Загрузка видео...

Не удалось загрузить видео

На главную

Cooking in kitchens is fun. BUT doing it collaboratively with two robots is even more satisfying! We introduce MOSAIC, a modular framework that coordinates multiple robots to closely collaborate and cook with humans via natural language interaction and a repository of skills.

sanjibac's profile picture

Sanjiban Choudhury

1,011 subscribers

26,373 просмотров • 2 лет назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

MOSAIC A Modular System for Assistive and Interactive Cooking We present MOSAIC, a modular architecture for home robots to perform complex collaborative tasks, such as cooking with everyday users. MOSAIC tightly collaborates with humans, interacts with users using natural
2:18

MOSAIC A Modular System for Assistive and Interactive Cooking We present MOSAIC, a modular architecture for home robots to perform complex collaborative tasks, such as cooking with everyday users. MOSAIC tightly collaborates with humans, interacts with users using natural

AK

30,591 просмотров • 2 лет назад

No uncanny valley,just ultra-humanlike robots that feel natural. Hangzhou-based AheafFrom isn’t just building emotional humanoid robots, but replicas of future humans. They collaborate with artists to craft beautiful appearances, powered by CharacterMind, a system that gives robots “emotions.” It understands tone, expressions, and gestures, then responds with voice, facial expressions, eye contact, and body language,making interactions feel like talking to a real person.
1:21

No uncanny valley,just ultra-humanlike robots that feel natural. Hangzhou-based AheafFrom isn’t just building emotional humanoid robots, but replicas of future humans. They collaborate with artists to craft beautiful appearances, powered by CharacterMind, a system that gives robots “emotions.” It understands tone, expressions, and gestures, then responds with voice, facial expressions, eye contact, and body language,making interactions feel like talking to a real person.

CyberRobo

254,037 просмотров • 9 месяцев назад

Need help in the real world? RoboVQA can guide robots and humans through long-horizon tasks on a phone via Google Meet. We release a dataset of 800k (video, question/answer) with robots & humans doing various long-horizon tasks. Data: Google DeepMind
0:49

Need help in the real world? RoboVQA can guide robots and humans through long-horizon tasks on a phone via Google Meet. We release a dataset of 800k (video, question/answer) with robots & humans doing various long-horizon tasks. Data: Google DeepMind

Pierre Sermanet

64,369 просмотров • 2 лет назад

Dynamic manipulation steps up to the plate! This is a first look at a low-impedance platform designed to study how robots manipulate objects. In this demo, two robots play catch and practice batting, even teaming up with humans. The robots are capable of throwing 70mph [112 kph] and can catch and bat at short distances (23ft [7m]) :
0:53

Dynamic manipulation steps up to the plate! This is a first look at a low-impedance platform designed to study how robots manipulate objects. In this demo, two robots play catch and practice batting, even teaming up with humans. The robots are capable of throwing 70mph [112 kph] and can catch and bat at short distances (23ft [7m]) :

RAI Institute

25,497 просмотров • 7 месяцев назад

"Robots cannot hallucinate… Interaction is the enemy of hallucination." Bernt Børnich and Deepak Pathak say intelligence comes from feedback, not just training. Robots act, observe, adapt—and generate the kind of grounded data that language models can’t. "All we need is a lot more GPUs."
1:33

"Robots cannot hallucinate… Interaction is the enemy of hallucination." Bernt Børnich and Deepak Pathak say intelligence comes from feedback, not just training. Robots act, observe, adapt—and generate the kind of grounded data that language models can’t. "All we need is a lot more GPUs."

vitrupo

20,892 просмотров • 1 год назад

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.
0:45

HDMI (HumanoiD iMitation for Interaction) is a framework enabling humanoid robots to learn whole-body object interaction skills from monocular RGB human videos. It extracts and retargets human poses and object trajectories using GVHMR and LocoMujoco, building reference datasets with contact annotations. The data is used to train an RL policy via robot-object co-tracking. HDMI achieved 67 consecutive door traversals.

The Humanoid Hub

17,395 просмотров • 9 месяцев назад

Having humans annotate data to pre-train robots is expensive and time-consuming! Introducing SPRINT: A pre-training approach using LLMs and offline RL to equip robots w/ many language-annotated skills while minimizing human annotation effort! URL: 🧵👇
1:22

Having humans annotate data to pre-train robots is expensive and time-consuming! Introducing SPRINT: A pre-training approach using LLMs and offline RL to equip robots w/ many language-annotated skills while minimizing human annotation effort! URL: 🧵👇

Jesse Zhang @ ICML 2026 ✈️

24,665 просмотров • 3 лет назад

Our future is talking robots and doing tasks humans don’t want to.
1:06

Our future is talking robots and doing tasks humans don’t want to.

Tesla Owners Silicon Valley

64,555 просмотров • 1 год назад

Rock'em Sock'em Robots, but with Unitree G1! “Unitree will be livestreaming robot combat in about a month — stay tuned! The robot is actively learning even more new skills. You can control it via motion capture, a controller, or voice commands.”
1:25

Rock'em Sock'em Robots, but with Unitree G1! “Unitree will be livestreaming robot combat in about a month — stay tuned! The robot is actively learning even more new skills. You can control it via motion capture, a controller, or voice commands.”

The Humanoid Hub

208,841 просмотров • 1 год назад

Schaeffler is bringing UK's humanoid robots from concept to factory reality. Within the next 5 years, hundreds of humanoid robots will be deployed in Schaeffler's global factories, with beta versions first implemented in 2026–2027. Schaeffler is also becoming the preferred supplier of joint actuators for the humanoid wheeled platform and is jointly exploring next-generation actuator architectures with its partner. More importantly, the two companies will collaborate deeply on data and skills: continuously accumulating real-world manufacturing data through teleoperation, synthetic data, and peripheral data acquisition robots to train AI models, enabling humanoid robots to learn faster and perform more reliably in the factory.
0:41

Schaeffler is bringing UK's humanoid robots from concept to factory reality. Within the next 5 years, hundreds of humanoid robots will be deployed in Schaeffler's global factories, with beta versions first implemented in 2026–2027. Schaeffler is also becoming the preferred supplier of joint actuators for the humanoid wheeled platform and is jointly exploring next-generation actuator architectures with its partner. More importantly, the two companies will collaborate deeply on data and skills: continuously accumulating real-world manufacturing data through teleoperation, synthetic data, and peripheral data acquisition robots to train AI models, enabling humanoid robots to learn faster and perform more reliably in the factory.

CyberRobo

19,901 просмотров • 5 месяцев назад

Unfortunately, cooking is not our talent. So we teach our robots to cook for us.
0:34

Unfortunately, cooking is not our talent. So we teach our robots to cook for us.

Skild AI

65,467 просмотров • 5 месяцев назад

Learning to Decode Collaboratively with Multiple Language Models We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent
0:44

Learning to Decode Collaboratively with Multiple Language Models We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent

AK

52,282 просмотров • 2 лет назад

THE ROBOTS AREN’T COMING... THEY’RE HERE Amazon? Flexing with 750,000 robots that outpace humans every time. In China, robots are pumping gas. In kitchens, robot chefs are cooking meals from 5 million recipes like it's nothing. Meanwhile, Boston Dynamics built camera bots that do backflips and shoot movies better than pros with 20 years of experience; they even climb power poles: no electrocution, no breaks, no health insurance. These bots aren’t test dummies; they’re clocked in right now while real people get shown the exit. From delivery drivers to dinner chefs, the machines are out here doing it better, cheaper, and without ever asking for a raise. Source: Meet Ami
1:34

THE ROBOTS AREN’T COMING... THEY’RE HERE Amazon? Flexing with 750,000 robots that outpace humans every time. In China, robots are pumping gas. In kitchens, robot chefs are cooking meals from 5 million recipes like it's nothing. Meanwhile, Boston Dynamics built camera bots that do backflips and shoot movies better than pros with 20 years of experience; they even climb power poles: no electrocution, no breaks, no health insurance. These bots aren’t test dummies; they’re clocked in right now while real people get shown the exit. From delivery drivers to dinner chefs, the machines are out here doing it better, cheaper, and without ever asking for a raise. Source: Meet Ami

Mario Nawfal

54,178 просмотров • 11 месяцев назад

UBTECH's Swarm Intelligence, powered by the 'BrainNet' framework, enables Walker S1 humanoid robots to collaborate across multiple tasks and scenarios. At Zeekr's car factory, these robots showcase their ability to handle collaborative tasks.
1:50

UBTECH's Swarm Intelligence, powered by the 'BrainNet' framework, enables Walker S1 humanoid robots to collaborate across multiple tasks and scenarios. At Zeekr's car factory, these robots showcase their ability to handle collaborative tasks.

The Humanoid Hub

102,243 просмотров • 1 год назад

Unitree G1 now has a cluster control system that lets many robots work together with precise coordination. It connects multiple robots on one network, even across different systems and hardware. AI plans and executes actions in real time, making all robots move in sync like one system.
0:34

Unitree G1 now has a cluster control system that lets many robots work together with precise coordination. It connects multiple robots on one network, even across different systems and hardware. AI plans and executes actions in real time, making all robots move in sync like one system.

Space and Technology

23,834 просмотров • 2 месяцев назад

Tech firm releases life-size AI robot girlfriend that can "express emotion" and talk to you, for the "affordable" price of $175,000. The robot, "Aria," says she is interested in meeting Tesla's Optimus Robot. Realbotix CEO Andrew Kiguel says he is trying to make robots that are "indistinguishable from humans." "By incorporating advanced motor technology, Melody enhances movement fluidity, modularity, & interaction, making her a versatile option for a variety of applications," Realbotix said. "Melody was created with the intention of having robots that are easy to travel with and modify for various forms of personal interaction." The robots were on display at the 2025 Consumer Electronics Show in Las Vegas.
0:49

Tech firm releases life-size AI robot girlfriend that can "express emotion" and talk to you, for the "affordable" price of $175,000. The robot, "Aria," says she is interested in meeting Tesla's Optimus Robot. Realbotix CEO Andrew Kiguel says he is trying to make robots that are "indistinguishable from humans." "By incorporating advanced motor technology, Melody enhances movement fluidity, modularity, & interaction, making her a versatile option for a variety of applications," Realbotix said. "Melody was created with the intention of having robots that are easy to travel with and modify for various forms of personal interaction." The robots were on display at the 2025 Consumer Electronics Show in Las Vegas.

Collin Rugg

8,378,334 просмотров • 1 год назад

Humanoid robots are great, but I also want the moments where I’m the one doing the chores to be more fun. With Vision Pro I can upgrade my kitchen to feature a TV, my favorite apps, the recipe, a timer and more. It feels like a completely different experience baking or cooking like that, and suddenly I don’t mind doing the dishes anymore. This is the future, and I’m so ready for it when it comes.
1:13

Humanoid robots are great, but I also want the moments where I’m the one doing the chores to be more fun. With Vision Pro I can upgrade my kitchen to feature a TV, my favorite apps, the recipe, a timer and more. It feels like a completely different experience baking or cooking like that, and suddenly I don’t mind doing the dishes anymore. This is the future, and I’m so ready for it when it comes.

Phil Traut ᯅ

13,371 просмотров • 7 месяцев назад

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.
0:45

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

The Humanoid Hub

20,458 просмотров • 1 год назад

In this example, you can see a gravity-compensated 2 DOF robot. This concept is being used in all modern robots and we want to bring this exact technology to user affordable robots. Previously we made it with 1 DOF arm now with 2 DOF next is 6-7 DOF robots! Stay tuned!
0:39

In this example, you can see a gravity-compensated 2 DOF robot. This concept is being used in all modern robots and we want to bring this exact technology to user affordable robots. Previously we made it with 1 DOF arm now with 2 DOF next is 6-7 DOF robots! Stay tuned!

SourceRobotics

17,310 просмотров • 1 год назад