<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>LeRobot on rocPAI-Forge</title><link>https://rocpai-forge.github.io/en/tags/lerobot/</link><description>Recent content in LeRobot on rocPAI-Forge</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 15 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://rocpai-forge.github.io/en/tags/lerobot/index.xml" rel="self" type="application/rss+xml"/><item><title>Closing the Loop: SO-101 SimStudio Lab 01 Pick-and-Place on ROCm</title><link>https://rocpai-forge.github.io/en/posts/so101-simstudio-lab01/</link><pubDate>Sat, 15 Aug 2026 00:00:00 +0000</pubDate><guid>https://rocpai-forge.github.io/en/posts/so101-simstudio-lab01/</guid><description>&lt;blockquote>
&lt;p>📖 This is the &lt;strong>concise version&lt;/strong> (~3 min). For the full engineering details (design decisions, algorithm / reward, diagnostics, reproduce commands), read the &lt;a href="https://github.com/rocPAI-Forge/tech-blog-pub/blob/main/PhysicalAI/so101-simstudio-lab01-pnp/README-details.md">&lt;strong>deep-dive →&lt;/strong>&lt;/a>&lt;/p>&lt;/blockquote>
&lt;h2 id="from-can-record-to-can-train--eval">From “can record” to “can train &amp;amp; eval”&lt;/h2>
&lt;p>The &lt;a href="../so101-simstudio/README.md">intro post&lt;/a> wired SO-101, MuJoCo, and LeRobot on &lt;strong>AMD ROCm&lt;/strong> so you can &lt;strong>teleoperate in sim and collect expert trajectories&lt;/strong>.&lt;/p>
&lt;p>&lt;strong>v0.1.3&lt;/strong> (&lt;a href="https://github.com/rocPAI-Forge/so101-simstudio/releases/tag/release-v0.1.3">&lt;code>release-v0.1.3&lt;/code>&lt;/a>) closes the next loop — &lt;strong>Lab 01 pick-and-place&lt;/strong>: sim demos → ACT / SmolVLA training → MuJoCo closed-loop eval, plus downloadable Hub reference assets.&lt;/p></description></item><item><title>SO-101 SimStudio: Opening the Door to Robot Physical AI on AMD ROCm</title><link>https://rocpai-forge.github.io/en/posts/so101-simstudio/</link><pubDate>Thu, 16 Jul 2026 00:00:00 +0000</pubDate><guid>https://rocpai-forge.github.io/en/posts/so101-simstudio/</guid><description>&lt;p>&lt;video src="https://rocpai-forge.github.io/media/so101-simstudio/hero-intro_web.mp4" poster="/media/so101-simstudio/hero-intro.jpg" autoplay loop muted playsinline style="width:100%;max-width:100%;border-radius:.6rem;display:block;margin:0 auto;">&lt;/video>&lt;p style="text-align:center;color:#888;font-size:.8rem;margin:.25rem 0 0;">SO-101 SimStudio 项目介绍 / Project intro&lt;/p>&lt;/p>
&lt;blockquote>
&lt;p>📖 This is the &lt;strong>concise version&lt;/strong> (~3 min). For the full engineering details (design decisions, algorithm / reward, diagnostics, reproduce commands), read the &lt;a href="https://github.com/rocPAI-Forge/tech-blog-pub/blob/main/PhysicalAI/so101-simstudio/README-details.md">&lt;strong>deep-dive →&lt;/strong>&lt;/a>&lt;/p>&lt;/blockquote>
&lt;h2 id="why-this-project">Why this project&lt;/h2>
&lt;p>Like many in this community, I started my physical-AI and robotics journey with &lt;strong>SO-101&lt;/strong> and &lt;a href="https://github.com/huggingface/lerobot">&lt;strong>LeRobot&lt;/strong>&lt;/a> — an excellent on-ramp: open hardware, an active community, and a clear dataset format that gets you moving quickly.&lt;/p></description></item></channel></rss>