Threaded fastening operations are widely used in assembly and are typically time-consuming and costly. In low-volume, high-value manufacturing, fastening operations are carried out manually by skilled workers. The existing approaches are found to be less flexible and robust for performing assembly in a less structured industrial environment. This paper introduces a novel algorithm for detecting the position and orientation of threaded holes and a new method for tightening bolts. First, the elliptic arc fitting method and the three-point method are used to estimate the initial position and orientation of the threaded hole, and the force impact caused by switching from the free space to the constrained space during bolt tightening is solved. Second, by monitoring the deformation of passive compliance, the position information is introduced into the control process to better control the radial force between the bolt and the threaded hole in the tightening process. The constant force controller and orientation compliance controller are designed according to the adaptive control theory. A series of experiments are carried out. The results show that the proposed method can estimate the initial position and orientation of an M24 bolt with an average position error of 0.36 mm, 0.43 mm and 0.46 mm and an orientation error of 0.65°, 0.46° and 0.59°, and it can tighten the bolt with a success rate of 98.5%.

To realize the automatic tightening of nuts, a nut tightening robot system strategy based on machine vision was designed in this work. The strategy was based on three stages: nut image calibration, nut identification and nut pose estimation. In the first stage, the template pose image of the nut and the coordinates of the nut center in this nut image were obtained by calibration. In the second stage, a nut identification algorithm based on improved the backbone feature extraction network and area generation network of Faster-RCNN was presented, which improved the efficiency and accuracy of nut identification. In the last stage, a nut pose estimation algorithm based on Fourier and log-polar coordinate transformation was presented to solve the rotation angle, translation and scale of the nut relative to the template nut image, and then obtain the rotation angle of the sleeve and the central coordinate of the nut. An experimental nut tightening robot platform was also set up in this work. The results of 50 tests showed that the proposed detection methods could identify nuts with 100% accuracy, and with this proposed pose estimation methods the average error of the rotation angle of the nut was 0.057, the average error of the center position of the nut in and directions was and of direction was . The experimental results showed that the nut tightening robot scheme and algorithm designed in this work were feasible in nut identification and pose estimation, and met the requirements of insertion accuracy in the process of nut tightening.