Robotics and Computer-integrated Manufacturing最新文献

Robotic machining could provide a solution for removing supports from metal additive manufactured workpieces, replacing labor-intensive work. However, the robot’s intrinsic weaknesses of low positioning accuracy and structural rigidity primarily restrict its applications. Improving the accuracy of robotic machining remains an unresolved issue. A mixed solution is proposed, in which a portable CNC machine with the capability of visual feature recognition is equipped with a universal industrial robot. The robot implements positioning motions in a large space, while the portable CNC fulfills accurate machining motions on a local feature of the workpiece. A sizeable weight of the portable CNC exerts a moderate load on the industrial robot’s joints, increasing joint stiffness. The mixed machining system exhibits high accuracy and stiffness when milling a steel/titanium alloy workpiece, achieving tolerances up to ±0.04 mm on a 60×80 mm U-shaped path without exciting any structural vibration modes. When the dimension of the workpiece exceeds the machining range of the portable CNC, a combined algorithm of coarse-fine registration based visual identification and robot error compensation is designed to align the spatial coordinates of the machining motion with that of the positioning motion, thereby extending the machining range with high accuracy. Through the proposed mixed robot machining method, experiments of doubling the machining range have been done to verify that the mixed machining robotic system is able to slot a 550 mm-long path with accuracy of ±0.1 mm. Furthermore, the mixed robotic machining system is applied to recognize and remove multiple supports of lattices, grids and ribs from a titanium-alloy additive manufactured thin-wall workpiece with high accuracy and high efficiency.

Visual recognition of weld beads is essential for post-weld robotic grinding. The recognition of thin-walled weld bead boundary, especially the backside boundary, remains challenging due to the diverse features such as debris, misalignment, and deformation. Based on point cloud from a laser scanner, we present a robust and accurate backside boundary recognition method for girth weld beads of thin-walled pipes. A boundary point extraction method is designed based on an adaptive sliding window model. Without prior morphology features, the influence of misalignment and deformation on the accuracy of boundary point recognition is greatly reduced by the local model matching strategy. Leveraging the correlation among overall weld bead features, an anomalous boundary point recognition and correction method based on DBSCAN clustering is proposed to further enhance robustness. A series of validation experiments were conducted by the obtained backside point cloud data inside a girth weld pipe, and our proposed method showed a high accuracy and a high robustness to misalignment, deformation and debris features.

The process design intent is the concentration of the technologists’ design cognitive process which contains the experiential knowledge and skills. It can reproduce technologists’ design thinking process in process design and provides guidance and interpretability for the generation of process results. The machining process route, as a core component of a part's entire manufacturing process, contains substantial process design intent. If the process design intent embedded in the existing process route can be explicitly identified, subsequent technologists will be able to learn and understand the original designers’ thinking, methodologies, and intents. This understanding enables effective reuse of design thinking and logic in the process design of new parts, rather than merely reusing data. It can also promote the propagation of the expertise and skills inherent in the process design intent. However, existing research on process design intent lacks a detailed explanation of its formation and specific structure from the design cognition perspective, making it challenging to effectively predict the process design intent containing interpretable empirical knowledge in the process route. To address this issue, this paper provides a method for predicting process design intent in the process route using heterogeneous graph convolutional networks. First, the heterogeneous graph is used to represent the parts and their associated process routes in the dataset. The nodes in the graph are then labeled based on accumulated and summarized process design intent. The prediction of process design intent in the process route is then converted into a node classification issue with heterogeneous graphs. A node classification network model is constructed using a heterogeneous graph convolutional network where the input is the created heterogeneous graph, and the output is the design reason contained in the machining feature and the intent cognition embedded in the working step, both of which are part of the process design intent. After training, the proposed model accurately predicted design reasons for machining features and intent cognitions for working steps (95.13 % and 96.85 %, respectively). Finally, examples of actual process routes are analyzed to verify the method's feasibility and reliability. The method given in this article can help technologists gain a deeper understanding of process route generation, hence improving their process design capabilities.

Human–robot collaborative polishing can integrate the capabilities of humans and automation to deal with complex polishing tasks. Traditional impedance-control-based human–robot collaboration (HRC) requires operators to physically interact with robots for a good polishing performance, which brings unsafety to operators. To address this issue, a corrective shared control architecture using haptic feedback is proposed in this paper, where the direct force-reflection is used to guarantee the exact human-intention intervention. The proposed control architecture is designed with two layers: (i) the transparency layer in which the direct force-reflection and the human–robot collaborative polishing strategy are implemented; (ii) the passivity layer in which two energy tanks are designed and endowed with master and slave sides and a coupling energy scaling policy is employed to guarantee the passivity of the whole system. Under the proposed architecture, the constant force is adopted to polish normal areas of workpieces, and corrective force based on human intention is applied to deal with unexpected issues. Finally, two groups of experiments are conducted to evaluate the proposed architecture from two aspects: polishing effect and user experience.

Generating model-free grasps in complex scattered scenes remains a challenging task. Most current methods adopt PointNet++ as the backbone to extract structural features, while the relative associations of geometry are underexplored, leading to non-optimal grasp prediction results. In this work, a parallelized graph-based pipeline is developed to solve the 7-DoF grasp pose generation problem with point cloud as input. Using the non-textured information of the grasping scene, the proposed pipeline simultaneously performs feature embedding and grasping location focusing in two branches, avoiding the mutual influence of the two learning processes. In the feature learning branch, the geometric features of the whole scene will be fully learned. In the location focusing branch, the high-value grasping locations on the surface of objects will be strategically selected. Using the learned graph features at these locations, the pipeline will eventually output refined grasping directions and widths in conjunction with local spatial features. To strengthen the positional features in the grasping problem, a graph convolution operator based on the positional attention mechanism is designed, and a graph residual network based on this operator is applied in two branches. The above pipeline abstracts the grasping location selection task from the main process of grasp generation, which lowers the learning difficulty while avoiding the performance degradation problem of deep graph networks. The established pipeline is evaluated on the GraspNet-1Billion dataset, demonstrating much better performance and stronger generalization capabilities than the benchmark approach. In robotic bin-picking experiments, the proposed method can effectively understand scattered grasping scenarios and grasp multiple types of unknown objects with a high success rate.

Automating fabric manipulation in garment manufacturing remains a challenging task due to the characteristics of limp sheet materials and the diversity of fabrics used. This paper introduces an adaptive and optimized robotic fabric handling system, designed to address these challenges. The system comprises an industrial robot, four needle grippers, and a novel adaptive gripper jig system capable of adjusting the positions of the grippers adaptively to accommodate the shape and material properties of the garment fabric parts. To do this, an in-depth analysis of fabric gripping characteristics—accounting for material properties, gripping position, and fabric deformation—is conducted. A two-stage machine learning model predicting fabric deflection and folding is established from the analyzed data. This model is then incorporated into a vision-guided algorithm that determines the optimal gripping points on garment parts using corresponding CAD data. In addition, the exact position of the target fabric part is swiftly recognized via an algorithm that maps the real-time captured images to the CAD-based shape information. The decision-making information—namely optimal gripping points and garment part position—are subsequently transmitted to the robotic system for automated fabric handling process. The performance of the developed algorithms was quantitatively evaluated, and the integrated robotic system verified to be capable of completing garment manufacturing automation by connecting the processes of automatic fabric cutting and sewing.

Owing to the advantages of good flexibility and low cost, robots are gradually replacing manual labor as an effective carrier for the grinding and polishing of aeroengine blades. However, the geometric features of blades are complex and diverse, and the contour accuracy and surface quality requirements are high, making the robotic grinding and polishing of blades still a challenging task. For this reason, this article first designs a new device by integrating different tools, which can achieve full-feature grinding and polishing of blades. Then, in order to improve the accuracy and stability of force tracking during the robotic grinding and polishing processes, a variable impedance control approach with simultaneous changes in stiffness and damping and parameter boundaries is proposed. Finally, the superiority of the proposed variable impedance control method is verified by comparative experiments on surface tracking. In addition, by combining the device with the variable impedance control method in the robotic grinding and polishing experiments of an aeroengine blade, their effectiveness in practical situations is confirmed.