产品美国

谷歌Gemini Robotics 2.5在奔驰产线配料任务成功率达96%

发布 阅读约 1 分钟
原文

谷歌DeepMind于11月10日发布视觉语言动作模型Gemini Robotics 2.5,称在200多项任务中成功率较前代提高30%至100%,速度快20%至30%。在梅赛德斯-奔驰匈牙利凯奇凯梅特和德国辛德尔芬根产线上,搭载该模型的Apptronik人形机器人Apollo 2完成金属支架配料,成功率96%。

谷歌DeepMind于11月10日在博客中称,Gemini Robotics 2.5是其迄今能力最强的视觉语言动作(VLA)模型。在200多项任务测试中,成功率按任务类型提高30%至100%,完成速度加快20%至30%。模型先向机器人合作伙伴开放,未公布公开API。

产线上的96%

在梅赛德斯-奔驰位于匈牙利凯奇凯梅特和德国辛德尔芬根的在产线上,Apptronik的Apollo 2人形机器人运行该模型执行配料任务,把散装料箱中的金属支架按顺序放入托盘,成功率96%。机器人使用22个自由度的五指SharpaWave灵巧手。博客未披露试点时长和尝试次数。

Gemini Robotics 2与2.5分任务成功率
  • 用夹子装糕点
    2
    5%
    2.5
    100%
  • 合上工具箱盖
    2
    0%
    2.5
    93%
  • 取下挂杯放到桌上
    2
    29%
    2.5
    75%
  • 解开丝带结
    2
    0%
    2.5
    70%
  • 挂开衫
    2
    0%
    2.5
    62%
  • 扫垃圾入簸箕
    2
    0%
    2.5
    52%
  • 打包电饭煲
    2
    0%
    2.5
    40%
  • 叠裤子
    2
    0%
    2.5
    40%
  • 简单平均
    2
    4.3%
    2.5
    66.5%

DeepMind博客图表数据,平均值为MEKAWIRE计算。

截至 2026年11月14日

按DeepMind图表中的8项任务计算,简单平均成功率从4.3%升至66.5%(MEKAWIRE计算),但叠裤子和打包电饭煲仍只有40%。

MEKAWIRE 分析

DeepMind的竞争点已从演示转向产线成功率。

优必选Walker S系列此前在比亚迪、吉利等车厂实训,但很少公布逐项成功率;DeepMind这次给出了车厂产线数据,抬高了行业披露标准。反方观点是,缺少尝试次数和节拍,96%难以与传统自动化对比。

这条消息是利好还是利空?

 

要点
发布
2026年11月10日
奔驰试点
配料成功率96%,Apollo 2
工厂
凯奇凯梅特和辛德尔芬根
提升
成功率高30%至100%,快20%至30%
测试任务
200多项
8项任务平均
4.3%升至66.5%(MEKAWIRE计算)
安全
Gemini 4 Argon越狱抵抗99.5%,ER 2为82%
开放范围
仅限机器人合作伙伴
来源
MEKAWIRE 情报版
  1. 01

    为何重要

    The reported 96% kitting success puts Gemini Robotics 2.5 and Apollo 2 into a specific automotive production workflow at two Mercedes-Benz plants. DeepMind also reports 30% to 100% higher task success and 20% to 30% faster execution than its predecessor across more than 200 tasks. Sample size, intervention rates and production economics are missing, so the pilot does not establish readiness for broader deployment.

  2. 02

    竞争对手分析

    Agile Robots offers factory automation hardware and AI software, with Audi among its listed customers; its subsidiary Franka supplies torque-sensing arms. Sharpa focuses on tactile hands, haptic gloves and manipulation robots, making dexterity components another relevant competitive axis. No comparable kitting benchmarks or deployment economics are supplied, so these companies cannot be ranked against Apollo 2 on performance or cost.

  3. 03

    估值背景

    Agile Robots has a disclosed $8.5B valuation and $720M in reported funding, including a $500M Series F announced Nov 12. Apptronik's reported $1.25B total funding is capital raised, not a valuation; no valuation is supplied. DeepMind is an Alphabet subsidiary with no standalone valuation supplied, and the input provides no market capitalization figures.

  4. 04

    研究依据

    DeepMind's listed papers include Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical Grounding. Franka's list includes FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs. Only titles are supplied, so neither paper establishes the cause of the reported gains or validates the Mercedes-Benz result.

  5. 05

    供应链影响

    The pilot combines DeepMind's model, Apptronik's Apollo 2 hardware and Mercedes-Benz production sites. Partner-only model access makes access terms and integration support relevant deployment dependencies. Component suppliers, manufacturing capacity, hardware prices and service arrangements are not supplied, leaving scaling costs and bottlenecks unresolved.

  6. 06

    后续看点

    Watch for paid deployments beyond the two pilot plants, repeatable success across shifts and disclosed human intervention rates. Cycle times, uptime and cost per completed kit would make the performance claims commercially assessable. The reported 99.5% jailbreak resistance for Gemini 4 Argon does not establish physical safety; the input supplies no physical safety validation.

  7. 07

    分析师观点

    The pilot is a concrete signal of industrial applicability, but the investment case depends on sustained throughput and support costs. Partner-only access makes commercial terms and partner expansion important indicators of adoption. The supplied evidence supports monitoring deployment conversion, while revenue, margins and customer commitments remain undisclosed.

  8. 08

    值得追问的问题

    How many kitting attempts underpin the 96% success rate, and what human assistance or recovery was required? What are cycle time, uptime and total cost per completed kit against Mercedes-Benz's existing process? What commitments, access terms and physical safety requirements govern expansion beyond the pilot?