https://rocpai-forge.github.io/en/tags/vla/Recent content in VLA on rocPAI-ForgeHugoenTue, 30 Jun 2026 00:00:00 +0000https://rocpai-forge.github.io/en/posts/openarm-traj-gen/Tue, 30 Jun 2026 00:00:00 +0000https://rocpai-forge.github.io/en/posts/openarm-traj-gen/<blockquote> <p>📖 This is the <strong>concise version</strong> (~3 min). For the full engineering details (design decisions, algorithm / reward, diagnostics, reproduce commands), read the <a href="https://github.com/rocPAI-Forge/tech-blog-pub/blob/main/PhysicalAI/openarm-traj-gen-for-vla/README-details.md"><strong>deep-dive →</strong></a></p></blockquote> <h2 id="overview">Overview</h2> <p>VLA (Vision-Language-Action) models are data-hungry, and real-robot collection is slow and expensive. So we flip it: on an <strong>AMD Instinct MI300X + ROCm</strong> box, we turn OpenArm&rsquo;s pick-and-place into an in-sim <strong>expert trajectory data engine</strong> with <a href="https://github.com/alexhegit/openarm_mp_labs"><code>openarm_mp_labs</code></a> — given an object and a grasp pose, auto-solve a smooth, physically feasible, sub-mm-accurate demonstration trajectory that&rsquo;s reproducible at scale.</p>