Google DeepMind just introduced Gemini Robotics 2.
@TheHumanoidHub119 тыс. подписчиков
133 792 просмотра
41 комментарий
Комментарии из оригинального поста в X (Twitter)

@TheHumanoidHub
For the first time, a Gemini Robotics model controls an entire humanoid, feet to fingertips, not just the upper body.
96 отметок «Нравится»

@TheHumanoidHub
The slow thinking brain: Gemini Robotics ER 2 The high-level reasoning model observes the room, plans multi-step tasks lasting minutes (hundreds of decisions), coordinates with the VLA to act, and self-corrects when a step fails. New: multi-robot collaboration
49 отметок «Нравится»

@TheHumanoidHub
Results: Hits medium-to-high success on whole-body and gripper tasks. But multi-finger dexterity is still hard. On Apollo + Sharpa hands: unscrew bulb 92%, yet tie trash bag 44%, ziplock 40%, dustpan 32%. Dexterous hands remain the challenging frontier.
36 отметок «Нравится»

@TheHumanoidHub
Availability: Gemini Robotics ER 2 (reasoning): on Google AI Studio, plus private preview on the Gemini Enterprise Agent Platform. The GR2 VLA and lighter On-Device VLA: open to early-access partners.
19 отметок «Нравится»

@TheHumanoidHub
My conversation with Google DeepMind's Kanishka Rao about the latest model, alternatives to VLAs, the real path to physical AGI, and more:
21 отметка «Нравится»

@CaliPaddy
A good physical Turing test would be: 1. Make a fly 2. Tie it to line 3. Walk to a boat 4. Row a boat 5. Catch a fish 6. Gut a fish 7. Cook a fish 8. Serve a fish And then clean up .
12 отметок «Нравится»

@TheHumanoidHub
fair
3 отметки «Нравится»

@gymshower2
Dope but what happens when it gets bitch slapped?
1 отметка «Нравится»

@wilderthanrogue
Computers were useful because they did things quicker, this is like watching paint dry
1 отметка «Нравится»

@BrianBellia
I've been following Apptronik's Apollo for years - this bot's hardware, except for recent improvements to the hands - hardly seems to have evolved at all. I don't even think Figure AI existed when I first saw Apollo, but progress at Figure appears to have overtaken them.
1 отметка «Нравится»

@l123333123
🤔 meticulously slow...
1 отметка «Нравится»

@47CryptoJV
Ziplock bags were designed for humans, not robots. Let's design the robots to do robot things. I'll seal my own plastic bag thank you.
1 отметка «Нравится»

@weluvrogercook
Checkpoints from the database point of view ??
1 отметка «Нравится»

@jiktop
very slow, why?
1 отметка «Нравится»

@TimoS163822
Is there something erotic about those gentle movements, or am I just weird? 😂
1 отметка «Нравится»

@stewthedeluxe
Yeah, at 100x the amount of time it takes you to do it yourself. Not helpful at all.
1 отметка «Нравится»

@TheLostArhu
Today, George Jetson turns Four. Just saying.
1 отметка «Нравится»

@TheHumanoidHub
cool trivia!
2 отметки «Нравится»

@JibroniSandwich
SharpaWave sounds creepy to me as the name for a hand

@AliciaV_0726
Great cut, really highlights the difficulty there. Who could have guessed that this would be possible even 2 years ago?

















