The purpose of this paper is to develop a planner for finding an optimal assembly sequence for robots to assemble objects. Each manipulated object in the optimal sequence is stable during assembly. They are easy to grasp and robust to motion uncertainty.
The input to the planner is the mesh models of the objects, the relative poses between the objects in the assembly and the final pose of the assembly. The output is an optimal assembly sequence, namely, in which order should one assemble the objects, from which directions should the objects be dropped and candidate grasps of each object. The proposed planner finds the optimal solution by automatically permuting, evaluating and searching the possible assembly sequences considering stability, graspability and assemblability qualities.
The proposed planner could plan an optimal sequence to guide robots to do assembly using translational motion. The sequence provides initial and goal configurations to motion planning algorithms and is ready to be used by robots. The usefulness of the proposed method is verified by both simulation and real-world executions.
The paper proposes an assembly planner which can find an optimal assembly sequence automatically without teaching of the assembly orders and directions by skilled human technicians. The planner is highly expected to improve teachingless robotic manufacturing.
The paper is based on results obtained from a project commissioned by the New Energy and Industrial Technology Development Organization (NEDO).
CitationDownload as .RIS
Emerald Publishing Limited
Copyright © 2017, Emerald Publishing Limited