Fully autonomous factories of the future will need automated quality control processes to monitor products during manufacture. Here, we demonstrate that an artificial tactile system offers a solution to autonomous quality inspection, using a biomimetic tactile fingertip mounted as end-effector on an industrial arm. The study considers a task of gap width inspection suitable for judging parts alignment, although the methods apply generally. An active perception method implements optimal decision making while controlling sensor location, which was recently shown to attain superresolved spatial perception. In consequence, gap width is estimated to submillimeter accuracy comparable to human discrimination performance and is robust to uncertainty in test object placement. We conclude that an artificial tactile system of the type here offers an ideal solution to automated quality control on the production line.