DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
In fact, some Gemini robots were able to get actual work done in Mercedes-Benz factories, and the team is preparing for a day when robots operate alongside humans with an open source safety benchmark.
- The other main component is the vision-language-action (VLA) that actually generates robot actions, like moving an actuator—that's Gemini Robotics, which has been bumped to version 2.5.
- Google DeepMind has revealed a new generation of the AI-powered Gemini Robotics platform.
- There's the vision-language model piece, which is Gemini Embodied Reasoning.
Google also showed that Apptronik’s Apollo 2 humanoid robot with Gemini Robotics 2.5 can now tie a bow with its five-fingered hands, a notable feat, because deformable objects (like ribbon) are notoriously difficult for robots to manipulate.
DeepMind says that Gemini Robotics 2.5 is much better at tasks that require a high degree of dexterity.
- The model was evaluated across more than 200 activities, including serving food with tongs and using a pipette, as you would see in a laboratory.
- In the 2.5 release, Google says its robotic AI is getting tantalizingly close to completing real-world tasks as well as humans do.
- Essentially, it takes your instructions and uses live video to plan how the robot can accomplish the task.
- DeepMind's physical AI platform has several computational layers between user input and robotic action.
How this summary was made: extractive summary — built from the sources' own reporting. It is drawn only from the reporting of the sources listed below — read the originals for full detail. How we summarize →