Rearranging objects on a planar surface arises in a variety of robotic applications, such as product packaging. Using two arms can improve efficiency but introduces new computational challenges. This article studies the problem structure of object rearrangement using two arms in synchronous, monotone tabletop setups and develops an optimal mixed-integer model. It then describes an efficient and scalable algorithm, which first minimizes the cost of object transfers and then moves between objects. This is motivated by the fact that, asymptotically, object transfers dominate the cost of solutions. Moreover, a lazy strategy minimizes the number of motion planning calls and results in significant speedups. Theoretical arguments support the benefits of using two arms and indicate that synchronous execution, in which the two arms perform together either transfers or moves, introduces only a small overhead. Experiments support these claims and show that the scalable method can quickly compute solutions close to the optimal for the considered setup. Note to Practitioners—Monotone tabletop rearrangement challenges arise in a variety of automation scenarios, including product sorting or packing. Performing this task with two robotic manipulators introduces the overhead of coordinating them in the shared workspace, as well as an increase in the size of the underling search space. The objective of this work is to study the feasibility of such dual-arm solutions, providing both theoretical bounds, as well as a fast, and approximate solution. The approach leverages an effective algorithmic decomposition of the problem so as to take advantage of efficient motion planners and mixed-integer linear programming solvers. The proposed solution has been evaluated in settings that include delta robots as well as seven-degree-of-freedom (DOF) manipulators. Interesting extensions of this work correspond to studying the case of additional arms, nonmonotone, and general manipulation scenarios.

中文翻译：

---

在同步、单调桌面设置中快速、高质量的两臂重新排列


在平面上重新排列物体出现在各种机器人应用中，例如产品包装。使用两只手臂可以提高效率，但会带来新的计算挑战。本文研究了在同步、单调桌面设置中使用两个臂进行对象重新排列的问题结构，并开发了最佳混合整数模型。然后，它描述了一种高效且可扩展的算法，该算法首先最小化对象传输的成本，然后在对象之间移动。这是因为对象传输渐进地主导了解决方案的成本。此外，惰性策略可以最大限度地减少运动规划调用的数量，并显着提高速度。理论论证支持使用两个臂的好处，并表明同步执行（其中两个臂一起执行传输或移动）仅引入很小的开销。实验支持了这些说法，并表明可扩展方法可以快速计算出接近所考虑设置的最佳解决方案。从业人员注意——单调桌面重新排列挑战出现在各种自动化场景中，包括产品分类或包装。使用两个机器人操纵器执行此任务会带来在共享工作空间中协调它们的开销，并且会增加底层搜索空间的大小。这项工作的目的是研究此类双臂解决方案的可行性，提供理论界限以及快速近似解决方案。该方法利用问题的有效算法分解，以便利用高效的运动规划器和混合整数线性规划求解器。 所提出的解决方案已在包括 Delta 机器人和七自由度 (DOF) 机械手的设置中进行了评估。这项工作的有趣扩展对应于研究附加臂、非单调和一般操作场景的情况。