Planning for assembly from solid models

This paper describes how to use geometric boundary models of assembly components to find mating features, thereby permitting simpler task specifications to be used. This forms part of our work on a high-level robot assembly task planner. To mitigate the combinatorics of searching for a feasible correspondence between features of different bodies, boundary models produced by PADLS are matched against a library of standard compound features. The feasibility of mating compound features is analysed using the symmetry groups of features.