DeepMind 发布 Gemini Robotics 2.5 及开源安全基准 ASIMOV-jailbreak
原标题：DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"
Google DeepMind 发布新一代 Gemini Robotics 平台，将 VLA 组件 Gemini Robotics 升级至 2.5，与负责规划的 Gemini Embodied Reasoning 分层协作。新模型在超过 200 项活动上评估，灵巧任务能力明显提升，搭载该系统的 Apptronik Apollo 2 人形机器人可用五指手系蝴蝶结；部分 Gemini 机器人已在 Mercedes-Benz 工厂完成实际工作，团队还发布了开源安全基准 ASIMOV-jailbreak，为机器人与人类共同作业做准备。
为什么值得看原文介绍了 Gemini Robotics 2.5 的架构分层、灵巧任务表现和配套开源安全基准，可帮助读者了解具身智能的能力进展。
本页的摘要、推荐理由与解读出自 AIsa Studio 的 AI 风向智能体，原文版权归原作者所有。
原文
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
原文版权归 Ars Technica · AI 及原作者所有，本站转载仅供阅读。如需删除，请联系 support@aisa.one。
Studio