
  <rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
      <title>Chaos and Order</title>
      <link>https://www.youngju.dev/blog</link>
      <description>천천히 올바르게. AI Researcher &amp; DevOps Engineer Youngju&#39;s tech blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, distributed training, and data engineering.</description>
      <language>ko</language>
      <managingEditor>fjvbn2003@gmail.com (Youngju Kim)</managingEditor>
      <webMaster>fjvbn2003@gmail.com (Youngju Kim)</webMaster>
      <lastBuildDate>Mon, 29 Jun 2026 00:00:00 GMT</lastBuildDate>
      <atom:link href="https://www.youngju.dev/tags/sim-to-real/feed.xml" rel="self" type="application/rss+xml"/>
      
  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-06-29-sim-to-real-transfer-robotics.en</guid>
    <title>Sim-to-Real — Bringing What Was Learned in Simulation into Reality</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-06-29-sim-to-real-transfer-robotics.en</link>
    <description>An analysis of why robot policies learned in simulation collapse in reality (the reality gap), covering countermeasures such as domain randomization, domain adaptation, system identification, and digital twins, along with hard-to-reproduce physics like tactile sensing and friction, and the promise and limits of zero-shot transfer, illustrated with diagrams and examples.</description>
    <pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>robotics</category><category>sim-to-real</category><category>domain-randomization</category><category>digital-twin</category><category>simulation</category>
  </item>

  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-06-29-sim-to-real-transfer-robotics.ja</guid>
    <title>Sim-to-Real — シミュレーションで学んだことを現実へ</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-06-29-sim-to-real-transfer-robotics.ja</link>
    <description>シミュレーションで学習したロボット方策が現実で崩れる理由(現実ギャップ)を分析し、ドメインランダム化・ドメイン適応・システム同定・デジタルツインといった対応手法、触覚や摩擦など再現が難しい物理、そして zero-shot 転移の可能性と限界を、図と事例で説明します。</description>
    <pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>robotics</category><category>sim-to-real</category><category>domain-randomization</category><category>digital-twin</category><category>simulation</category>
  </item>

  <item>
    <guid>https://www.youngju.dev/blog/ai-papers/2026-06-29-sim-to-real-transfer-robotics</guid>
    <title>Sim-to-Real — 시뮬레이션에서 배운 것을 현실로</title>
    <link>https://www.youngju.dev/blog/ai-papers/2026-06-29-sim-to-real-transfer-robotics</link>
    <description>시뮬레이션에서 학습한 로봇 정책이 현실에서 무너지는 이유(현실 격차)를 분석하고, 도메인 랜덤화·도메인 적응·시스템 식별·디지털 트윈 같은 대응 기법과, 촉각·마찰 등 재현이 어려운 물리, zero-shot 전이의 가능성과 한계를 다이어그램과 사례로 설명합니다.</description>
    <pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate>
    <author>fjvbn2003@gmail.com (Youngju Kim)</author>
    <category>ai-papers</category><category>robotics</category><category>sim-to-real</category><category>domain-randomization</category><category>digital-twin</category><category>simulation</category>
  </item>

    </channel>
  </rss>
