Stable bin packing of non-convex 3D objects with a robot manipulator
This addresses the problem of efficient and stable robotic packing for warehouse automation, but it is incremental as it builds on existing packing methods with domain-specific adaptations.
The paper tackles the problem of automatically packing non-convex 3D objects in warehouses by minimizing waste space while ensuring pile stability and robot feasibility, proposing a pipeline with a new heuristic that achieves stable and high-quality packing plans in simulations with real-world items.
Recent progress in the field of robotic manipulation has generated interest in fully automatic object packing in warehouses. This paper proposes a formulation of the packing problem that is tailored to the automated warehousing domain. Besides minimizing waste space inside a container, the problem requires stability of the object pile during packing and the feasibility of the robot motion executing the placement plans. To address this problem, a set of constraints are formulated, and a constructive packing pipeline is proposed to solve for these constraints. The pipeline is able to pack geometrically complex, non-convex objects with stability while satisfying robot constraints. In particular, a new 3D positioning heuristic called Heightmap-Minimization heuristic is proposed, and heightmaps are used to speed up the search. Experimental evaluation of the method is conducted with a realistic physical simulator on a dataset of scanned real-world items, demonstrating stable and high-quality packing plans compared with other 3D packing methods.