基于身体状态重规划的物理自适应操作

中文摘要 AI 辅助

操作不仅需要推理外部环境，还需要考虑机器人的物理状况。一个策略可能在几何上仍然可行，但由于关节负载增加或活动能力受限而变得在物理上不合适，然而内部物理状态通常仅用于低级控制。我们提出了基于身体状态的高级重规划方法，该方法在执行过程中利用内部物理状态来调整操作策略。身体状态事件触发策略重规划，大语言模型（LLM）解释底层的关节级状态、最近的执行统计数据和执行历史，以选择依赖于上下文的替代方案，同时保持任务目标和低级控制器不变。我们在模拟和真实机器人上，在受控负载和不对称活动能力约束下，对到达任务评估了该框架。我们的实验表明，基于身体状态的重规划在保持高任务成功率的同时，减少了物理消耗并实现了更高效的策略适应。额外的接触丰富操作实验证明了相同的重规划接口在到达任务之外的适用性。这些结果表明，内部物理状态不仅可以为低级控制提供信息，还可以为关于如何执行操作任务的高级决策提供信息。

英文摘要

Manipulation requires not only reasoning about the external environment, but also about the robot's physical condition. A strategy may remain geometrically feasible while becoming physically unsuitable due to increased joint load or limited mobility, yet internal physical state is typically used only for low-level control. We propose body-grounded high-level replanning, which uses internal physical state to adapt manipulation strategies during execution. Body-state events trigger strategy replanning, and an LLM interprets the underlying joint-level state, recent execution statistics, and execution history to select a context-dependent alternative, while leaving the task objective and low-level controller unchanged. We evaluate the framework on a reaching task under controlled load and asymmetric mobility constraints in simulation and on a real robot. Our experiments show that body-grounded replanning maintains high task success while reducing physical effort and enabling more efficient strategy adaptation. Additional contact-rich manipulation experiments demonstrate the applicability of the same replanning interface beyond reaching. These results show that internal physical state can inform not only low-level control, but also high-level decisions about how a manipulation task should be performed.

发表机构

• Microsoft Research Asia - Tokyo（微软亚洲研究院-东京）
• Waseda University（早稻田大学）
• Chiba University（千叶大学）
• National Institute of Informatics（国立情报学研究所）

机构由 AI 辅助整理，请以论文原文为准。