A Neural Net-based Assembly Algorithm for Flexible Parts Assembly

For successful assembly of flexible parts, informations about their deformation as well as possible misalignments between the holes and their mating parts are essential, since the corrective assembly motion to compensate for such misalignments has to be determined from the measured informations. However, the relationship between them is very complex, and thus cannot be simply derived from analytical methods. This paper presents a neural net-based inference system that can infer the complex relationship between the corrective motion and the measured information of parts deformation and misalignments. The lateral misalignment and the inclination angle of a part are given as the inputs, and the lateral corrective motion is given as the output for the neural network. By using the proposed method, a series of experiments to compensate for the lateral misalignment are performed. Experimental results show that the proposed neural net-based assembly algorithm is effective in compensating for the lateral misalignment from the point of view of a fast search toward the hole center, and that it can be extended to the assembly tasks under more general conditions.