Similarity-based Assembly Success/Failure Estimation Algorithm

Abstract

Mobile IT products, such as tablet PCs, are not only composed of parts with complex shapes, but also include various assembly processes, which makes it difficult to automate processes. Robot assembly based on position control exhibits a fast assembling speed, but if assembly fails, excessive contact force may occur and thus parts or robot may be damaged. In this study, we proposed a similarity-based assembly success/failure estimation algorithm to solve this problem. Several similarity evaluation methods were applied to the battery assembly process, which is a part of tablet PC. It is shown that a combination of similarities on Mahalanobis distance and singular value decomposition offer the best performance.