Dense Robotic Packing of Irregular and Novel 3D Objects
Fan Wang, Kris Hauser
Abstract
Recent progress in the field of robotic manipulation has generated interest in fully automatic object packing in warehouses. This article presents a formulation of the robotic packing problem that ensures stability of the object pile during packing and the feasibility of the robot motion while maximizing packing density. A constructive packing algorithm is proposed to address this problem by searching over the space of item positions and orientations. Moreover, a new heightmap minimization heuristic is shown to outperform existing heuristics in the literature in the presence of nonconvex objects. Two strategies for improving the robustness of executed packing plans are also proposed: 1) conservative planning ensures plan feasibility under uncertainty in model parameters; and 2) closed-loop packing uses vision sensors to measure placement errors and replans to correct for them. The proposed planner and error mitigation strategies are evaluated in simulation and on a state-of-the-art physical packing testbed. Experiments demonstrate that the proposed planner generates high-quality packing plans, and the error mitigation strategies improve success rates beyond an open-loop baseline from 83% to 100% on five-item orders.