发表机构
The University of Tennessee, Knoxville; The University of Texas at Arlington; The University of Arizona（田纳西大学诺克斯维尔分校; 德克萨斯大学阿灵顿分校; 亚利桑那大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出SAGE系统，利用LLM提取文档材料强度并结合有限元插值计算轴向承载能力，指导机器人插入力限制，显著降低误差并实现可追溯决策。
AI 中文摘要
插入是机器人建筑装配中的一项基本操作，其中材料属性和装配条件的变化使得选择既能完成任务又不超出装配承载能力的接触力变得困难。尽管建筑文档编码了关于材料及其条件的工程知识，但将这些知识转化为特定装配的载荷限制仍然困难。本文提出了SAGE（源接地装配门控与执行）系统，该系统将文档化的材料证据转换为机器人插入的承载能力估计。SAGE限制大型语言模型（LLM）仅从检索到的段落和表格中提取抗拉强度和抗压强度，并记录其来源。随后，一个响应模型对离线有限元（FE）解进行插值，将这些强度和装配条件转换为轴向载荷能力。对于具有正间隙的配合，估计的承载能力设定策略的轴向力限制；对于过盈配合，将其与测量的支撑需求进行比较以决定是否准入。在主要基准测试中，SAGE将基于相同证据的直接LLM估计的平均承载能力误差从80.65%降低到10.74%。在不重新拟合的情况下，在16个额外几何体上的平均误差仍为8.00%。在指定的支撑释放模型下，SAGE正确分类了62次评分模拟运行中的59次，且仅出现保守性错误。在记录的xArm6演示中，SAGE以材料文档为输入，在13次试验中完成了9次物理插入。这些结果表明，将文档解释分配给LLM，将力计算分配给显式机械模型，能够产生准确的承载能力估计和可追溯的插入决策。
英文摘要
Insertion is a fundamental operation in robotic construction assembly, where variations in material properties and assembly conditions make it difficult to select contact forces that complete the task without exceeding the assembly's capacity. Although construction documents encode engineering knowledge about materials and their conditions, translating this knowledge into load limits for a specific assembly remains difficult. This paper presents SAGE (Source-grounded Assembly Gating and Execution), a system that converts documented material evidence into capacity estimates for robotic insertion. SAGE restricts a large language model (LLM) to extracting tensile and compressive strengths from retrieved passages and tables and records their sources. A response model then interpolates offline finite element (FE) solutions to convert these strengths and the assembly conditions into axial load capacity. For fits with positive clearance, the estimated capacity sets the policy's axial force limit; for interference fits, it is compared with measured support demand to determine admission. On the primary benchmark, SAGE reduces mean capacity error from 80.65\% for direct LLM estimates based on the same evidence to 10.74\%. Without refitting, the mean error remains 8.00\% on 16 additional geometries. Under the assigned support release model, SAGE correctly classifies 59 of 62 scored simulation runs, with only conservative errors. In recorded xArm6 demonstrations, SAGE takes material documents as input and completes physical insertion in 9 of 13 trials. These results show that assigning document interpretation to the LLM and force calculation to an explicit mechanical model produces accurate capacity estimates and traceable insertion decisions.
