用分层框架让机器人完成复杂多步骤操作任务
Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks
- 高阶世界模型规划可行子目标，低阶扩散策略执行动作
- 在多个基准上表现优于现有方法，实现稳定多阶段控制
- 基于物体中心表征，支持对每个物体独立规划
视觉世界模型在学习复杂系统动态方面展现出巨大潜力。近期进展将其作为模型预测控制（MPC）中的转移函数来解决各类控制任务。然而，在机器人应用中，这些方法仅限于单阶段任务（如抓取或到达），难以应对需要复杂序列规划的多阶段任务。本文提出WorldDP，一种面向多阶段机器人操作的世界模型框架。该框架采用分层结构：高阶世界模型作为转移函数，在运行时优化可行子目标；随后由低阶扩散策略执行具体动作。为提升动态学习与规划能力，引入物体中心表示，解耦环境实体，实现针对每个物体的顺序规划。在多个机器人基准测试中，WorldDP持续优于现有基线，验证了将物理合理规划与高效执行结合能显著提升多阶段性能。
原文摘要 · Abstract (English)
Visual world models have shown great potential in learning complex system dynamics. Recent advancements leverage these models as transition functions within Model Predictive Control (MPC) frameworks to solve various control tasks. When applied to robotics, however, they are limited to single-stage tasks such as reaching or grasping, and struggle with multi-stage ones that demand complex sequential planning. In this work, we introduce WorldDP, a world model framework designed for multi-stage robotic manipulation. Our hierarchical approach utilizes a high-level world model as a transition function to optimize for feasible subgoals during runtime, which are subsequently reached by a low-level Diffusion Policy. To further aid in learning dynamics and planning, we incorporate object-centric representations that decouple environmental entities and enable us to plan sequentially with respect to each. Evaluated across several robotics benchmarks, WorldDP consistently outperforms existing baselines, validating that coupling the world model's physically grounded planning with diffusion policy's efficient execution yields superior multi-stage performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。