An improved posture evaluation method of cylindrical intersecting holes on large aerospace component based on monocular vision

Cylindrical intersecting holes(CIHs) are common connection and location reference features in assembly of large aerospace structures such as missile and rocket cabins. The posture accuracy of assembly holes significantly impacts the relative position accuracy of joined parts and fatigue strength of finished product. At present, monocular vision measurement is widely used in automatic drilling of assembly holes for its integration simplicity and lower cost, but in most research, only the front face edge of the hole is used in the measurement model, and the hole end surface is usually assumed to be plane, which inevitably leads to precision loss. In this research, a novel posture measurement method for CIHs is proposed. Firstly, by introducing an ambiguity removal strategy, a coarse posture estimation method based on plane hypothesis of the two end surfaces of CIHs is suggested. Secondly, considering that there is no simply explicit expression for CIHs edge, thus it is difficult to adopt the conventional model projection based pose optimization method. In view of this, the three-dimensional points corresponding to the edge pixels of CIHs image are derived, and the pose optimization model is established by minimizing the deviations between the distance from the points to the CIHs axis and the hole radius. Moreover, to better control the direction parameters of CIHs during the global optimization process, the approximately perpendicular and intersection constraints between CIHs axis and cylindrical component axis are involved in solution. The effectiveness of the posture measurement method is verified by comparative experiments with current methods and CMM, which demonstrates improvements on both measurement accuracy and robustness.

WPO-Net: Windowed Pose Optimization Network for Monocular Visual Odometry Estimation

Visual odometry is the process of estimating incremental localization of the camera in 3-dimensional space for autonomous driving. There have been new learning-based methods which do not require camera calibration and are robust to external noise. In this work, a new method that do not require camera calibration called the “windowed pose optimization network” is proposed to estimate the 6 degrees of freedom pose of a monocular camera. The architecture of the proposed network is based on supervised learning-based methods with feature encoder and pose regressor that takes multiple consecutive two grayscale image stacks at each step for training and enforces the composite pose constraints. The KITTI dataset is used to evaluate the performance of the proposed method. The proposed method yielded rotational error of 3.12 deg/100 m, and the training time is 41.32 ms, while inference time is 7.87 ms. Experiments demonstrate the competitive performance of the proposed method to other state-of-the-art related works which shows the novelty of the proposed technique.

Stereo Vision-Based Relative Position and Attitude Estimation of Non-Cooperative Spacecraft

In on-orbit services, the relative position and attitude estimation of non-cooperative spacecraft has become the key issues to be solved in many space missions. Because of the lack of prior knowledge about manual marks and the inability to communicate between non-cooperative space targets, the relative position and attitude estimation system poses great challenges in terms of accuracy, intelligence, and power consumptions. To address these issues, this study uses a stereo camera to extract the feature points of a non-cooperative spacecraft. Then, the 3D position of the feature points is calculated according to the camera model to estimate the relationship. The optical flow method is also used to obtain the geometric constraint information between frames. In addition, an extended Kalman filter is used to update the measurement results and obtain more accurate pose optimization results. Moreover, we present a closed-loop simulation system, in which the Unity simulation engine is employed to simulate the relative motion of the spacecraft and binocular vision images, and a JetsonTX2 supercomputer is involved to conduct the proposed autonomous relative navigation algorithm. The simulation results show that our approach can estimate the non-cooperative target’s relative pose accurately.