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。

Here is another uncut video of real-time interactions with Google DeepMind 's Gemini Robotics!

Dorsa Sadigh

11,810 subscribers

204,499 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

11 条评论

Dorsa Sadigh 的头像

Dorsa Sadigh1 年前

Fun fact that the robot and fox are completely OOD and are random toys that I grabbed from Niv's toy box!

Togoda AI Search Engine 的头像

Togoda AI Search Engine1 年前

Togoda is Google on Steroids with AI summaries . 🚀 The only thematic AI search engine.👀 It's 100% private with third party proxy. 🧨 Try it today & experience the difference! 👉Follow us @togoda_com 👈 🚀Help us grow & share this post!🚀

Aryaman 的头像

Aryaman1 年前

@GoogleDeepMind Very cool! It looked like it started picking up the boat before you instructed it to do so. Was this intended?

Dorsa Sadigh 的头像

Dorsa Sadigh1 年前

@GoogleDeepMind Regarding the robot going for some early picks, the reason is that it has learned some default behaviors based on all the past instructions. You can ask it to pause or have a success detector to avoid some of the early picks.

prakyath kantharaju 的头像

prakyath kantharaju1 年前

@GoogleDeepMind Nice and congrats! One question: why was the model pushy and was trying to pick up before you asked? Was it mentioned in the prompt ( not sure exactly in words ) or preprogrammed to pick everything on the desk and place it in the basket?

Ciszek 的头像

Ciszek1 年前

@GoogleDeepMind an AI that can finally fix printer errors

Ge Yang 的头像

Ge Yang1 年前

@GoogleDeepMind There is so much joy in this video! ❤️

Amir Abs 的头像

Amir Abs1 年前

@GoogleDeepMind Super cool Dorsa!!

Hoss Doge 的头像

Hoss Doge1 年前

@GoogleDeepMind Wow. Hope this does better soon. Really shatters my hopes and dreams watching that.

Rethynk AI 的头像

Rethynk AI1 年前

@GoogleDeepMind Google DeepMind’s work on real-time robot interactions is seriously impressive, especially with that low-latency voice.

Anindya 的头像

Anindya1 年前

@GoogleDeepMind Btw super cool, I am noticing one thing here that it's somehow taking the action of putting things in the basket as a default instruction, so without you even telling properly, it starts to put everything in the basket for whatever it sees or interprets

相关视频

What better way to welcome spring than a picnic with friends! Watch Gemini Robotics help Rachel and friends Google DeepMind London pack a picnic basket. 🧺 uncut, autonomous, 1x speed

What better way to welcome spring than a picnic with friends! Watch Gemini Robotics help Rachel and friends Google DeepMind London pack a picnic basket. 🧺 uncut, autonomous, 1x speed

Dhruv Shah

13,261 次观看 • 1 年前

Google DeepMind introduced two foundational models for embodied reasoning, enabling robots to comprehend, react, and take action in the physical world: ⦿ Gemini Robotics – built on Gemini 2.0. Integrates vision, language, and action for real-world dexterity, . ⦿ Gemini Robotics-ER – Enhances spatial reasoning for advanced robotic control. They are working with Apptronik to develop the next generation of humanoid robots.

Google DeepMind introduced two foundational models for embodied reasoning, enabling robots to comprehend, react, and take action in the physical world: ⦿ Gemini Robotics – built on Gemini 2.0. Integrates vision, language, and action for real-world dexterity, . ⦿ Gemini Robotics-ER – Enhances spatial reasoning for advanced robotic control. They are working with Apptronik to develop the next generation of humanoid robots.

The Humanoid Hub

73,097 次观看 • 1 年前

Here we go: Gemini 3.0 is live! Thankfully, I was able to be an early tester. It's the best model I've ever tested - nothing comes even close to it. OpenAI will have a very hard time to keep up with Google, because Gemini 3.0 will now be the benchmark for all future models. I have been invited by Google DeepMind / Google - Thanks to Google DeepMind for the #EarlyAccess Here's a summary of Gemini 3.0 with all the important benchmark evals:

Here we go: Gemini 3.0 is live! Thankfully, I was able to be an early tester. It's the best model I've ever tested - nothing comes even close to it. OpenAI will have a very hard time to keep up with Google, because Gemini 3.0 will now be the benchmark for all future models. I have been invited by Google DeepMind / Google - Thanks to Google DeepMind for the #EarlyAccess Here's a summary of Gemini 3.0 with all the important benchmark evals:

Chubby♨️

108,611 次观看 • 7 个月前

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

The Humanoid Hub

65,928 次观看 • 9 个月前

Boston Dynamics and Google DeepMind announced a partnership to integrate Gemini Robotics AI models with the new electric Atlas humanoid robots. Got to say hi to Carolina Parada before the presentation

Boston Dynamics and Google DeepMind announced a partnership to integrate Gemini Robotics AI models with the new electric Atlas humanoid robots. Got to say hi to Carolina Parada before the presentation

The Humanoid Hub

14,689 次观看 • 6 个月前

The Gemini era is here — helping you do more with the magic of Google AI.

The Gemini era is here — helping you do more with the magic of Google AI.

Google

9,171,205 次观看 • 2 年前

In a new Google DeepMind video, Hannah Fry threw a curveball into the scene: a squishy stress ball the model had never encountered. Watch it adapt to the physics in real-time. This is what open-ended robotics looks like.

In a new Google DeepMind video, Hannah Fry threw a curveball into the scene: a squishy stress ball the model had never encountered. Watch it adapt to the physics in real-time. This is what open-ended robotics looks like.

Humanoids daily

306,837 次观看 • 7 个月前

“We think we have a competitive advantage.” - Demis Hassibis, Head of Google DeepMind / AI efforts While Anthropic and OpenAI seek to win via training on “text” (written language), Demis Hassabis says Google Gemini is attempting a different path: Multimodal. Gemini aims to be the most effective model in the real world: physics, robotics, voice, visual, sensory, & text. The bet is multimodal unlocks more of what humanity really cares about.

“We think we have a competitive advantage.” - Demis Hassibis, Head of Google DeepMind / AI efforts While Anthropic and OpenAI seek to win via training on “text” (written language), Demis Hassabis says Google Gemini is attempting a different path: Multimodal. Gemini aims to be the most effective model in the real world: physics, robotics, voice, visual, sensory, & text. The bet is multimodal unlocks more of what humanity really cares about.

Compound248 💰

17,731 次观看 • 2 个月前

Excited to share what we've been cooking Google DeepMind to bring Gemini into the physical world! 🦾🧠 Here is an uncut interaction of the Gemini Robotics VLA helping me clean up my desk. 🔊 Interacting with a robot through voice is the most surreal experience, and parallels the giddy excitement I had playing with early LLMs that is hard to put in words. You've got to try it to believe it! Over the next few days, we'll be sharing more such interactions that go beyond shiny demos and expose raw capabilities of our models. Stay tuned for more raw videos! Tech Report: Blog: YouTube Playlist:

Excited to share what we've been cooking Google DeepMind to bring Gemini into the physical world! 🦾🧠 Here is an uncut interaction of the Gemini Robotics VLA helping me clean up my desk. 🔊 Interacting with a robot through voice is the most surreal experience, and parallels the giddy excitement I had playing with early LLMs that is hard to put in words. You've got to try it to believe it! Over the next few days, we'll be sharing more such interactions that go beyond shiny demos and expose raw capabilities of our models. Stay tuned for more raw videos! Tech Report: Blog: YouTube Playlist:

Dhruv Shah

68,585 次观看 • 1 年前

Google DeepMind announces Gemini Robotics On-Device - an efficient VLA model optimized to run locally with low-latency inference. It enables general-purpose dexterity, adapts to new tasks or robot hardware with fewer than 100 demos.

Google DeepMind announces Gemini Robotics On-Device - an efficient VLA model optimized to run locally with low-latency inference. It enables general-purpose dexterity, adapts to new tasks or robot hardware with fewer than 100 demos.

The Humanoid Hub

46,528 次观看 • 1 年前

WOW. I made Portal with Gemini 3 Pro in minutes! It has full controller support and runs great! Google AI Google DeepMind Logan Kilpatrick

WOW. I made Portal with Gemini 3 Pro in minutes! It has full controller support and runs great! Google AI Google DeepMind Logan Kilpatrick

Christopher Fryant

79,196 次观看 • 7 个月前

The introduction of AI Visual Inspections expanded what Spot and Orbit could tell you about your facility - now, AIVI-Learning powered by Google DeepMind Gemini Robotics unlocks a whole new level of visual intelligence for your robot. Learn more:

The introduction of AI Visual Inspections expanded what Spot and Orbit could tell you about your facility - now, AIVI-Learning powered by Google DeepMind Gemini Robotics unlocks a whole new level of visual intelligence for your robot. Learn more:

Boston Dynamics

25,155 次观看 • 3 个月前

Google Gemini Gemini crafted this History of Electricity time frame with Gemini integrated with it to give informative information about that time period of electricity. Truly incredible 🙏🏿

Google Gemini Gemini crafted this History of Electricity time frame with Gemini integrated with it to give informative information about that time period of electricity. Truly incredible 🙏🏿

Marco Kelly

32,179 次观看 • 7 个月前

Apptronik is in advanced talks to secure a new funding round of at least $400 million, led by existing investor B Capital, potentially reaching a $5 billion pre-money valuation. This follows a previous Series A round in February 2025 where the Austin-based humanoid robotics company raised $350 million, co-led by B Capital and Capital Factory, with participation from Google. Apptronik is also in a strategic partnership with Google DeepMind to integrate advanced AI models. Here’s Apptronik’s Apollo robot showcasing Gemini Robotics 1.5’s agentic capabilities.

Apptronik is in advanced talks to secure a new funding round of at least $400 million, led by existing investor B Capital, potentially reaching a $5 billion pre-money valuation. This follows a previous Series A round in February 2025 where the Austin-based humanoid robotics company raised $350 million, co-led by B Capital and Capital Factory, with participation from Google. Apptronik is also in a strategic partnership with Google DeepMind to integrate advanced AI models. Here’s Apptronik’s Apollo robot showcasing Gemini Robotics 1.5’s agentic capabilities.

The Humanoid Hub

83,009 次观看 • 7 个月前

🚨 BREAKING: Google DeepMind just revealed Gemini- ChatGPT's biggest competitor. Gemini is the FIRST multimodal AI to outperform human experts on the MMLU, scoring over 90%.

🚨 BREAKING: Google DeepMind just revealed Gemini- ChatGPT's biggest competitor. Gemini is the FIRST multimodal AI to outperform human experts on the MMLU, scoring over 90%.

Rowan Cheung

1,858,921 次观看 • 2 年前

It's happening... Google DeepMind is about to drop Genie 3 This AI can generate interactive 3D worlds with just text... And you can interact with objects in real time 🤯

It's happening... Google DeepMind is about to drop Genie 3 This AI can generate interactive 3D worlds with just text... And you can interact with objects in real time 🤯

Min Choi

727,450 次观看 • 5 个月前

Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥 🌎 Introducing our new work from Google DeepMind: Evaluating Gemini Robotics Policies in a Veo World Simulator 🧵👇

Generalist robots need a generalist evaluator. But how do you test safety without breaking things? 💥 🌎 Introducing our new work from Google DeepMind: Evaluating Gemini Robotics Policies in a Veo World Simulator 🧵👇

Anirudha Majumdar

238,689 次观看 • 7 个月前