<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>RobotRove</title><description>Open source humanoid robotics — research papers, community projects, tutorials, and industry news.</description><link>https://robotrove.com/</link><language>en-us</language><item><title>Open Source Is the Best MoAI for Robotics Startups</title><link>https://robotrove.com/blog/open-source-is-the-best-moai-for-robotics-startups/</link><guid isPermaLink="true">https://robotrove.com/blog/open-source-is-the-best-moai-for-robotics-startups/</guid><description>NVIDIA&apos;s Isaac GR00T Reference Robot drops the full stack — hardware, simulation, models, deployment — under open licenses. Here&apos;s why that changes the economics of starting a robotics company.</description><pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate><category>industry-news</category><category>nvidia</category><category>isaac-gr00t</category><category>open-source</category><category>humanoid</category><category>unitree</category><category>startup</category><category>isaac-sim</category><category>isaac-lab</category><category>ros2</category></item><item><title>One Policy, Any Body: How COMPASS Is Making Robot Navigation Truly Portable</title><link>https://robotrove.com/blog/compass-cross-embodiment-navigation/</link><guid isPermaLink="true">https://robotrove.com/blog/compass-cross-embodiment-navigation/</guid><description>NVIDIA&apos;s COMPASS uses residual reinforcement learning and policy distillation to deploy a single navigation policy across wheeled and legged platforms — with zero-shot sim-to-real transfer on the Unitree G1 humanoid.</description><pubDate>Fri, 29 May 2026 00:00:00 GMT</pubDate><category>research-papers</category><category>cross-embodiment</category><category>navigation</category><category>sim-to-real</category><category>unitree-g1</category><category>nvidia</category><category>open-source</category><category>humanoid</category><category>reinforcement-learning</category><category>policy-distillation</category><category>icra-2026</category></item><item><title>Why Robotic Hands Are the Final Frontier in Humanoid Robotics</title><link>https://robotrove.com/blog/why-robotic-hands-are-the-final-frontier/</link><guid isPermaLink="true">https://robotrove.com/blog/why-robotic-hands-are-the-final-frontier/</guid><description>The human hand is a 27-bone masterpiece honed over millions of years of evolution. Replicating it in silicon and steel is why companies are spending decades and billions on a single appendage. Here is why the hand matters, why it is so hard to build, and which open-source projects are democratizing dexterity.</description><pubDate>Thu, 28 May 2026 00:00:00 GMT</pubDate><category>open-source-projects</category><category>robotic-hands</category><category>dexterous-manipulation</category><category>open-source</category><category>humanoid</category><category>tactile-sensing</category><category>ros2</category><category>leap-hand</category><category>allegro-hand</category><category>shadow-robot</category></item><item><title>ROS 2 Lyrical Luth Is Out: What&apos;s New in the Latest LTS</title><link>https://robotrove.com/blog/ros2-lyrical-luth/</link><guid isPermaLink="true">https://robotrove.com/blog/ros2-lyrical-luth/</guid><description>ROS 2 Lyrical Luth is now available as the twelfth ROS 2 release and the latest Long Term Support (LTS) edition, supported until May 2031. Here&apos;s a breakdown of the features that matter most for robotics developers.</description><pubDate>Sun, 24 May 2026 00:00:00 GMT</pubDate><category>industry-news</category><category>ros2</category><category>lyrical-luth</category><category>robotics</category><category>open-source</category><category>lts</category><category>middleware</category></item><item><title>One Brain, Many Bodies: How HEX Is Breaking the Embodiment Barrier in Humanoid Robotics</title><link>https://robotrove.com/blog/hex-cross-embodiment-vla/</link><guid isPermaLink="true">https://robotrove.com/blog/hex-cross-embodiment-vla/</guid><description>HEX is a 2.4B-parameter open-source VLA model pretrained on 12 million frames from seven different humanoid robots — and it controls all of them with a single policy.</description><pubDate>Thu, 21 May 2026 00:00:00 GMT</pubDate><category>research-papers</category><category>vla</category><category>cross-embodiment</category><category>unitree-g1</category><category>unitree-h1</category><category>open-source</category><category>humanoid</category><category>manipulation</category></item><item><title>Open Source Humanoid Robots in 2026: A Field Survey</title><link>https://robotrove.com/blog/open-source-humanoid-robots-2026/</link><guid isPermaLink="true">https://robotrove.com/blog/open-source-humanoid-robots-2026/</guid><description>From Open Duck Mini to Zeroth Bot — a survey of the open source humanoid robot projects you can actually build, study, or contribute to today.</description><pubDate>Thu, 19 Mar 2026 00:00:00 GMT</pubDate><category>open-source-projects</category><category>humanoid</category><category>ros2</category><category>hardware</category><category>community</category></item><item><title>Getting Started with ROS 2 for Humanoid Robotics</title><link>https://robotrove.com/blog/ros2-humanoid-tutorial/</link><guid isPermaLink="true">https://robotrove.com/blog/ros2-humanoid-tutorial/</guid><description>A practical guide to setting up ROS 2 Jazzy for humanoid robot simulation — from installation to your first walking controller in MuJoCo.</description><pubDate>Tue, 10 Mar 2026 00:00:00 GMT</pubDate><category>tutorials</category><category>ros2</category><category>mujoco</category><category>simulation</category><category>python</category></item><item><title>Humanoid Locomotion in 2025: What the Research Says</title><link>https://robotrove.com/blog/humanoid-locomotion-survey-2025/</link><guid isPermaLink="true">https://robotrove.com/blog/humanoid-locomotion-survey-2025/</guid><description>A survey of the most significant papers on bipedal locomotion from 2025 — reinforcement learning, model predictive control, and sim-to-real transfer.</description><pubDate>Thu, 15 Jan 2026 00:00:00 GMT</pubDate><category>research-papers</category><category>locomotion</category><category>reinforcement-learning</category><category>sim-to-real</category><category>mpc</category></item></channel></rss>