Due to the limitations of welding complexity and machining error, traditional manual teaching and offline programming are not intelligent enough and have weak adaptability to workpiece. At present, the 2D perception visual welding guidance programming method is commonly used which cannot accurately locate and model the complicated 3D spatial curve welding seam. The 2D perception method can hardly meet the requirements of welding process. In this paper, a welding seam perception method based on a line structure-light sensor was proposed, which optimizes the generation of the weld seam trajectory, and builds a highly adaptable intelligent guidance programming system for welding robots. Firstly, 3D modeling perception of welding parts is realized through eye-in-hand system of robot, which solves the problem that offline programming system cannot be applied when the welding model is not precise enough or partly miss. Secondly, aiming at solving extraction problem of common types of 3D space curve welding seam, corresponding types of weld extraction algorithms are proposed according to the characteristics of different types of welds under the general process of weld extraction. These methods not only can directly extract the weld from the ordered point cloud with high precision and resolution, but also are less affected by the welding environment, which solve the problem of low perception accuracy of complex curved welds in 3D space. Then, on the basis of welding seam extraction, NURBS curves are used to realize the optimal generation of weld trajectory. Finally, the feasibility and effectiveness of all the methods proposed in this paper are verified by a large number of experiments.
18 October 2023 in IEEE Robotics and Automation Letters
Identifying moving objects is an essential capability for autonomous systems, as it provides critical information for pose estimation, navigation, collision avoidance, and static map construction. In this letter, we present MotionBEV, a fast and accurate framework for LiDAR moving object segmentation, which segments moving objects with appearance and motion features in the bird's eye view (BEV) domain. Our approach converts 3D LiDAR scans into a 2D polar BEV representation to improve computational efficiency. Specifically, we learn appearance features with a simplified PointNet and compute motion features through the height differences of consecutive frames of point clouds projected onto vertical columns in the polar BEV coordinate system. We employ a dual-branch network bridged by the Appearance-Motion Co-attention Module (AMCM) to adaptively fuse the spatio-temporal information from appearance and motion features. Our approach achieves state-of-the-art performance on the SemanticKITTI-MOS benchmark. Furthermore, to demonstrate the practical effectiveness of our method, we provide a LiDAR-MOS dataset recorded by a solid-state LiDAR, which features non-repetitive scanning patterns and a small field of view.
Although the navigation of robots in urban environments has achieved great performance, there is still a problem of insufficient robustness in cross-scene (ground, water surface) navigation applications. An intuitive idea is to introduce multi-modal complementary data to improve the robustness of the algorithms. Therefore, this paper presents an MMDF (multi-modal deep feature) based cross-scene place recognition framework, which consists of four kinds of modules: LiDAR module, image module, fusion module and NetVLAD module. 3D point clouds and images are input to the network firstly. The point cloud module uses PointNet to extract point cloud features. The image module uses a lightweight network to extract image features. The fusion module uses image semantic features to enhance point cloud features, and then the enhanced point cloud features are aggregated using NetVLAD to obtain the final enhanced descriptors. Extensive experiments on KITTI, Oxford RobotCar and USVInland datasets demonstrate MMDF outperforms PointNetVLAD, NetVLAD and a camera-LiDAR fused descriptor.