发表机构
University of Maryland; Institute for Systems Research（马里兰大学; 系统研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对经典抓取质量度量无法应对摩擦值范围问题，提出基于CVaR的FIRMGrasp度量。该度量评估力封闭裕度，确定其相关特性，通过实验与其他方法对比，能更准确识别摩擦敏感抓取，提升抓取成功率。
AI 中文摘要
经典的抓取质量度量假设单一确定性摩擦系数，无法预测抓取在接触表面可能呈现的摩擦值范围内是否保持力封闭。为预测此类失败情况，我们提出FIRMGrasp，这是一族基于条件风险价值（CVaR）风险度量的摩擦波动性感知抓取质量度量。与假设单一摩擦实现的标准抓取质量评估器不同，我们的度量在不利摩擦尾部的CVaR折扣均值处评估力封闭裕度，得出风险调整裕度ε^(β)，即风险调整扳手空间的内切球半径。我们确定了其在置信水平β上的单调性、在抓取参数上的可微性，以及一个概率封闭证书——当ε^(β)为正时，保证力封闭概率至少为β。在校准摩擦分布下，分析评估表明我们的ε^(β)度量能识别出名义上法拉利 - 坎尼ε率评为高质量的摩擦敏感抓取。我们与名义ε及近期可微基线进行比较。在1599次LEAP手和Allegro手抓取中，名义法拉利 - 坎尼裕度认证的抓取中有53%在不利摩擦尾部失去力封闭。在同一组中，名义裕度区分实际摇晃和拾取成功的概率仅为0.53和0.67，接近摇晃成功的随机概率，而ε^(β)分别以0.63和0.78的概率正确排序这对情况。在不利摩擦系数为0.2且启用重力的模拟提升试验中，ε^(β)认证的抓取在侧向拉力下成功率达到70%，而名义裕度认证但ε^(β)拒绝的抓取成功率为25%。
英文摘要
Classical grasp quality metrics assume one deterministic friction coefficient and therefore cannot assess whether a grasp maintains force closure across plausible friction values. We present FIRMGrasp, a family of grasp quality metrics that incorporates friction uncertainty through Conditional Value-at-Risk (CVaR). At confidence level $β$, we evaluate the force-closure margin at the mean of the adverse friction tail. This evaluation defines the risk-adjusted margin $\varepsilon^{(β)}$, the inscribed-ball radius of the corresponding grasp wrench space. We prove that $\varepsilon^{(β)}$ varies monotonically with $β$, remains differentiable in the grasp parameters, and certifies that any grasp with $\varepsilon^{(β)} > 0$ achieves force closure with probability at least $β$. Across 1,599 LEAP Hand and Allegro Hand grasps, $\varepsilon^{(β)}$ identifies friction-sensitive grasps that receive high nominal Ferrari-Canny scores, and 53% of the nominally force-closed grasps lose closure in the adverse friction tail. The nominal margin ranks a successful grasp above a failed grasp with probabilities of only 0.53 in the shake test and 0.67 in the pick test, whereas $\varepsilon^{(β)}$ achieves 0.63 and 0.78. At an adverse friction coefficient of 0.2, 70% of grasps with positive $\varepsilon^{(β)}$ withstand a simulated lift and lateral pull, compared with 25% of grasps with positive nominal margin and nonpositive $\varepsilon^{(β)}$. We also synthesize grasps with positive $\varepsilon^{(β)}$ for the RealHand L6 and LEAP Hand, both of which retain the object during adverse-friction lifts. In MuJoCo trials with the RealHand L6, 95% of grasps that establish contact and have positive $\varepsilon^{(β)}$ retain the object at the same adverse friction coefficient.
Comments16 pages, 14 figures, 10 tables
