Google Rolls Out New Gemini Model That Can Run On Robots Locally
(Wednesday June 25, 2025 @03:00AM (BeauHD)
from the on-device dept.)
- Reference: 0178165831
- News link: https://hardware.slashdot.org/story/25/06/24/2150256/google-rolls-out-new-gemini-model-that-can-run-on-robots-locally
- Source link:
Google DeepMind has [1]launched Gemini Robotics On-Device, a new language model that [2]enables robots to perform complex tasks locally without internet connectivity . TechCrunch reports:
> Building on the company's previous Gemini Robotics model that was released in March, Gemini Robotics On-Device can control a robot's movements. Developers can control and fine-tune the model to suit various needs using natural language prompts. In benchmarks, Google claims the model performs at a level close to the cloud-based Gemini Robotics model. The company says it outperforms other on-device models in general benchmarks, though it didn't name those models.
>
> In a demo, the company showed robots running this local model doing things like unzipping bags and folding clothes. Google says that while the model was trained for ALOHA robots, it later adapted it to work on a bi-arm Franka FR3 robot and the Apollo humanoid robot by Apptronik. Google claims the bi-arm Franka FR3 was successful in tackling scenarios and objects it hadn't "seen" before, like doing assembly on an industrial belt. Google DeepMind is also releasing a [3]Gemini Robotics SDK . The company said developers can show robots 50 to 100 demonstrations of tasks to train them on new tasks using these models on the MuJoCo physics simulator.
[1] https://deepmind.google/discover/blog/gemini-robotics-on-device-brings-ai-to-local-robotic-devices/
[2] https://techcrunch.com/2025/06/24/google-rolls-out-new-gemini-model-that-can-run-on-robots-locally/
[3] https://github.com/google-deepmind/gemini-robotics-sdk
> Building on the company's previous Gemini Robotics model that was released in March, Gemini Robotics On-Device can control a robot's movements. Developers can control and fine-tune the model to suit various needs using natural language prompts. In benchmarks, Google claims the model performs at a level close to the cloud-based Gemini Robotics model. The company says it outperforms other on-device models in general benchmarks, though it didn't name those models.
>
> In a demo, the company showed robots running this local model doing things like unzipping bags and folding clothes. Google says that while the model was trained for ALOHA robots, it later adapted it to work on a bi-arm Franka FR3 robot and the Apollo humanoid robot by Apptronik. Google claims the bi-arm Franka FR3 was successful in tackling scenarios and objects it hadn't "seen" before, like doing assembly on an industrial belt. Google DeepMind is also releasing a [3]Gemini Robotics SDK . The company said developers can show robots 50 to 100 demonstrations of tasks to train them on new tasks using these models on the MuJoCo physics simulator.
[1] https://deepmind.google/discover/blog/gemini-robotics-on-device-brings-ai-to-local-robotic-devices/
[2] https://techcrunch.com/2025/06/24/google-rolls-out-new-gemini-model-that-can-run-on-robots-locally/
[3] https://github.com/google-deepmind/gemini-robotics-sdk
TermOS 0.0001 (Score:4, Funny)
by I'm just joshin ( 633449 )
In the future this will be known as Terminator OS 0.0001
amazingly accurate (Score:2)
by ZipNada ( 10152669 )
If you actually look at the demonstration videos you will see they are very impressive. A couple of bot arms can respond to voice commands and perform complex operations on objects on a table. I'd like to experiment with their SDK but the hardware would be expensive.
ALOHA Robots? (Score:2)
What do they do, dress in drag and do the hula?
Re: ALOHA Robots? (Score:2)
Ohhhhyeah babay and much more. The, umm... shall we say "use case" for the effable vacuum cleaner with a french maid outfit ... I'm ready for my Bender quote now.
Re: (Score:2)
> I'm ready for my Bender quote now.
Sorry to have gone so far off-script with a Lion King quote...
ALOHA Humans (Score:2)
In addition to murdering us? Not the way I imagined we'd go out.
Re: (Score:2)
Being completely ignorant on the topic of robots, thus having no fucking idea what ALOHA is... how in the fucking 9 hells can your robot require 60Gbps of bandwidth for articulation and some cameras?
That's two thousand and 400 fucking netflix streams.
Re: (Score:2)
> Being completely ignorant on the topic of robots, thus having no fucking idea what ALOHA is... how in the fucking 9 hells can your robot require 60Gbps of bandwidth for articulation and some cameras? That's two thousand and 400 fucking netflix streams.
Cameras with high resolution use a crapton of bandwidth, and compression adds considerable, which is probably undesirable. 1080p60 uncompressed is roughly 3 gigabits per camera, which is a whole USB 3 channel. Then again with a Pi, you'd probably want to use MIPI instead.
*shrugs*
But yeah, I can't imagine the motor control parts needing USB 2.0 speeds, much less 3.0. :-)
Re: (Score:2)
3Gbps for 24bpp, which seems excessive... but if that's what the camera outputs, that's what the camera outputs. Besides, dropping it to 16 doesn't materially affect the problem.
As for compression..... I have little experience with USB camera modules, but I know that MJPEG is a normal feature on them, which would get you 1080p60 (24bpp) for about 80Mbps per stream. The quality can be very high with huge bandwidth reduction. Still high compared to a temporally aware codec like H.264, but it's since it's per
Re: (Score:2)
Were it so easy.