Exploring 2D projection and 3D spatial information for aircraft 6D pose

The 6D pose estimation is important for the safe take-off and landing of the aircraft using a single RGB image. Due to the large scene and large depth, the exiting pose estimation methods have unstratified performance on the accuracy. To achieve precise 6D pose estimation of the aircraft, an end-to-end method using an RGB image is proposed. In the proposed method, the 2D and 3D information of the keypoints of the aircraft is used as the intermediate supervision, and 6D pose information of the aircraft in this intermediate information will be explored. Specifically, an off-the-shelf object detector is utilized to detect the Region of the Interest (RoI) of the aircraft to eliminate background distractions. The 2D projection and 3D spatial information of the pre-designed keypoints of the aircraft is predicted by the keypoint coordinate estimator (KpNet). The proposed method is trained in an end-to-end fashion. In addition, to deal with the lack of the related datasets, this paper builds the Aircraft 6D Pose dataset to train and test, which captures the take-off and landing process of three types of aircraft from 11 views. Compared with the latest Wide-Depth-Range method on this dataset, our proposed method improves the average 3D distance of model points metric (ADD) and 5° and 5 m metric by 86.8% and 30.1%, respectively. Furthermore, the proposed method gets 9.30 ms, 61.0% faster than YOLO6D with 23.86 ms.     

Improving performance of macro electrolyte jet machining of TC4 titanium alloy: Experimental and numerical studies

Electrolyte jet machining (EJM) is a promising method for shaping titanium alloys due to its lack of tool wear, thermal and residual stress, and cracks and burrs. Recently, macro-EJM has attracted increasing attention for its high efficiency in machining wide grooves or planes. However, macro-EJM generates large amounts of electrolytic products, thereby increasing the difficulty of rapid product removal with a standard tool and reducing the surface quality. Therefore, for enhanced product transport, a novel tool with a back inclined end face was proposed for macro-EJM of TC4 titanium alloy. For comparison, also proposed were ones with a standard flat end face, a front inclined end face, and both front and back inclined end faces. The flow field distributions of all proposed tools were simulated numerically, and experiments were also conducted to validate the simulation results. The results show that one with a 5° back inclined end face can decrease the low-velocity flow zone in the machining area and increase the high-velocity flow zone at the back end of tool, thereby promoting rapid product removal. A relatively smooth bright-white groove surface was obtained. The same tool also resulted in the highest machining depth and material removal rate among the tested ones. In addition, rapid product removal was beneficial to the subsequent processing. Because of its rapid product removal, the machining depth and material removal rate during deep groove machining using the tool with a 5° back inclined end face were respectively 7% and 14% higher than those produced using a standard one. Moreover, the lowest bottom height difference of 0.027 mm can be obtained when the step-over value was 8.2 mm, and a plane with a depth of 0.285 mm and a bottom height difference of 0.03 mm was fabricated using the tool with a 5° back inclined end face.