发表机构
Tsinghua University; Chinese Academy of Sciences（清华大学; 中国科学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出GraphOp-WM结构化世界模型，通过分解转移为形态无关局部基与形态相关算子，实现连续控制中铰接机器人家族的形态参数泛化，定义MuJoCo参数划分验证方法。
AI 中文摘要
用于连续控制的世界模型通常针对固定物理系统进行训练，当连杆长度、质量、阻尼、致动等已知形态参数发生变化时，模型性能会下降。现有方法常将这些参数作为条件信息提供，但未明确学习到的转移中哪部分应保持可复用、哪部分应随形态变化。我们提出图算子世界模型（GraphOp-WM），这是一种结构化世界模型，用于在相关铰接机器人家族中对未见形态参数进行泛化。GraphOp-WM 将主体及其运动学关系表示为属性图，并将每个转移分解为与形态无关的局部动力学基和与形态相关的结构化算子。该算子结合了节点局部调制、运动学树耦合和低秩全局修正，同时架构信息分离、基归一化和配对形态监督，促使静态形态依赖由算子路径承载。图级读出和逐边动作表示为奖励、价值和 TD-MPC 风格规划提供兼容接口。我们进一步定义了受控 MuJoCo 参数划分，涵盖 Hopper、Walker2d 和 HalfCheetah 中连杆几何、质量、阻尼及致动参数的插值、外推和保留组成部分。
英文摘要
World models for continuous control are commonly trained for a fixed physical system and can degrade when known morphology parameters such as link lengths, masses, damping, and actuation change. Existing approaches often provide these parameters as conditioning information, but leave unspecified which part of the learned transition should remain reusable and which part should change with morphology. We propose Graph-Operator World Models (GraphOp-WM), a structured world model for generalization across unseen morphology parameters within related articulated robot families. GraphOp-WM represents bodies and their kinematic relations as an attributed graph and factorizes each transition into a morphology-independent local dynamics basis and a morphology-conditioned structured operator. The operator combines node-local modulation, kinematic-tree coupling, and a low-rank global correction, while architectural information separation, basis normalization, and paired-morphology supervision encourage static morphology dependence to be carried by the operator pathway. Graph-level readout and edge-wise action representations provide a compatible interface for reward, value, and TD-MPC-style planning. We further define controlled MuJoCo parameter splits covering interpolation, extrapolation, and held-out compositions of link geometry, mass, damping, and actuation parameters in Hopper, Walker2d, and HalfCheetah.
