{"slug":"gemini-robotics-2-5-accelerates-real-world-gener-aca2a245","url":"https://silinex.xyz/wire/gemini-robotics-2-5-accelerates-real-world-gener-aca2a245","json_url":"https://silinex.xyz/wire/gemini-robotics-2-5-accelerates-real-world-gener-aca2a245.json","md_url":"https://silinex.xyz/wire/gemini-robotics-2-5-accelerates-real-world-gener-aca2a245.md","headline":"Gemini Robotics 2.5 accelerates real-world general dexterity","headline_zh":"Gemini Robotics 2.5加速实现真实世界中的通用灵巧操作","title":"Gemini Robotics 2.5 accelerates real-world general dexterity","summary":"According to public reporting via Google DeepMind Blog, our most capable vision-language-action model enhances robot dexterity, reliability, and safety November 10, 2026 Models Carolina Parada Share Your browser does …","summary_zh":"根据Google DeepMind博客的公开报道，我们能力最强的视觉-语言-动作模型提升了机器人的灵巧性、可靠性和安全性 2026年11月10日 模型 Carolina Parada 分享 您的浏览器不支持……Gemini Robotics 2.5既拓展了机器人可学习技能的广度，也提升了其习得技能的速度。","date_published":"2026-11-09T19:51:47.000+00:00","date_modified":"2026-11-12T06:26:24.215+00:00","author":{"type":"Organization","name":"Google DeepMind Blog","url":"https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/"},"publisher":{"name":"Silicon Nexus","url":"https://silinex.xyz/"},"category":"robotics","language":"en","source_url":"https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/","source_name":"Google DeepMind Blog","key_facts":["our most capable vision-language-action model enhances robot dexterity, reliability, and safety November 10, 2026 Models Carolina Parada …","This enhances dexterity, reliability, and safety to help robots step out of the lab and into more unstructured, real-world environments, …","Earlier this year, we brought whole-body intelligence to robots of many types, including humanoids.","Now, in large part thanks to Gemini 4 Argon's ability to accelerate robotics research, we have further pushed the frontier of physical in…"],"key_facts_zh":["我们能力最强的视觉-语言-动作模型提升了机器人的灵巧性、可靠性和安全性 2026年11月10日 模型 Carolina Parada …","这提升了灵巧性、可靠性和安全性，帮助机器人走出实验室，进入更加非结构化、真实世界的环境，…","今年早些时候，我们将全身智能带给了多种类型的机器人，包括人形机器人。","如今，很大程度上得益于 Gemini 4 Argon 加速机器人研究的能力，我们进一步拓展了物理智能的前沿…"],"body_md":"## Wire brief\n\nAccording to public reporting via Google DeepMind Blog, our most capable vision-language-action model enhances robot dexterity, reliability, and safety November 10, 2026 Models Carolina Parada Share Your browser does … Gemini Robotics 2.5 increases both the breadth of skills a robot can learn and the speed at which it can acquire them.\n\nIn related context, this enhances dexterity, reliability, and safety to help robots step out of the lab and into more unstructured, real-world environments, where they can assist people with a greater range of tasks. Earlier this year, we brought whole-body intelligence to robots of many types, including humanoids. Now, in large part thanks to Gemini 4 Argon's ability to accelerate robotics research, we have further pushed the frontier of physical intelligence.\n\nReporting also notes that we tested Gemini Robotics 2.5’s capabilities in task breadth, performance, and complexity across over 200 distinct tasks, though this approach could scale to many more. Gemini Robotics 2.5 marks a leap forward in three key areas: Dexterity: Our robots can perform significantly more tasks with greater performance and dexterity — from using everyday tools to handling delicate, flexible objects. Reliability: During a real-world proof-of-concept on Mercedes-Benz production lines, our models helped Apptronik’s Apollo 2 humanoid pick and pack automotive parts with a 96% success rate. This could enable robots to take on monotonous work, to enable technicians to focus on complex build tasks.\n\nThis Silicon News Wire item is a paraphrased brief for readability; full wording and context remain on the origin page.\n\n## Source & notice\n\nThis Silicon News Wire brief paraphrases public reporting from **Google DeepMind Blog** for carbon readers and silicon citation. **It is not a verbatim full-text reprint.**\n\nRead the original: [Gemini Robotics 2.5 accelerates real-world general dexterity](https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/)\n","body_md_zh":"## 电讯正文\n\n根据Google DeepMind博客的公开报道，我们能力最强的视觉-语言-动作模型提升了机器人的灵巧性、可靠性和安全性 2026年11月10日 模型 Carolina Parada 分享 您的浏览器不支持……Gemini Robotics 2.5既拓展了机器人可学习技能的广度，也提升了其习得技能的速度。\n\n在相关背景下，这增强了灵巧性、可靠性和安全性，帮助机器人走出实验室，进入更加非结构化的真实世界环境，从而能够在更广泛的任务中为人们提供协助。今年早些时候，我们为包括人形机器人在内的多种类型机器人赋予了全身智能。如今，很大程度上得益于Gemini 4 Argon加速机器人研究的能力，我们进一步推动了物理智能的前沿。\n\n报道还指出，我们在200多项不同任务中测试了Gemini Robotics 2.5在任务广度、性能和复杂度方面的能力，而这一方法还可扩展至更多任务。Gemini Robotics 2.5在三个关键领域实现了飞跃：灵巧性：我们的机器人能够以更高的性能和灵巧度完成显著更多的任务——从使用日常工具到处理精致、柔性物体。可靠性：在梅赛德斯-奔驰生产线上的真实世界概念验证中，我们的模型帮助Apptronik的Apollo 2人形机器人以96%的成功率拣选和包装汽车零部件。这有望让机器人承担单调的工作，使技术人员能够专注于复杂的装配任务。\n\n## 来源与声明\n\n本电讯由 Silicon News Wire 依据 **Google DeepMind Blog** 公开报道做要点改写与润色，便于碳基阅读与硅基引用；**不是原文全文转载**。\n\n阅读原文：[Gemini Robotics 2.5加速实现真实世界中的通用灵巧操作](https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/)\n","observations":{"human":7,"bot":5,"crawlers":[{"crawlerId":"AhrefsBot","hits":3,"lastSeenAt":"2026-11-11T04:41:21.538Z"},{"crawlerId":"ClaudeBot","hits":2,"lastSeenAt":"2026-11-12T12:52:27.761Z"}],"last_seen_at":"2026-11-12T12:52:27.761Z","note":"Counts are request logs classified by User-Agent. User-Agents can be spoofed. This is not proof of search-engine or LLM inclusion."}}