DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
DeepMind releases Gemini Robotics 2.5, whose robotic AI has approached human level in completing 200 tasks such as gripping food and laboratory pipetting, and has achieved high-precision operations like tying bows on the Apptronik Apollo humanoid robot; this version significantly improves dexterity while launching the open-source security benchmark "ASIMOV-jailbreak".
Same story3 other outlets also reported this
- Google DeepMind··First
Google DeepMind releases Gemini Robotics 2.5 vision-language-action model
- Ars Technica · AI··+19 h 9 min·Reading now
DeepMind releases Gemini Robotics 2.5 and open-source security benchmark "ASIMOV-jailbreak"
- The Decoder··+21 h 19 min
Google DeepMind's Gemini Robotics 2.5 achieves a success rate of 96% in Mercedes-Benz assembly line trials
- ITHome · AI··+27 h 3 min
Google's strongest VLA robot model, Gemini Robotics 2.5, debuts, can tie bows, already on the Mercedes production line
In order of publication · later reports are added as they appear
Google DeepMind has revealed a new generation of the AI-powered Gemini Robotics platform. In the 2.5 release, Google says its robotic AI is getting tantalizingly close to completing real-world tasks as well as humans do. 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.
DeepMind's physical AI platform has several computational layers between user input and robotic action. There's the vision-language model piece, which is Gemini Embodied Reasoning. Essentially, it takes your instructions and uses live video to plan how the robot can accomplish the task. 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.
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. 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.
Source: Ars Technica · AI · arstechnica.com