Open AccessView Planning for Robotic Inspection of Tolerances Through Visual Tracking of Manual Surface Finishing Operations
Author(s) -
Eirik B. Njaastad
Publication year - 2020
Publication title -
international journal of robotic computing
Language(s) - English
Resource type - Journals
ISSN - 2641-9521
DOI - 10.35708/rc1869-126261
Subject(s) - computer vision , artificial intelligence , process (computing) , computer science , visual inspection , tracking (education) , robot , sort , psychology , pedagogy , information retrieval , operating system
This article presents an approach for determining suitablecamera view poses for inspection of surface tolerances based on visualtracking of the tool movements performed by a skilled worker. Automated surface inspection of a workpiece adjusted by manual operationsdepends on manual programming of the inspecting robot, or a timeconsuming exhaustive search over the entire surface. The proposed approach is based on the assumption that the tool movements of the skilledworker coincide with the most relevant regions of the underlying surfaceof the workpiece, namely the parts where a manual process has beenperformed. The affected region is detected with a visual tracking system,which measures the motion of the tool using a low-cost RGBD-camera,a particle filter, and a CAD model of the tool. The main contributionis a scheme for selecting relevant camera view poses for inspecting theaffected region using a robot equipped with a high-accuracy RGBDcamera. A principal component analysis of the tracked tool paths allowsfor evaluating the view poses by the Hotelling’s T-squared distributiontest in order to sort and select suitable camera view poses. The approachis implemented and tested for the case where a large ship propeller bladecast in NiAl bronze is to be inspected by a robot after manual adjustments of its surface.