Purpose The purpose of this study is to achieve multi-variety and small-batch assembly through direct cooperation between equipment and people and to improve assembly efficiency as well as flexibility. Design/methodology/approach Firstly, the concept of the human–computer interaction is designed. Secondly, the machine vision technology is studied theoretically. Skin color filter based on hue, saturation and value color model is put forward to screen out images that meet the skin color characteristics of the worker, and a multi-Gaussian weighted model is built to separate moving objects from its background. Both of them are combined to obtain the final images of the target objects. Then, the key technology is applied to the smart assembly workbench. Finally, experiments are conducted to evaluate the role of the human–computer interaction features in improving productivity for the smart assembly workbench. Findings The result shows that multi-variety and small-batch considerable increases assembly time and the developed human–computer interaction features, including prompting and introduction, effectively decrease assembly time. Originality/value This study proves that the machine vision technology studied in this paper can effectively eliminate the interferences of the environment to obtain the target image. By adopting the human–computer interaction features, including prompting and introduction, the efficiency of manual operation is improved greatly, especially for multi-variety and small-batch assembly.

No abstract

Purpose The purpose of this paper is to study a method to optimize the arrangement of the devices on a smart assembly workbench, which help to reduce fatigue and improve efficiency for the worker. Design/methodology/approach The optimization priority is studied based on the users’ decisions, a mathematical model of the layout optimization is established from ergonomic perspective and an improved algorithm is adopted to solve the built the mathematical model. Findings Ergonomic software Jack is chosen to simulate the four layout schemes obtained. Through comparative analysis of the simulation results, it is proven that the optimal solution can be obtained using the improved algorithm. Originality/value The mathematical model built on observation comfort, operation comfort and device accessibility, as well as the improved algorithm in this paper, has some reference values for the layout design of smart assembly workbench.

At present, discrete workshops demand higher transportation efficiency, but the traditional scheduling strategy of the logistics systems can no longer meet the requirements. In a transportation system with multiple automated guided vehicles (multi-AGVs), AGV path conflicts directly affect the efficiency and coordination of the whole system. At the same time, the uncertainty of the number and speed of AGVs will lead to excessive cost. To solve these problems, an AGVs Multi-Objective Dynamic Scheduling (AMODS) method is proposed which is based on the digital twin of the workshop. The digital twin of the workshop is built in the virtual space, and a two-way exchange and real-time control framework based on dynamic data is established. The digital twin system is adopted to exchange data in real time, create a real-time updated dynamic task list, determine the number of AGVs and the speed of AGVs under different working conditions, and effectively improve the efficiency of the logistics system. Compared with the traditional scheduling strategy, this paper is of practical significance for the scheduling of the discrete workshop logistics systems to improve the production efficiency, utilization rate of resources, and dynamic response capability.

Six-dimensional pose estimation for non-Lambertian objects, such as metal parts, is essential in intelligent manufacturing. Current methods pay much less attention to the influence of the surface reflection problem in 6D pose estimation. In this paper, we propose a cross-attention-based reflection-aware 6D pose estimation network (CAR6D) for solving the surface reflection problem in 6D pose estimation. We use a pseudo-Siamese network structure to extract features from both an RGB image and a 3D model. The cross-attention layers are designed as a bi-directional filter for each of the inputs (the RGB image and 3D model) to focus on calculating the correspondences of the objects. The network is trained to segment the reflection area from the object area. Training images with ground-truth labels of the reflection area are generated with a physical-based rendering method. The experimental results on a 6D dataset of metal parts demonstrate the superiority of CAR6D in comparison with other state-of-the-art models.