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 2611.26596cs.ROcs.AI
收藏

PGX:面向长周期人形机器人移动操作的物理接地执行框架

PGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-Manipulation

Oxford Robotics Institute, University of Oxford(牛津大学牛津机器人研究所);Department of Computer Science, University of Oxford(牛津大学计算机科学系)

Kai Lu, Chenyang Ma, Ioannis Havoutis

AI总结:

针对人形机器人长周期移动操作任务中VLA模型的时间结构与精度耦合难题,提出PGX框架,通过三层分解提升阶段进展与任务成功率,经模拟及真实机器人实验验证有效。

摘要:

机器人视觉-语言-动作(VLA)模型可执行多种单一操作技能,但在长周期移动操作任务中仍存在困难,这类任务中时间结构、技能与精度在单一模型内紧密耦合。本文提出物理接地执行(PGX)框架,将时间与精度控制卸载至两个经典无训练组件,使VLA模型可专注于特定阶段的技能动态。PGX将长周期移动操作分解为三层:(i)基于谓词的状态机控制任务进展,利用物理谓词门控阶段转换、触发恢复及协调导航与等待,共享谓词语义连接离线演示分割、在线执行与分阶段评估;(ii)VLA技能在主动操作阶段运行,平面或分阶段训练的模型专注于任务相关动作;(iii)世界坐标锁定(WCL)通过基站保持、物体相对定位及世界锚定接触目标维持空间一致性。我们在三项模拟任务及一项使用Unitree G1人形机器人的真实世界任务中开展大量实验验证PGX的有效性,结果显示其在阶段进展与任务成功率上均有提升。项目页面可访问:this https URL

英文摘要:

Robotic vision-language-action (VLA) models can execute diverse individual manipulation skills, yet they still struggle with long-horizon loco-manipulation tasks, where temporal structure, skills, and precision are tightly coupled within a monolithic model. We propose Physically Grounded Execution (PGX), a framework that offloads temporal and precision control to two classical training-free components, allowing the VLA to focus on stage-specific skill dynamics. PGX decomposes long-horizon loco-manipulation into three layers: (i) a predicate-based state machine governs task progression, using physical predicates to gate phase transitions, trigger recovery, and coordinate navigation and waiting. Shared predicate semantics connect offline demonstration segmentation, online execution, and stage-wise evaluation; (ii) VLA skills operate within active manipulation phases, with flat or stage-trained models concentrating on task-relevant actions; and (iii) world-coordinate locking (WCL) maintains spatial consistency through base station keeping, object-relative positioning, and world-anchored contact targets. We demonstrate the effectiveness of PGX with extensive experiments conducted on three simulated tasks and one real-world task using a Unitree G1 humanoid robot for long-horizon loco-manipulation, showing improvements in stage progression and task success rates. Project page is available at: https://kl-research.github.io/pgx

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。

↑