发表机构
Harvard University（哈佛大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出World Action Planner机器人规划系统，结合VLMs与多任务位姿图像条件世界模型，可迭代优化动作规划，在组合任务、新布局等场景中泛化性能优于VLAs、WAMs等端到端策略模型。
AI 中文摘要
构建适用于多样应用的通用智能体仍是一项基础挑战。基于模仿学习的策略虽能在特定训练环境中取得成功，但往往无法泛化到新场景和新任务中。本研究提出World Action Planner，这是一种机器人规划系统，它利用视觉语言模型（VLMs）的推理能力以及多任务位姿图像条件世界模型的物理接地性。该系统使智能体能够提出初始动作规划，并通过优化和搜索迭代细化这些规划，同时基于想象中的世界模型回滚进行推理。我们证明，该方法在组合任务、新布局和零样本泛化场景中均取得了优异性能，显著优于VLAs和WAMs等最先进的端到端策略模型。项目网站为this http URL。
英文摘要
Building generalizable robot agents for diverse applications remains a fundamental challenge. While imitation learning-based policies can perform well in familiar training environments, they often struggle to generalize to novel scenes, layouts, and task compositions. To this end, we present World Action Planner, an agentic robot planning system in which the agent searches for and composes executable action plans through imagination with an action-conditioned world model. The search proceeds in a coarse-to-fine manner. First, the agent performs global action optimization by reasoning over imagined world-model rollouts to identify potential failures and refine the proposed action plan. It then performs local action search, comparing the imagined future outcomes of neighboring candidates to select the best action for execution. Across compositional long-horizon tasks, novel object layouts, and real-robot planning on novel tasks without expert demonstrations, World Action Planner consistently outperforms state-of-the-art end-to-end generalist policy models and VLM planners, demonstrating the effectiveness of world-model-based action search for generalizable robot decision making. Qualitative results and videos are available at https://worldactionplanner.github.io/
CommentsProject page at worldactionplanner.github.io
