MetaWorld-X: 通过VLM协调的专家实现人形机器人的分层世界建模
MetaWorld-X: Hierarchical World Modeling via VLM-Orchestrated Experts for Humanoid Loco-Manipulation
AI总结：
MetaWorld-X通过VLM协调的专家实现人形机器人分层世界建模，解决loco-manipulation任务中的控制策略泛化问题。
摘要：
学习自然、稳定且具有组成通用性的全身控制策略，以使人形机器人同时进行运动和操作（loco-manipulation）仍然是机器人学中的基本挑战。现有的强化学习方法通常依赖于单一的单一策略来获取多种技能，这往往导致在高自由度系统中出现跨技能梯度干扰和运动模式冲突。因此，生成的行为经常表现出不自然的运动、有限的稳定性以及在复杂任务组合中的较差泛化能力。为了解决这些限制，我们提出了MetaWorld-X，一种用于人形控制的分层世界模型框架。受分而治之的原则引导，我们的方法将复杂的控制问题分解为一组专门的专家策略（Specialized Expert Policies，SEP）。每个专家通过模仿约束的强化学习在人类运动先验下进行训练，引入了生物力学一致的归纳偏差，确保自然且物理上合理的运动生成。在此基础上，我们进一步开发了由视觉语言模型（VLM）监督的智能路由机制（IRM），实现语义驱动的专家组合。VLM引导的路由器根据高层任务语义动态整合专家策略，促进在多阶段loco-manipulation任务中的组成泛化和自适应执行。
英文摘要：
Learning natural, stable, and compositionally generalizable whole-body control policies for humanoid robots performing simultaneous locomotion and manipulation (loco-manipulation) remains a fundamental challenge in robotics. Existing reinforcement learning approaches typically rely on a single monolithic policy to acquire multiple skills, which often leads to cross-skill gradient interference and motion pattern conflicts in high-degree-of-freedom systems. As a result, generated behaviors frequently exhibit unnatural movements, limited stability, and poor generalization to complex task compositions. To address these limitations, we propose MetaWorld-X, a hierarchical world model framework for humanoid control. Guided by a divide-and-conquer principle, our method decomposes complex control problems into a set of specialized expert policies (Specialized Expert Policies, SEP). Each expert is trained under human motion priors through imitation-constrained reinforcement learning, introducing biomechanically consistent inductive biases that ensure natural and physically plausible motion generation. Building upon this foundation, we further develop an Intelligent Routing Mechanism (IRM) supervised by a Vision-Language Model (VLM), enabling semantic-driven expert composition. The VLM-guided router dynamically integrates expert policies according to high-level task semantics, facilitating compositional generalization and adaptive execution in multi-stage loco-manipulation tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
