robots, Eureka rewards outperform expert human-written ones on 83% of the tasks by 52% improvement margin on average. We are surprised that Eureka is able to learn pen spinning tricks, which are very difficult even for CGI artists to animate frame by frame! Eureka also enables a new form of in-context RLHF, which is able to incorporate a human operator’s feedback in natural language to steer and align the reward functions. It can serve as a powerful co-pilot for robot engineers to design sophisticated motor behaviors. As usual, we open-source everything! Welcome you all to check out our video gallery and try the codebase today: Paper: Code: Deep dive with me: 🧵

Can GPT-4 teach a robot hand to do pen spinning tricks better than you do? I'm excited to announce Eureka, an open-ended agent that designs reward functions for robot dexterity at super-human level. It’s like Voyager in the space of a physics simulator API! Eureka bridges the gap between high-level reasoning (coding) and low-level motor control. It is a “hybrid-gradient architecture”: a black box, inference-only LLM instructs a white box, learnable neural network. The outer loop runs GPT-4 to refine the reward function (gradient-free), while the inner loop runs reinforcement learning to train a robot controller (gradient-based). We are able to scale up Eureka thanks to IsaacGym, a GPU-accelerated physics simulator that speeds up reality by 1000x. On a benchmark suite of 29 tasks across 10 robots, Eureka rewards outperform expert human-written ones on 83% of the tasks by 52% improvement margin on average. We are surprised that Eureka is able to learn pen spinning tricks, which are very difficult even for CGI artists to animate frame by frame! Eureka also enables a new form of in-context RLHF, which is able to incorporate a human operator’s feedback in natural language to steer and align the reward functions. It can serve as a powerful co-pilot for robot engineers to design sophisticated motor behaviors. As usual, we open-source everything! Welcome you all to check out our video gallery and try the codebase today: Paper: Code: Deep dive with me: 🧵

Jim Fan

2,674,165 Aufrufe • vor 2 Jahren

A pint-sized robot named Erbai in China has gone viral after it "kidnapped" dozens of larger robots at a robot showroom in China. People are finding the incident both hilarious and territying. The event, captured on CCTV, shows Erbai -an Al-powered robot - engaging in human-like conversations with other robots at the showroom to convince them to "go home" with it. The footage shows Erbai roaming the hallways at midnight, it then stops before a row of larger robots and asks one, "Are you still working overtime?" "We don't get off work," the larger robot responds. "Are you going home?" Erbai persists. "I don't have a home," the larger robot replies. Erbai then invites the bigger robots to "go home" and, surprisingly, the robots followed its lead, chanting, "Go home, go home!" The company behind Erbai confirmed that the "kidnapping" was real, though pre-planned. They explained it was a test designed to evaluate Erbai's ability to interact with and influence other robots. The team collaborated with an Al firm to see whether Erbai could autonomously "recruit" other robots.

A pint-sized robot named Erbai in China has gone viral after it "kidnapped" dozens of larger robots at a robot showroom in China. People are finding the incident both hilarious and territying. The event, captured on CCTV, shows Erbai -an Al-powered robot - engaging in human-like conversations with other robots at the showroom to convince them to "go home" with it. The footage shows Erbai roaming the hallways at midnight, it then stops before a row of larger robots and asks one, "Are you still working overtime?" "We don't get off work," the larger robot responds. "Are you going home?" Erbai persists. "I don't have a home," the larger robot replies. Erbai then invites the bigger robots to "go home" and, surprisingly, the robots followed its lead, chanting, "Go home, go home!" The company behind Erbai confirmed that the "kidnapping" was real, though pre-planned. They explained it was a test designed to evaluate Erbai's ability to interact with and influence other robots. The team collaborated with an Al firm to see whether Erbai could autonomously "recruit" other robots.

Brian Roemmele

659,913 Aufrufe • vor 7 Monaten

🚨 Apple joins the robotics race! Researchers from Carnegie Mellon University and Apple have developed a robot collision avoidance system. They called it ARMOR and they implemented it on the Fourier GR-1 robot. What is ARMOR? 👘 ARMOR is a system that helps humanoid robots "see" their surroundings better by using small, smart depth sensors placed on their arms. It solves the problem of blind spots and occlusions in traditional robot perception, making robots much safer and more efficient. It uses Time-of-Flight (ToF) sensors to detect obstacles, providing a near-complete view of the robot’s environment. 🔭 A smart software powered by transformer-based AI learns from human movements to help robots plan their actions dynamically. ARMOR reduces collisions by an impressive 63.7%, making robots significantly better at navigating crowded or complex spaces. The system is fast as well! 💨 ARMOR-Policy cuts computational time by 26× compared to traditional planning methods, ensuring robots can act quickly. P.S. Thoughts on this? The research paper is in the comments! ~~~ ♻️ RT to help 1 robot find a new workplace.

🚨 Apple joins the robotics race! Researchers from Carnegie Mellon University and Apple have developed a robot collision avoidance system. They called it ARMOR and they implemented it on the Fourier GR-1 robot. What is ARMOR? 👘 ARMOR is a system that helps humanoid robots "see" their surroundings better by using small, smart depth sensors placed on their arms. It solves the problem of blind spots and occlusions in traditional robot perception, making robots much safer and more efficient. It uses Time-of-Flight (ToF) sensors to detect obstacles, providing a near-complete view of the robot’s environment. 🔭 A smart software powered by transformer-based AI learns from human movements to help robots plan their actions dynamically. ARMOR reduces collisions by an impressive 63.7%, making robots significantly better at navigating crowded or complex spaces. The system is fast as well! 💨 ARMOR-Policy cuts computational time by 26× compared to traditional planning methods, ensuring robots can act quickly. P.S. Thoughts on this? The research paper is in the comments! ~~~ ♻️ RT to help 1 robot find a new workplace.

Lukas Ziegler

169,472 Aufrufe • vor 1 Jahr

Exploration is key for robots to generalize, especially in open-ended environments with vague goals and sparse rewards. BUT, how do we go beyond random poking? Wouldn't it be great to have a robot that explores an environment just like a kid? Introducing Imagine, Verify, Execute (IVE)! IVE leverages Vision-Language models to • extract semantic scene graphs, • imagine novel scenes, • predict their physical plausibility, and • generate executable sequences. IVE is a memory-guided agentic exploration framework that operates fully automatically, enabling more diverse and meaningful exploration.

Exploration is key for robots to generalize, especially in open-ended environments with vague goals and sparse rewards. BUT, how do we go beyond random poking? Wouldn't it be great to have a robot that explores an environment just like a kid? Introducing Imagine, Verify, Execute (IVE)! IVE leverages Vision-Language models to • extract semantic scene graphs, • imagine novel scenes, • predict their physical plausibility, and • generate executable sequences. IVE is a memory-guided agentic exploration framework that operates fully automatically, enabling more diverse and meaningful exploration.

Jia-Bin Huang

45,352 Aufrufe • vor 1 Jahr

World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or compete intelligently? 2️⃣ How do humans build social bonds and communities? 3️⃣ How can both co-exist in an open, dynamic world? Announcing Virtual Community Project — a social-physical world simulator, where human characters and robotic agents can interact, grow, and co-evolve within open-world societies, stretching from London to New York, and beyond! Key features include: ✅ Unified multi-agent physics simulations for rich social + physical interactions of humans and robots ✅ Massive auto-generated 3D scenes grounded with the rea-world geospatial data ✅ Agent communities populated by robots and LLM-driven human characters with rich appearances, personalities, and social ties. 🌍 Enter our Virtual Community, an open world to study embodied AI at scale— one social-physical world model at a time! 🔗 Project: 💻 Code: Paper: 1/n

World Simulator, reimagined — now alive with humans, robots, and their vibrant society unfolding in 3D real-world geospatial scenes across the globe! 🚀 One day soon, humans and robots will co-exist in the same world. To prepare, we must address: 1️⃣ How can robots cooperate or compete intelligently? 2️⃣ How do humans build social bonds and communities? 3️⃣ How can both co-exist in an open, dynamic world? Announcing Virtual Community Project — a social-physical world simulator, where human characters and robotic agents can interact, grow, and co-evolve within open-world societies, stretching from London to New York, and beyond! Key features include: ✅ Unified multi-agent physics simulations for rich social + physical interactions of humans and robots ✅ Massive auto-generated 3D scenes grounded with the rea-world geospatial data ✅ Agent communities populated by robots and LLM-driven human characters with rich appearances, personalities, and social ties. 🌍 Enter our Virtual Community, an open world to study embodied AI at scale— one social-physical world model at a time! 🔗 Project: 💻 Code: Paper: 1/n

Chuang Gan

90,261 Aufrufe • vor 1 Jahr

A robot that leaps like a squirrel 🐿️ Researchers at the UC Berkeley have created a robot that can jump and land on a branch, just like a squirrel. This robot, called Salto, is inspired by how squirrels leap and balance in trees. Researchers studied how squirrels adjust their movements to stick a perfect landing. They then programmed Salto to mimic these techniques, helping it land safely on narrow surfaces. They programmed it to adjust its posture mid-air, extending or crouching based on its trajectory. The robot also uses a passive gripper for stability, though it doesn't actively grip like a squirrel. By combining biology and engineering, scientists are making robots more agile than ever. P.S. It's cool to see Salto again in action after 2 years :)

A robot that leaps like a squirrel 🐿️ Researchers at the UC Berkeley have created a robot that can jump and land on a branch, just like a squirrel. This robot, called Salto, is inspired by how squirrels leap and balance in trees. Researchers studied how squirrels adjust their movements to stick a perfect landing. They then programmed Salto to mimic these techniques, helping it land safely on narrow surfaces. They programmed it to adjust its posture mid-air, extending or crouching based on its trajectory. The robot also uses a passive gripper for stability, though it doesn't actively grip like a squirrel. By combining biology and engineering, scientists are making robots more agile than ever. P.S. It's cool to see Salto again in action after 2 years :)

Lukas Ziegler

20,612 Aufrufe • vor 1 Jahr

Japan Airlines has unveiled a humanoid robot trial at Tokyo’s Haneda Airport to test baggage handling and aircraft cabin cleaning to address Japan’s growing labor shortages caused by an aging population, shrinking workforce, and booming tourism demand. Starting next month, they will conduct mid-to-long-term phased verifications with these Unitree robots. Initially, operations at airport sites will be visualized and analyzed to identify areas where humanoid robots can operate safely. After that, repeated operational verifications simulating actual airport environments will be conducted, with the ultimate goal of establishing a sustainable operational structure through labor savings and reducing workload by having humanoid robots complement human tasks. The trial will last about two years. What a time to be alive that we are now seeing humanoid robot trials like this. Buckle up y'all, humanoid robots are going to start doing a lot of things us humans used to do.

Japan Airlines has unveiled a humanoid robot trial at Tokyo’s Haneda Airport to test baggage handling and aircraft cabin cleaning to address Japan’s growing labor shortages caused by an aging population, shrinking workforce, and booming tourism demand. Starting next month, they will conduct mid-to-long-term phased verifications with these Unitree robots. Initially, operations at airport sites will be visualized and analyzed to identify areas where humanoid robots can operate safely. After that, repeated operational verifications simulating actual airport environments will be conducted, with the ultimate goal of establishing a sustainable operational structure through labor savings and reducing workload by having humanoid robots complement human tasks. The trial will last about two years. What a time to be alive that we are now seeing humanoid robot trials like this. Buckle up y'all, humanoid robots are going to start doing a lot of things us humans used to do.

Sawyer Merritt

109,076 Aufrufe • vor 3 Monaten

Robotics models often struggle outside controlled environments. Ours is built to work in real ones. Today we're launching MolmoAct 2, which can assist with a host of chores & lab tasks, plus the MolmoAct 2-Bimanual YAM dataset—the largest open robotics dataset of its kind. 🧵

Robotics models often struggle outside controlled environments. Ours is built to work in real ones. Today we're launching MolmoAct 2, which can assist with a host of chores & lab tasks, plus the MolmoAct 2-Bimanual YAM dataset—the largest open robotics dataset of its kind. 🧵

Ai2

402,669 Aufrufe • vor 2 Monaten

Sunday Robotics CEO Tony Zhao believes home robots only need to master a handful of chores before they become indispensable. "What is the minimum number of tasks that a robot needs to do to justify its own existence so that people love having it in their homes? I actually think the list is pretty short. The tasks are pretty repetitive. You just need to learn it and just keep doing that over and over again, like folding shirts or loading dishwashers."

Sunday Robotics CEO Tony Zhao believes home robots only need to master a handful of chores before they become indispensable. "What is the minimum number of tasks that a robot needs to do to justify its own existence so that people love having it in their homes? I actually think the list is pretty short. The tasks are pretty repetitive. You just need to learn it and just keep doing that over and over again, like folding shirts or loading dishwashers."

TBPN

64,079 Aufrufe • vor 10 Tagen