用大模型和机器人交互，识别未知可变形物体的物理属性。
Understanding Physical Properties of Unseen Deformable Objects by Leveraging Large Language Models and Robot Actions
- 通过机器人动作与物体互动，让大模型推理其物理特性。
- 实验验证可成功识别折叠性、弯曲性等属性，助力任务规划。
- 适合需要理解未知柔性物体的机器人应用场景。
本文研究通过机器人与物体的交互来理解未知物体的物理属性，尤其针对可变形物体。传统任务与运动规划方法因假设世界封闭而难以应对具有特殊性质的未知物体。近期基于大语言模型（LLMs）的任务规划研究展现出对未知物体的推理能力，但多数仍假设物体为刚体，忽视其物理属性。本文提出一种基于LLM的方法，通过机器人动作探测未知可变形物体的物理属性（如可折叠性、可弯曲性），并据此生成特定领域（如物体装箱）的任务规划。实验表明，该方法能有效识别可变形物体属性，并在装箱任务中发挥关键作用，提升成功率。
原文摘要 · Abstract (English)
In this paper, we consider the problem of understanding the physical properties of unseen objects through interactions between the objects and a robot. Handling unseen objects with special properties such as deformability is challenging for traditional task and motion planning approaches as they are often with the closed world assumption. Recent results in Large Language Models (LLMs) based task planning have shown the ability to reason about unseen objects. However, most studies assume rigid objects, overlooking their physical properties. We propose an LLM-based method for probing the physical properties of unseen deformable objects for the purpose of task planning. For a given set of object properties (e.g., foldability, bendability), our method uses robot actions to determine the properties by interacting with the objects. Based on the properties examined by the LLM and robot actions, the LLM generates a task plan for a specific domain such as object packing. In the experiment, we show that the proposed method can identify properties of deformable objects, which are further used for a bin-packing task where the properties take crucial roles to succeed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。