Product description Recipe Generation from 3D STEP model for Autonomous Task Planning

Abstract

This paper introduces an autonomous product description recipe generator for knowledge base of teaching free robot system. Most of the work such as defining mission and planning tasks are the job of experienced human managers. Automating these jobs could dramatically reduce the setup time for tasks. The proposed system analyzes the product structure, part specifications and assembly step descriptions from the STEP model. The system consists of five modules: step analyzer, part analyzer, image analyzer, task analyzer, and recipe generator. The step analyzer extracts the bill of materials (BOM) from a STEP file, and configures components of each part separately. The part analyzer analyzes characteristics of each part such as feature size and relative position from the reference point. The image analyzer generates representative images of each part and analyzes the shape type of part. The task analyzer finds the pairs of parts that make up to the joint, and determines the assembly sequence of the joints. The recipe generator creates product recipe with descriptions of parts and tasks, and generates assembly instructions for the product. The recipe could be expected to be used as knowledge base for intelligent robots, as well as information for human managers to define tasks.