---
格式版本: 2
标题: "Amazon Devices & Services Achieves Major Step Toward Zero-Touch Manufacturing With NVIDIA AI and Digital Twins | NVIDIA Blog"
原文链接: "https://blogs.nvidia.com/blog/amazon-zero-touch-manufacturing/"
发布日期: "2026-06-30"
发布时间校准状态: "found"
发布时间来源: "llm:strict_original_body"
发布时间证据: "time class=related-news-date nvidia-article-date datetime=2026-06-30T08:00:57-07:00: Jun 30, 2026"
发布时间校准原因: "该日期位于标题下方，且带有 nvidia-article-date 语义标签，符合文章发布时间特征。"
发布时间校准置信度: "1"
发布时间候选数量: 32
发布时间严格候选数量: 12
发布时间原页读取状态: "原页面来自已抓取 HTML"
发布时间未找到原因: "候选日期无效或 LLM 未确认"
发布时间校准时间: "2026-07-20T11:06:40+08:00"
发现时间: "2026-07-20T09:24:38+08:00"
入库时间: "2026-07-20T03:09:15.044Z"
来源平台: "NVIDIA Blog 搜索"
搜索渠道: "source_template"
搜索词: "https://blogs.nvidia.com/?s=NPO"
匹配关键词:
  - "NPO"
相关厂家:
  - "NVIDIA"
  - "AWS"
相关专家:
  []
内容类型: "网页"
抓取工具: "AgentKey Scrape"
清洗工具: "AgentKey Markdown + LLM 正文裁剪"
原始附件:
  []
AI优质: "否"
AI打分: 32
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "正文主要讨论亚马逊设备与服务部门利用NVIDIA数字孪生和AI技术实现零接触制造，涉及机器人手臂训练、合成数据生成和缺陷检测，与超节点/AI Rack/机柜级AI基础设施、关键部件或系统架构无直接关联。"
AI质检模型: "qwen3.6-plus"
AI质检时间: "2026-07-20T11:09:15+08:00"
AI主题相关性: 5
AI来源权威性: 12
AI新颖性: 10
AI技术细节: 5
AI商业部署信号: 0
AI完整性: 0
图片摘要:
  - "✓ ./assets/img-e9a842cf.jpg | photo | 展示Amazon Devices真实机械臂工作站（左）与NVIDIA数字孪生模拟工作站（右）的对比，验证Sim-to-Real技术。"
  - "✗ ./assets/img-83d2f103.jpg | other | 图片标题涉及AI基础设施能效，与正文Amazon制造主题无关，疑似相关文章推荐图。"
  - "✗ ./assets/img-1f6575f1.png | diagram | 图片标题涉及NVIDIA Vera CPU架构，与正文Amazon制造主题无关，疑似相关文章推荐图。"
  - "✗ ./assets/img-3511966c.jpg | photo | 图片为NVIDIA园区照片，标题涉及AI计算扩展，与正文Amazon制造主题无关，疑似相关文章推荐图。"
  - "✗ ./assets/img-e47e99dc.png | other | 图片标题涉及推理软件栈和Token成本，与正文Amazon制造主题无关，疑似相关文章推荐图。"
采集批次: "2026年7月20日9点23分34秒"
采集批次ID: "20260720-092334-062"
去重键: "https://blogs.nvidia.com/blog/amazon-zero-touch-manufacturing"
---

Using NVIDIA [digital twin](https://www.nvidia.com/en-us/glossary/digital-twin/) technologies, Amazon Devices & Services is powering big leaps in manufacturing with a new [physical AI](https://www.nvidia.com/en-us/glossary/generative-physical-ai/) software solution.

Deployed this month at an Amazon Devices facility, the company’s innovative, simulation-first approach for zero-touch manufacturing trains robotic arms to inspect diverse devices for product-quality auditing and integrate new goods into the production line — all based on [synthetic data](https://www.nvidia.com/en-us/glossary/synthetic-data-generation/), without requiring hardware changes.

This new technology brings together Amazon Devices-created software that simulates processes on the assembly line with products in NVIDIA-powered digital twins. Using a modular, AI-powered workflow, the technology offers faster, more efficient inspections compared with the previously used audit machinery.

Simulating [processes and products in digital twins](https://www.nvidia.com/en-us/use-cases/industrial-facility-digital-twins/) eliminates the need for expensive, time-consuming physical prototyping. This eases manufacturer workflows and reduces the time it takes to get new products into consumers’ hands.

To enable zero-shot manufacturing for the robotic operations, the solution uses photorealistic, physics-enabled representations of Amazon devices and factory work stations to generate synthetic data. This factory-specific data is then used to enhance AI model performance in both simulation and at the real work station, minimizing the simulation-to-real gap before deployment.

It’s a huge step toward generalized manufacturing: the use of automated systems and technologies to flexibly handle a wide variety of products and production processes — even without physical prototypes.

YouTube

## AI, Digital Twins for Robot Understanding

By training robots in digital twins to recognize and handle new devices, Amazon Devices & Services is equipped to build faster, more modular and easily controllable manufacturing pipelines, allowing lines to change from auditing one product to another simply via software.

Robotic actions can be configured to manufacture products purely based on training performed in simulation — including for steps involved in assembly, testing, packaging and auditing.

A suite of [NVIDIA Isaac](https://developer.nvidia.com/isaac) technologies enables Amazon Devices & Services physically accurate, simulation-first approach.

When a new device is introduced, Amazon Devices & Services puts its computer-aided design (CAD) model into [NVIDIA Isaac Sim](https://developer.nvidia.com/isaac/sim), an open-source, [robotics simulation](https://www.nvidia.com/en-us/use-cases/robotics-simulation/) reference application built on the [NVIDIA Omniverse](https://www.nvidia.com/en-us/omniverse/) platform.

NVIDIA Isaac is used to generate over 50,000 diverse, synthetic images from the CAD models for each device, crucial for training object- and defect-detection models.

Then, Isaac Sim processes the data and taps into [NVIDIA Isaac ROS](https://developer.nvidia.com/isaac/ros) to generate robotic arm trajectories for handling the product.

![The robot is trained purely on synthetic data and can pick up packages and products of different shapes and sizes to perform cosmetic inspection. Real station (left) and simulated station (right). Image courtesy of Amazon Devices & Services.](./assets/img-e9a842cf.jpg)

The robot is trained purely on synthetic data and can pick up packages and products of different shapes and sizes to perform cosmetic inspection. Real station (left) and simulated station (right). Image courtesy of Amazon Devices & Services.

The development of this technology was significantly accelerated by AWS through distributed AI model training on Amazon devices’ product specifications using Amazon EC2 G6 instances via AWS Batch, as well as NVIDIA Isaac Sim physics-based simulation and synthetic data generation on Amazon EC2 G6 family instances.

The solution uses Amazon Bedrock — a service for building generative AI applications and agents — to plan high-level tasks and specific audit test cases at the factory based on analyses of product-specification documents. Amazon Bedrock AgentCore will be used for autonomous-workflow planning for multiple factory stations on the production line, with the ability to ingest multimodal product-specification inputs such as 3D designs and surface properties.

To help robots understand their environment, the solution uses [NVIDIA cuMotion](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_cumotion), a CUDA-accelerated motion-planning library that can generate collision-free trajectories in a fraction of a second on the [NVIDIA Jetson AGX Orin](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/) module. The [nvblox](https://github.com/nvidia-isaac/nvblox) library, part of Isaac ROS, generates distance fields that cuMotion uses for collision-free trajectory planning.

[FoundationPose](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/isaac/models/foundationpose), an NVIDIA foundation model trained on 5 million synthetic images for pose estimation and object tracking, helps ensure the Amazon Devices & Services robots know the accurate position and orientation of the devices.

Crucial for the new manufacturing solution, FoundationPose can generalize to entirely new objects without prior exposure, allowing seamless transitions between different products and eliminating the need to collect new data to retrain models for each change.

As part of product auditing, the new solution’s approach is used for defect detection on the manufacturing line. Its modular design allows for future integration of advanced reasoning models like [NVIDIA Cosmos Reason](https://developer.nvidia.com/cosmos).

*Watch the* [*NVIDIA Research special address at SIGGRAPH*](https://www.youtube.com/watch?v=rFcmv2pXR0w) *and learn more about how graphics and simulation innovations come together to drive industrial digitalization by joining NVIDIA at the conference, running through Thursday, Aug. 14.*

![The robot is trained purely on synthetic data and can pick up packages and products of different shapes and sizes to perform cosmetic inspection. Real station (left) and simulated station (right). Image courtesy of Amazon Devices & Services.](./assets/img-e9a842cf.jpg)The robot is trained purely on synthetic data and can pick up packages and products of different shapes and sizes to perform cosmetic inspection. Real station (left) and simulated station (right). Image courtesy of Amazon Devices & Services.