Goal2Skill：基于自适应规划与反思的长时程操作
Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
AI总结：
本文提出双系统框架，通过分离高层语义推理与低层运动执行，提升长时程操作的鲁棒性和适应性，实验表明其在RMBench任务中显著优于基线方法。
摘要：
近期的视觉-语言-动作（VLA）系统在具身操作中表现出色，但现有VLA策略依赖有限的观察窗口和端到端动作预测，难以应对长时程、依赖记忆的任务中的部分可观察性、遮挡和多阶段依赖。此类任务不仅需要精确的视觉-运动控制，还需持久的记忆、自适应任务分解和执行失败的显式恢复。为解决这些限制，我们提出了一种双系统框架用于长时程具身操作。该框架明确分离高层语义推理与低层运动执行。高层规划器以基于VLM的代理模块实现，维护结构化任务记忆并执行目标分解、结果验证和误差驱动修正。低层执行器以基于VLA的视觉-运动控制器实现，通过扩散基动作生成执行每个子任务，条件于几何保持过滤观测。两者共同形成规划与执行之间的闭环，实现记忆感知推理、自适应重规划和鲁棒在线恢复。在代表性RMBench任务上的实验表明，所提框架显著优于代表性基线，平均成功率为32.4%，远高于最强基线的9.8%。消融研究进一步证实了结构化记忆和闭环恢复对长时程操作的重要性。
英文摘要：
Recent vision-language-action (VLA) systems have demonstrated strong capabilities in embodied manipulation. However, most existing VLA policies rely on limited observation windows and end-to-end action prediction, which makes them brittle in long-horizon, memory-dependent tasks with partial observability, occlusions, and multi-stage dependencies. Such tasks require not only precise visuomotor control, but also persistent memory, adaptive task decomposition, and explicit recovery from execution failures. To address these limitations, we propose a dual-system framework for long-horizon embodied manipulation. Our framework explicitly separates high-level semantic reasoning from low-level motor execution. A high-level planner, implemented as a VLM-based agentic module, maintains structured task memory and performs goal decomposition, outcome verification, and error-driven correction. A low-level executor, instantiated as a VLA-based visuomotor controller, carries out each sub-task through diffusion-based action generation conditioned on geometry-preserving filtered observations. Together, the two systems form a closed loop between planning and execution, enabling memory-aware reasoning, adaptive replanning, and robust online recovery. Experiments on representative RMBench tasks show that the proposed framework substantially outperforms representative baselines, achieving a 32.4% average success rate compared with 9.8% for the strongest baseline. Ablation studies further confirm the importance of structured memory and closed-loop recovery for long-horizon manipulation.
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。
