发表机构
University of Maryland; Institute for Systems Research (ISR)(马里兰大学; 系统研究所(ISR))
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
该研究提出带可验证安全与质量保证的抓取距离场(GDFs),无需规划器即可执行抓取,在仿真中成功抓取 50 个物体中的 46 个,每步 QP 求解仅需 0.09 ms。
AI 中文摘要
标准多指抓取执行架构会规划一条通往选定抓取位姿的无碰撞轨迹,并通过反馈律跟踪该轨迹。执行时的物体位姿不确定性或扰动可能会使规划的轨迹失效,迫使进行代价高昂的重规划步骤。我们提出抓取距离场(Grasp Distance Fields, GDFs),这是一种在臂-手构型空间中针对抓取构型的平滑 softmin 距离场。我们的控制器通过跟随该场的负梯度,采用固定反馈律执行抓取,无需规划器、存储的轨迹或抓取选择。为确保安全,我们通过一个 CBF-CLF 二次规划(QP)过滤该指令,该规划约束自碰撞、工作空间、物体和障碍物间隙,并将受阻进展报告为显式松弛变量。我们证明,对于 N 个候选对象和平滑参数 ρ,softmin 在 log N/ρ 范围内跟踪真实集距离,且滤波后的回路使安全集前向不变。由于没有平滑场能捕捉手-物体接触切换,我们在预抓取构型处采用滞后切换模式,以放弃部分物体碰撞避免为代价换取接触允许。随后,力-质量屏障将已实现抓取的力闭合裕度保持在其保持起始时值的规定容差范围内。我们在固定基座机械臂和 Unitree G1 人形机器人(两者均配备相同的欠驱动手)的运动学仿真中进行评估。我们的控制器在杂乱和动态场景中导航,安全地伸手抓取并提起 50 个物体中的 46 个,涵盖原始、家用和对抗性类别。在这些抓取中,执行的抓取保留了其中值 94% 的合成质量裕度,每 20 ms 控制步骤的 QP 求解时间为 0.09 ms。每步 softmax 权重确认我们的控制器执行最近的候选对象,无需单独的选择步骤。项目页面:this http URL。
英文摘要
Mainstream plan-then-track approaches to multifingered grasp execution entail selecting a grasp, planning a collision-free trajectory, and tracking the resulting trajectory via a feedback controller. Pose-estimation error during execution or scene motion can invalidate this open-loop commitment and trigger replanning. We thus present Grasp Distance Fields (GDFs), smooth softmin distances to finite sets of arm-hand grasp configurations. Using their negative gradients as feedback, we jointly select and execute grasps without planning a trajectory. A CBF-CLF quadratic program (QP) enforces self-collision, workspace, object, and obstacle-clearance constraints, while its CLF slack quantifies obstruction of task progress. We bound the softmin approximation error by $\log N/ρ$ and prove forward invariance of the filtered safe set. To handle changes in contact topology, we combine a hysteretic contact-mode transition with a wrench-quality CBF that limits degradation of the realized force-closure margin relative to hold onset. Using our method, a fixed-base manipulator and a Unitree G1 equipped with the same underactuated hand grasp and lift 46 of 50 test objects amid clutter and moving obstacles. The realized grasps also retain a median 94% of their synthesized quality margin, and each QP solve requires 0.09 ms within a 20 ms control interval. Project page: www.clintonenwerem.com/gdf.
Comments14 pages, 7 figures, 3 tables. Project page: www.clintonenwerem.com/gdf