Robotics and Computer-integrated Manufacturing最新文献

Task planning and action planning for workshop machines are essential for modern manufacturing. Traditionally, these two problems are solved independently with elaborate manual methods. However, personalized customization introduces more dynamic exogenous events into the manufacturing system, and it is then impossible to consider all possible dynamic scenarios manually. This paper focuses on online automated planning, generating new plans automatically in response to new dynamic situations. We first formulate the planning problem for a flexible manufacturing system as a fully observable nondeterministic planning problem. Second, a hierarchical automated online planning approach is presented. Finally, the effectiveness of the proposed approach is verified by an ARIAC 2022 competition environment.

The Cloud Manufacturing Service Composition and Scheduling (CMfg-SCS) are essential processes in cloud manufacturing. Flexible Manufacturing Services (FMS), such as those provided by industrial robots, are widely used in cloud manufacturing to improve service quality and efficiency. Traditional CMfg-SCS methodologies, however, fall short in effectively managing the inherent temporal-dynamic QoS and flexible capability of FMS. To overcome these challenges, we propose a novel Cloud Manufacturing Service Cloud-edge Collaboration Composition and Scheduling (CMfg-SCCCS) method for FMS. Firstly, the service-task matching hypernetwork is constructed, and the temporal-dynamic QoS and flexible capacity of FMS are modeled. Subsequently, we develop a CMfg-SCCCS optimization model aimed at three objectives, along with a cloud-edge collaboration scheduling mechanism to harmonize cloud and edge-local tasks. Finally, a multi-population co-evolution algorithm with adaptive meta-knowledge transfer mechanism is proposed to solve the complex optimization model. The computational experiments serve to validate the effectiveness of the CMfg-SCCCS method and further reveal the superiority of the co-evolution algorithm in enhancing both the convergence and diversity of the population.

Elasto-geometrical calibration is crucial for enhancing the absolute accuracy of robots in machining operations through the identification and compensation of parameter errors. However, the presence of inconsistent measurement units and improper selection of measuring poses can result in the ill-conditioned identification matrix (ICIM) issue, consequently impacting the accuracy of parameter identification. This paper introduces a novel method to tackle this challenge. Initially, an elasto-geometrical error model is developed based on the orientation-independent measurements (OIM), efficiently reducing the impact of mismatched positions and orientations on the ICIM problem. Subsequently, a PSO-SFFS algorithm is proposed to optimize the measurement configurations and minimize the influence of measurement noise. Furthermore, the incorporation of screw theory and the consideration of parallelogram mechanisms enhance the precision and comprehensiveness of the error model. Subsequent to the development of the error model, calibration comparison experiments are conducted on an industrial robot. Both simulation and experimental results validate the effectiveness of the proposed method in improving parameter identification accuracy.

Compared to a single robot, multi-robot systems (MRS) offer several advantages in complex multi-task scenarios. The overall efficiency of MRS relies heavily on an efficient task allocation and scheduling process. Multi-robot task allocation (MRTA) is often formulated as a multiple traveling salesman problem, which is NP-hard and typically addressed offline. This paper specifically addresses the online allocation problem in multi-manipulator systems within multi-task scenarios. The tasks are initially pre-allocated to alleviate the computational burden of online allocation. Subsequently, considering collision constraints, we search for the current feasible set of manipulators and employ greedy algorithms to achieve local optima as the online allocation result within this set. Our method can handle the online addition of new, unknown tasks to the task list. Moreover, we demonstrate the feasibility of our approach through simulations and on a realistic platform, where multiple manipulators are tasked with polishing the white body of automobile parts. The results demonstrate that our method is effective and efficient for online allocation and scheduling scenarios.

The complex background on the car body surface, such as the orange peel-like texture and shiny metallic powder, poses a considerable challenge to automated defect detection. Two mainstream methods are currently used to tackle this challenge: global information-based and attention mechanism-based methods. However, these methods lack the capability to integrate valuable global-to-local information and explore deeper distinguishable features, thereby affecting the overall detection performance. To address this issue, we propose a novel attention enhanced global–local refined detection network (AEGLR-Net), which can perform effective global-to-local refined feature extraction and fusion. First, we design an adaptive Transformer–CNN tandem backbone (ATCT-backbone) to dynamically aware valuable global information and integrate local details to comprehensively extract specific features between defects and complex backgrounds. Then, we propose a novel refined cross-dimensional aggregation (RCDA) attention to facilitate the point-to-point interaction of multidimensional information, effectively emphasizing the representation of deeper discriminative defect features. Finally, we construct an attention-embedded flexible feature pyramid network (AE-FFPN), which incorporates the RCDA attention to guide the feature pyramid network in targeted feature fusion, thereby enhancing the efficiency of feature fusion in the detection model. Extensive comparative experiments demonstrate that the AEGLR-Net outperforms state-of-the-art approaches, attaining exceptional performance with 89.2 % mAP (mean average precision) and 85.5 FPS (frames per second).

When gripping delicate workpieces such as a silicon wafer, contact should be minimized to protect the workpiece. Some existing suction grippers can grip a workpiece with only three contact points on its upper surface, which is minimal to fully constrain the workpiece. Further reducing the contact points will make the workpiece under-constrained and thus difficult to grip. This paper develops a new suction gripper that can grip an under-constrained workpiece with only two contact points at the edge of its upper surface. The uniqueness of the new gripper lies in that it uses feedback control to stabilize the unstable motion of the under-constrained workpiece. First, to overcome the negative-stiffness effect that makes the under-constrained gripping unstable, a zero-stiffness suction unit based on closed-loop pressure feedback is developed via optimal design. Next, a cooperative actuating mechanism based on four suction units is designed to actuate the workpiece in four different DOFs individually, so that the workpiece can be levitated stably with the contact forces being controlled. Finally, the dynamics of the gripping system is modeled, and an adaptive robust controller is designed based on the dynamics model. With the proposed controller, the gripper can handle workpieces with unknown inertial parameters and irregular upper surfaces. Experiments were conducted to verify the new suction gripper with the proposed controller.

Worn tools might lead to substantial detrimental implications on the surface integrity of workpieces for precision/ultra-precision machining. Most previous research has heavily relied on singular information, which might not be appropriate enough to ascertain tool conditions and guarantee the accuracy of workpieces. This paper proposes a CNN-LSTM hybrid model directly utilizing tool images to predict surface roughness on machined parts for tool condition assessment. This work first performs pruning based on UNet3+ architecture to eliminate redundant structures while integrating attention mechanisms to enhance the model's focus on the target region. On this basis, tool wear region information is intensely mined and heterogeneous data is optimized using Spearman correlation analysis. Subsequently, we innovatively proposed a hybrid model that integrates CNN and RNN, endowing the model with the ability to process spatial and sequential information. The effectiveness of the proposed methodology is validated using the practical data obtained from cutting experiments. The results indicate that the proposed tool condition assessment methodology significantly improves the segmentation accuracy of the tool wear region to 94.52 % (Dice coefficient) and predicts the surface roughness of machined parts with an accuracy exceeding 93.1 % (R²). It can be observed that the developed methodology may provide an effective solution for accurate tool condition assessment and the implementation of tool health management.

In recent years, the rapid development of information technology represented by the new generation of artificial intelligence has brought unprecedented impacts, challenges, and opportunities to the transformation of the manufacturing industry and the evolution of manufacturing models. In the past decade, a variety of new manufacturing systems and models have been proposed, with cloud manufacturing being one such representative manufacturing system. In this study, the overall research progress and existing key scientific issues in cloud manufacturing are analyzed. Combining with current cloud–edge collaboration, digital twin, edge computing, and other technologies, a deeply integrated human–machine–object manufacturing system based on cloud–edge collaboration is proposed. We call it cloud-edge collaborative manufacturing (CeCM). The similarities and differences between cloud-edge collaborative manufacturing with cloud manufacturing are analyzed from the system architecture level. The cloud-edge collaborative manufacturing is divided into three major spaces, including a physical reality space, a virtual resource space, and a cloud service space. Based on the above division, a five-layer architecture for cloud-edge collaborative manufacturing is proposed, including a manufacturing resource perception layer, an edge application service layer, a cloud–edge collaboration layer, a cloud–edge service layer, and a cloud–edge application layer. All the layers build a manufacturing system that deeply integrates manufacturing resources, computer systems, and humans, machines, and objects. Its overall system operation process is explained based on the above architecture design, and its 12 types of collaboration features of cloud–edge collaborative manufacturing are explained. In this paper, we also summarize 5 categories of key technology systems for cloud-edge collaborative manufacturing and 21 supporting key technologies. Under the framework of the above, a cloud–edge collaborative manufacturing for 3D printing was developed, and an application scenario for the petroleum equipment field was constructed. In a word, we believe the cloud-edge collaborative manufacturing will offer a new opportunity for the development of manufacturing network, digitalization and intelligence, providing a new technical path for the evolution of cloud manufacturing model and further promoting precision manufacturing services anytime, anywhere, and on demand.

The Advancements in tactile sensors and machine learning techniques open new opportunities for achieving intelligent grasping in robotics. Traditional robot is limited in its ability to perform autonomous grasping in unstructured environments. Although the existing robotic grasping method enhances the robot's understanding of its environment by incorporating visual perception, it still lacks the capability for force perception and force adaptation. Therefore, tactile sensors are integrated into robot hands to enhance the robot's adaptive grasping capabilities in various complex scenarios by tactile perception. This paper primarily discusses the adaption of different types of tactile sensors in robotic grasping operations and grasping algorithms based on them. By dividing robotic grasping operations into four stages: grasping generation, robot planning, grasping state discrimination, and grasping destabilization adjustment, a further review of tactile-based and tactile-visual fusion methods is applied in related stages. The characteristics of these methods are comprehensively compared with different dimensions and indicators. Additionally, the challenges encountered in robotic tactile perception is summarized and insights into potential directions for future research are offered. This review is aimed for offering researchers and engineers a comprehensive understanding of the application of tactile perception techniques in robotic grasping operations, as well as facilitating future work to further enhance the intelligence of robotic grasping.

The use of mobile robots for machining large components has received considerable research interest for the application of industrial robots in the machinery manufacturing sector. However, the low structural stiffness of industrial robots can result in poor machining quality under the action of cutting forces. Therefore, this paper proposes a simultaneous optimization method the mobile robot base position and cabin angle using homogeneous stiffness domain (HSD) index for large spacecraft cabins. First, a nonlinear joint stiffness model that considers the gravity compensator mechanism is established to describe the stiffness characteristics of heavy-duty robots more accurately. Subsequently, a HSD index is proposed to evaluate the overall stiffness values and stiffness fluctuation for all robot postures in the machining program. An optimization model is then established based on the HSD under the constraints of machining accessibility, joint angle limitation and singularity. The optimal base position and cabin angle are determined simultaneously using the sparrow search algorithm. Finally, simulation and milling experiments are used to demonstrate that the optimization method proposed in this paper can effectively improve the machining quality.