In order to explore the application of robots in intelligent supply-chain and digital logistics, and to achieve efficient operation, energy conservation, and emission reduction in the field of warehousing and sorting, we conducted research in the field of unmanned sorting and automated warehousing. Under the guidance of the theory of sustainable development, the ESG (Environmental Social Governance) goals in the social aspect are realized through digital technology in the storage field. In the picking process of warehousing, efficient and accurate cargo identification is the premise to ensure the accuracy and timeliness of intelligent robot operation. According to the driving and grasping methods of different robot arms, the image recognition model of arbitrarily shaped objects is established by using a convolution neural network (CNN) on the basis of simulating a human hand grasping objects. The model updates the loss function value and global step size by exponential decay and moving average, realizes the identification and classification of goods, and obtains the running dynamics of the program in real time by using visual tools. In addition, combined with the different characteristics of the data set, such as shape, size, surface material, brittleness, weight, among others, different intelligent grab solutions are selected for different types of goods to realize the automatic picking of goods of any shape in the picking list. Through the application of intelligent item grabbing in the storage field, it lays a foundation for the construction of an intelligent supply-chain system, and provides a new research perspective for cooperative robots (COBOT) in the field of logistics warehousing.

Order picking is the part with the highest proportion of operation cost and time in the warehouse. The characteristics of small-batch and multi-frequency current orders reduce the applicability of the traditional layout in the warehouse. Besides this, the improvement of the layout will also affect the picking path, such as the Chevron warehouse layout, and at present, there is a lack of research on order picking with multiple picking locations under non-traditional layouts. In order to minimize the order picking cost and time, and expand the research in this field, this paper selects the Chevron layout to design and describe the warehouse layout, constructs the picking walking distance model of Return-type, S-type and Mixed-type path strategies in the random storage Chevron layout warehouse, and uses the Cuckoo Search (CS) algorithm to solve the picking walking distance generated by the Mixed-type path. Compared with the existing single-command order picking research, the order picking problem of multi picking locations is more suitable for the reality of e-commerce warehouses. Moreover, numerical experiments are carried out on the above three path strategies to study the impact of different walking paths on the picking walking distance, and the performance of different path strategies is evaluated by comparing the order picking walking distance with the different number of locations to be picked. The results show that, among the three path strategies, the Mixed-type path strategy is better than the Return-type path strategy, and the average optimization proportion is higher than 20%. When the number of locations to be picked is less than 36, the Mixed-type path is better than the S-type path. With the increase of the number of locations to be picked, the Mixed-type path is gradually worse than the S-type path. When the number of locations to be picked is less than 5, the Return-type path is better than the S-type path. With the increase of the number of locations to be picked in the order, the S-type path is gradually better than the Return-type path.