arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.14601cs.RO
收藏

StateSkill-Agent:一种基于状态条件技能的高效具身智能体

StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill

The Hong Kong Polytechnic University(香港理工大学);ACE Robotics(ACE机器人公司);Nanyang Technological University(南洋理工大学);Tsinghua University(清华大学);Zhejiang University(浙江大学);Fudan University(复旦大学)

Changxu Wei, Jingyi Zhang, Zhiyu Zheng, Tianyi Lin, Yixian Zhang, Yunpeng Qing, Jingyuan Liu, Zhi Hou, Jiaxing Huang

AI总结:

本研究提出基于状态条件技能的具身智能体StateSkill-Agent,通过StateSkill技能表示、StateSkill-Evolve进化机制与StateGRPO统一学习循环,在各类具身任务中验证了方法与模型的有效性。

摘要:

本研究旨在开发一种具身多模态大语言模型(MLLM)智能体,该智能体可通过学习、抽象和复用可迁移且可泛化的行为模式来理解并解决具身任务。为此,我们提出了StateSkill,这是一种用于具身智能体的新型技能表示,它将“有限状态机”概念引入技能建模,以实现高效且有效的技能构建与学习。StateSkill的核心思想是将具身交互经验建模为有限状态机,其中技能围绕一组任务进展状态、状态转换以及状态条件引导进行组织,使具身智能体能够在任务推进时动态调整技能,同时保持技能上下文紧凑且与阶段相关。我们进一步开发了StateSkill-Evolve,这是一种经验驱动的进化机制,通过对新的成功和失败的状态引导轨迹进行回顾性分析,迭代优化StateSkill。在此基础上,我们引入了StateGRPO,它将StateSkill进化与基于状态条件GRPO的模型优化整合到统一的迭代学习循环中,使状态条件技能与模型能力能够协同进化并相互增强。大量实验证明,我们提出的方法及训练得到的模型(即StateSkill-Agent)在各类具身任务中均表现出有效性。

英文摘要:

In this work, we aim to develop an embodied MLLM agent that understands and solves embodied tasks by learning, abstracting, and reusing transferrable and generalizable behavioral patterns. To this end, we propose StateSkill, a new skill representation for embodied agents, which introduces the concept of "finite-state machines" into skill modeling for effective and efficient skill construction and learning. The core idea of StateSkill is to model embodied interaction experiences as a finite-state machine, where a skill is organized around a set of task-progress states, state transitions, and state-conditioned guidance, enabling embodied agents to dynamically adjust their skills as the task progresses while keeping skill contexts compact and stage-relevant. We further develop StateSkill-Evolve, an experience-driven evolution mechanism that iteratively refines StateSkill through retrospective analysis of new successful and failed state-guided trajectories. Upon this, we introduce StateGRPO, which integrates StateSkill evolution and model optimization via state-conditioned GRPO into a unified iterative learning loop, enabling state-conditioned skills and model capabilities to co-evolve and reinforce each other. Extensive experiments demonstrate the effectiveness of our proposed methods and trained model (i.e., StateSkill-Agent) across various embodied tasks.

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。

↑