FORM：通过直接材料律识别实现机器人操作
FORM: Robot Manipulation through Direct Material Law Identification
浏览论文内容
中文总结 AI 辅助
FORM通过单次交互识别可变形材料属性，利用弱形式动量平衡和物质点法实现快速线性最小二乘求解，显著缩短识别时间并保持高精度，应用于多项机器人操作任务。
中文摘要 AI 辅助
当机器人与不熟悉的可变形材料交互时，它缺乏关于材料物理性质以及材料如何响应施加力和运动的先验知识。因此，快速在线识别对于可靠操作至关重要。我们提出FORM（从观测响应到材料律），该方法从单次机器人交互中识别材料属性，并重用恢复的模型来规划在新动作和几何形状下的操作。我们使用弱形式动量平衡将观测到的材料运动和接触力转化为关于未知材料参数的线性方程。这些方程使用与前向模拟器相同的物质点法离散化进行组装，因此识别简化为线性最小二乘求解，其解可直接用于预测，无需重新拟合或转换。在四类材料中，FORM将识别时间从迭代基线的约10-25分钟减少到2-5秒，同时在新运动、初始条件和几何形状上保持有竞争力的精度。我们在仿真和硬件上展示了我们的方法，涵盖四项操作任务：弹性杆插入、使用弹性杆的高尔夫推杆、弹塑性成形和目标体积倒水。在每项任务中，从单次交互中识别的模型被重用于规划新运动或操作不同几何形状。FORM估计弹性属性误差在3.4%以内，弹塑性属性误差在2%以内，在面团成形中达到72.4-77.8%的IoU，并在60-160 mL的目标体积下保持平均倒水误差为3.8 mL。
英文摘要
When interacting with an unfamiliar deformable material, a robot lacks prior knowledge of its physical properties and how it will respond to applied forces and motion. Rapid online identification is therefore essential for reliable manipulation. We present FORM (From Observed Response to Material laws), which identifies material properties from a single robot interaction and reuses the recovered model to plan manipulation under new actions and geometries. We use weak-form momentum balance to convert observed material motion and contact forces into linear equations in the unknown material parameters. These equations are assembled using the same material point method discretization as the forward simulator, so identification reduces to linear least-squares solves whose solutions can be used directly for prediction without refitting or conversion. Across four material classes, FORM reduces identification time from roughly 10--25 minutes for iterative baselines to 2--5 seconds, while maintaining competitive accuracy on new motions, initial conditions, and geometries. We demonstrate our approach in simulation and on hardware across four manipulation tasks: elastic rod insertion, golf putting with an elastic club, elastoplastic shaping, and target-volume pouring. In each task, the model identified from a single interaction is reused to plan new motions or manipulate a different geometry. FORM estimates elastic properties within 3.4% and elastoplastic properties within 2%, achieves 72.4--77.8% IoU in dough shaping, and keeps mean pouring error at 3.8 mL across target volumes of 60--160 mL.
发表机构
- University of California, Berkeley（加州大学伯克利分校）
- Chandra Family Department of Electrical and Computer Engineering（Chandra Family 电气与计算机工程系）
- Maseeh Department of Civil, Architectural and Environmental Engineering（Maseeh 土木、建筑与环境工程系）
- Oden Institute for Computational Engineering and Sciences（Oden 计算工程与科学研究所）
- The University of Texas at Austin（德克萨斯大学奥斯汀分校）
机构由 AI 辅助整理，请以论文原文为准。
