DeepMind reveals Gemini Robotics 2.5 and open safety benchmark ASIMOV-jailbreak
Original title: DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
Google DeepMind has revealed the new-generation Gemini Robotics platform, bumping its VLA component Gemini Robotics to version 2.5, which works alongside the Gemini Embodied Reasoning planning layer. The model was evaluated across more than 200 activities with notable gains in dexterity, and Apptronik's Apollo 2 humanoid running Gemini Robotics 2.5 can now tie a bow with its five-fingered hands. Some Gemini robots have done real work in Mercedes-Benz factories, and DeepMind released the open-source safety benchmark ASIMOV-jailbreak as robots prepare to operate alongside humans.
Why it mattersThe article details Gemini Robotics 2.5's architecture layers, dexterity gains, and the accompanying open-source safety benchmark, offering a read on embodied AI progress.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.
Original article
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.
Read full article
Comments
The original belongs to Ars Technica · AI and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.
Studio