Загрузка видео...

Не удалось загрузить видео

На главную

Control a robot in simulation with the Gemini Robotics Embodied Reasoning model 🤖 Direct tasks like object localization and placement by simply prompting a robotic arm to pick up and place objects.

googleaidevs's profile picture

Google AI Developers

117,367 subscribers

1,296,887 просмотров • 7 месяцев назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

We teamed up with Boston Dynamics to power their robot Spot with Gemini Robotics embodied reasoning models. This means it can better understand its surroundings, identify objects and follow simple commands - like tidying up a room.
0:37

We teamed up with Boston Dynamics to power their robot Spot with Gemini Robotics embodied reasoning models. This means it can better understand its surroundings, identify objects and follow simple commands - like tidying up a room.

Google DeepMind

154,311 просмотров • 5 месяцев назад

One more thing 🚀 Qwen’s agentic capability is no longer limited to the digital world — we’re bringing it into physical world. With our in-house robotic agentic system and navigation model, Qwen can now control a robot to execute tasks in real-world. #qwen #embodied #robotics
1:16

One more thing 🚀 Qwen’s agentic capability is no longer limited to the digital world — we’re bringing it into physical world. With our in-house robotic agentic system and navigation model, Qwen can now control a robot to execute tasks in real-world. #qwen #embodied #robotics

barry (xiong-hui) chen

25,104 просмотров • 3 месяцев назад

We took a robot to RSS in LA running our new Gemini Robotics On-Device VLA model. People interacted with the model with new objects and instructions in a brand new environment and the results were amazing!
0:48

We took a robot to RSS in LA running our new Gemini Robotics On-Device VLA model. People interacted with the model with new objects and instructions in a brand new environment and the results were amazing!

Ayzaan Wahid

19,710 просмотров • 1 год назад

We’re launching the first in a series of Embodied Reasoning offerings: Perceptron Egocentric. It achieves SOTA over the best robotic annotation pipelines built on Gemini 3.5 Flash and Gemini Robotics-ER 1.6. Early access is available to partners.
0:58

We’re launching the first in a series of Embodied Reasoning offerings: Perceptron Egocentric. It achieves SOTA over the best robotic annotation pipelines built on Gemini 3.5 Flash and Gemini Robotics-ER 1.6. Early access is available to partners.

Perceptron AI

107,859 просмотров • 2 месяцев назад

Gemini Robotics ER 2 is our most capable embodied reasoning model designed for physical AI 🤖 Built as a high-level brain for robotics, the model connects directly to the Gemini Live API. It processes continuous video streams to track progress, call tools, search the web, and command an action model in real time. Upgrades for developers include: + Enhanced progress tracking + Real-time mid-execution failure detection + Multi-robot collaboration + Advanced safety instruction following
2:31

Gemini Robotics ER 2 is our most capable embodied reasoning model designed for physical AI 🤖 Built as a high-level brain for robotics, the model connects directly to the Gemini Live API. It processes continuous video streams to track progress, call tools, search the web, and command an action model in real time. Upgrades for developers include: + Enhanced progress tracking + Real-time mid-execution failure detection + Multi-robot collaboration + Advanced safety instruction following

Google AI Developers

21,498 просмотров • 1 месяц назад

Teamwork makes the dream work. To test multi-robot collaboration with Gemini Robotics 2, we challenged our Apollo and Duo robots to tidy up a messy garage. The high-level reasoning model breaks down what to do, where to go, and identifies the exact moment to hand over control ↓
2:31

Teamwork makes the dream work. To test multi-robot collaboration with Gemini Robotics 2, we challenged our Apollo and Duo robots to tidy up a messy garage. The high-level reasoning model breaks down what to do, where to go, and identifies the exact moment to hand over control ↓

Google DeepMind

23,160 просмотров • 1 месяц назад

For an industrial robot built for the rigors of factories and power plants, tidying up a living room may seem like a light day at the office for Spot. Yet, this demonstration represents the promise of AI models in robotics. In this case, Google DeepMind's visual-language model (VLM) Gemini Robotics-ER 1.5 was empowering Spot with embodied reasoning. Go behind the scenes and watch the full demo in our blog:
1:39

For an industrial robot built for the rigors of factories and power plants, tidying up a living room may seem like a light day at the office for Spot. Yet, this demonstration represents the promise of AI models in robotics. In this case, Google DeepMind's visual-language model (VLM) Gemini Robotics-ER 1.5 was empowering Spot with embodied reasoning. Go behind the scenes and watch the full demo in our blog:

Boston Dynamics

61,283 просмотров • 5 месяцев назад

Gemini Robotics 2 by Google DeepMind uses sim-only post-training on a mixed-data base model to handle automotive kitting. Contact-rich tasks like these have long been considered one of the hardest challenges in Sim2Real. Gemini Robotics 2 shows simulation can work even here. General robot intelligence needs much more data than real-robot collection alone can provide. Simulation has proven to be an effective way to fill that gap.
2:31

Gemini Robotics 2 by Google DeepMind uses sim-only post-training on a mixed-data base model to handle automotive kitting. Contact-rich tasks like these have long been considered one of the hardest challenges in Sim2Real. Gemini Robotics 2 shows simulation can work even here. General robot intelligence needs much more data than real-robot collection alone can provide. Simulation has proven to be an effective way to fill that gap.

Axis Robotics

16,857 просмотров • 1 месяц назад

THIS IS VIBE CODING ROBOTICS. Someone just built a complete robot arm simulation using Gemini 3. AI wrote the inverse kinematics from scratch the robot stacks cubes to build walls.
0:43

THIS IS VIBE CODING ROBOTICS. Someone just built a complete robot arm simulation using Gemini 3. AI wrote the inverse kinematics from scratch the robot stacks cubes to build walls.

Aman

82,987 просмотров • 4 месяцев назад

A paper in Nature Communications describes a detachable robotic hand that can crawl and grab objects. The design enables tasks such as retrieving objects beyond normal reach and performing multi-object handling.
1:24

A paper in Nature Communications describes a detachable robotic hand that can crawl and grab objects. The design enables tasks such as retrieving objects beyond normal reach and performing multi-object handling.

Nature Portfolio

28,409 просмотров • 7 месяцев назад

Today we're releasing Isaac 0.5: 36B dynamic MoE, open weight 🤗 embodied foundation model. Isaac combines multimodal video understanding, embodied reasoning and robot control into a single, sparse backbone.
0:42

Today we're releasing Isaac 0.5: 36B dynamic MoE, open weight 🤗 embodied foundation model. Isaac combines multimodal video understanding, embodied reasoning and robot control into a single, sparse backbone.

Perceptron AI

268,524 просмотров • 18 дней назад

Robot vacuum and mop with a robotic arm that picks up trash 😲
0:55

Robot vacuum and mop with a robotic arm that picks up trash 😲

tiway🦋💙

1,206,518 просмотров • 10 месяцев назад

Stop prompting for "a room" and start prompting for "a mood." Create visual tension in your scenes with subject placement, lighting, and objects.
0:20

Stop prompting for "a room" and start prompting for "a mood." Create visual tension in your scenes with subject placement, lighting, and objects.

Google Flow

86,216 просмотров • 6 месяцев назад

A conversation with the Google DeepMind Robotics team about our latest Gemini Robotics 2 model, the arc of robotics progress, and where we go next 🤖
39:13

A conversation with the Google DeepMind Robotics team about our latest Gemini Robotics 2 model, the arc of robotics progress, and where we go next 🤖

Logan Kilpatrick

127,714 просмотров • 1 месяц назад

Very Powerful but very simple Prompting technique. Simply ask the LLM to re-read the question - and this significantly boosts LLM reasoning across diverse tasks and model types. 💡 Repeats question input twice in prompt, unlocks latent reasoning potential **Original Problem** 🤔: Decoder-only LLMs with unidirectional attention struggle with nuanced reasoning tasks due to limited global understanding of input questions. **Key Insights from this Paper **💡: • Re-reading (RE2) input enhances reasoning by improving question comprehension • Enables "bidirectional" understanding in unidirectional LLMs • Compatible with existing thought-eliciting prompting methods • Effective across various LLM types and reasoning tasks
5:19

Very Powerful but very simple Prompting technique. Simply ask the LLM to re-read the question - and this significantly boosts LLM reasoning across diverse tasks and model types. 💡 Repeats question input twice in prompt, unlocks latent reasoning potential **Original Problem** 🤔: Decoder-only LLMs with unidirectional attention struggle with nuanced reasoning tasks due to limited global understanding of input questions. **Key Insights from this Paper **💡: • Re-reading (RE2) input enhances reasoning by improving question comprehension • Enables "bidirectional" understanding in unidirectional LLMs • Compatible with existing thought-eliciting prompting methods • Effective across various LLM types and reasoning tasks

Rohan Paul

169,522 просмотров • 2 лет назад

Gemini Robotics 2 moves physical AI beyond tabletop tasks, enabling intelligent whole-body control for humanoids. Watch Apptronik's Apollo 2 process a single prompt to reach, bend, and pick up a watering can ↓
1:29

Gemini Robotics 2 moves physical AI beyond tabletop tasks, enabling intelligent whole-body control for humanoids. Watch Apptronik's Apollo 2 process a single prompt to reach, bend, and pick up a watering can ↓

Google DeepMind

42,372 просмотров • 1 месяц назад

How to rotate a tomato with a potato using a robot hand? 🤖🍅🥔 Our new model, Robot Synesthesia, blends touch and vision to manipulate multiple objects, even non-convex ones like a cross!
0:30

How to rotate a tomato with a potato using a robot hand? 🤖🍅🥔 Our new model, Robot Synesthesia, blends touch and vision to manipulate multiple objects, even non-convex ones like a cross!

Yuzhe Qin

78,609 просмотров • 2 лет назад

What happens when we train the largest vision-language model and add in robot experiences? The result is PaLM-E 🌴🤖, a 562-billion parameter, general-purpose, embodied visual-language generalist - across robotics, vision, and language. Website:
0:42

What happens when we train the largest vision-language model and add in robot experiences? The result is PaLM-E 🌴🤖, a 562-billion parameter, general-purpose, embodied visual-language generalist - across robotics, vision, and language. Website:

Danny Driess

1,272,600 просмотров • 3 лет назад