<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Sim-to-Real on WorldSense Tech Blog</title><link>https://worldsensetech.com/en/tags/sim-to-real/</link><description>Recent content in Sim-to-Real on WorldSense Tech Blog</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sat, 08 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://worldsensetech.com/en/tags/sim-to-real/index.xml" rel="self" type="application/rss+xml"/><item><title>Domain Randomization: The Bridge from Simulation to Reality</title><link>https://worldsensetech.com/en/articles/domain-randomization-sim-to-real/</link><pubDate>Sat, 08 Aug 2026 00:00:00 +0000</pubDate><guid>https://worldsensetech.com/en/articles/domain-randomization-sim-to-real/</guid><description>&lt;p&gt;In the previous post, we discussed how TD-MPC uses world models for robot control. But whether you&amp;rsquo;re using Dreamer, TD-MPC, or any other method, the learned policy ultimately needs to be deployed on a real robot. This inevitably leads to Sim-to-Real transfer — and Domain Randomization is the most fundamental technique on this path.&lt;/p&gt;
&lt;p&gt;This article systematically breaks down domain randomization: what problem it solves, what types exist, how to implement it in engineering, and the latest advances.&lt;/p&gt;</description></item><item><title>Is Sim-to-Real Too Hard? World Model-Driven Adaptive Transfer Methods</title><link>https://worldsensetech.com/en/articles/sim-to-real-transfer/</link><pubDate>Wed, 05 Aug 2026 00:00:00 +0000</pubDate><guid>https://worldsensetech.com/en/articles/sim-to-real-transfer/</guid><description>&lt;p&gt;This is the fourth article in the World Models series. The first three covered the basic concepts of world models, the core principles of RSSM, and an introduction to embodied AI. Today, we&amp;rsquo;re diving into a more practical topic: how do we actually deploy policies trained in simulation onto real robots?&lt;/p&gt;
&lt;p&gt;This problem has plagued the robotics AI field for nearly a decade. World models perform brilliantly in simulated environments — DreamerV3&amp;rsquo;s sample efficiency is 10-100x higher than traditional RL. But once deployed on real robots, performance often drops by 30-50%. This gap is the famous &amp;ldquo;Sim-to-Real Gap&amp;rdquo;.&lt;/p&gt;</description></item><item><title>Embodied AI in 2026: What Breakthroughs Can We Expect?</title><link>https://worldsensetech.com/en/articles/embodied-ai-2026-breakthrough/</link><pubDate>Mon, 03 Aug 2026 00:00:00 +0000</pubDate><guid>https://worldsensetech.com/en/articles/embodied-ai-2026-breakthrough/</guid><description>&lt;p&gt;Embodied AI has clearly accelerated in 2025. Humanoid robot companies are clustering around funding rounds, large model providers are aggressively moving into robotics, and governments worldwide have listed embodied AI as a strategic priority. Standing at the threshold of 2026, I see several directions poised for substantive breakthroughs.&lt;/p&gt;
&lt;h2 id="breakthrough-1-world-models--from-imagination-to-decision-making"&gt;Breakthrough 1: World Models — From &amp;ldquo;Imagination&amp;rdquo; to &amp;ldquo;Decision-Making&amp;rdquo;&lt;/h2&gt;
&lt;p&gt;In 2023–2024, DreamerV3 demonstrated that world models could efficiently train policies in simulation. But those world models were more like &amp;ldquo;environment simulators&amp;rdquo; — they could predict what would happen next, yet there was still a gap between prediction and actual decision-making.&lt;/p&gt;</description></item><item><title>World Models: 8 Years and the Same Bottleneck</title><link>https://worldsensetech.com/en/articles/world-model-8year-bottleneck/</link><pubDate>Mon, 03 Aug 2026 00:00:00 +0000</pubDate><guid>https://worldsensetech.com/en/articles/world-model-8year-bottleneck/</guid><description>&lt;p&gt;After working in the world models direction for over half a year, my biggest takeaway is this: there are plenty of papers, but very few that truly land in practice. Recently I read a 2026 survey from the Chinese Academy of Sciences and several universities that does an excellent job of mapping out eight years of progress. Drawing on my own hands-on experience, I want to discuss a few bottlenecks that still haven&amp;rsquo;t been fundamentally broken.&lt;/p&gt;</description></item></channel></rss>