基于对象中心表征的泛化分层技能学习
Generalizable Hierarchical Skill Learning via Object-Centric Representation
AI总结：
提出GSL框架，通过对象中心技能连接高层VLM与低层策略，分解演示为可迁移技能原语，显著提升机器人操作的泛化与样本效率，仿真和真实实验中均以极少数据超越基线。
摘要：
我们提出了泛化分层技能学习（GSL），一种用于分层策略学习的新框架，显著提升了机器人操作中策略的泛化能力和样本效率。GSL的核心思想之一是使用对象中心技能作为接口，连接高层视觉-语言模型与低层视觉-运动策略。具体而言，GSL利用基础模型将演示分解为可迁移且对象规范化的技能原语，确保在对象坐标系中进行高效的低层技能学习。在测试时，高层智能体预测的技能-对象对输入低层模块，其中推断出的规范化动作被映射回世界坐标系以执行。这种结构化且灵活的设计使我们的方法在未见过的空间布局、对象外观和任务组合上，样本效率和泛化能力得到显著提升。在仿真中，每个任务仅使用3个演示训练的GSL，在未见任务上比使用30倍数据训练的基线高出15.5%。在真实世界实验中，GSL也超越了使用10倍数据训练的基线。
英文摘要：
We present Generalizable Hierarchical Skill Learning (GSL), a novel framework for hierarchical policy learning that significantly improves policy generalization and sample efficiency in robot manipulation. One core idea of GSL is to use object-centric skills as an interface that bridges the high-level vision-language model and the low-level visual-motor policy. Specifically, GSL decomposes demonstrations into transferable and object-canonicalized skill primitives using foundation models, ensuring efficient low-level skill learning in the object frame. At test time, the skill-object pairs predicted by the high-level agent are fed to the low-level module, where the inferred canonical actions are mapped back to the world frame for execution. This structured yet flexible design leads to substantial improvements in sample efficiency and generalization of our method across unseen spatial arrangements, object appearances, and task compositions. In simulation, GSL trained with only 3 demonstrations per task outperforms baselines trained with 30 times more data by 15.5 percent on unseen tasks. In real-world experiments, GSL also surpasses the baseline trained with 10 times more data.
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。
