Significance: Artificial skin (AS) is widely used in dermatology, pharmacology, and toxicology, and has great potential in transplant medicine, burn wound care, and chronic wound treatment. There is a great demand for high-quality AS product and a non-invasive detection method is highly desirable.Aim: To quantify the constructure parameters (i.e., thickness and surface roughness) of AS samples in the culture cycle and explore the growth regularities using optical coherent tomography (OCT).Approach: An adaptive interface detection algorithm is developed to recognize surface points in each A-scan, offering a rapid method to calculate parameters without constructing OCT B-scan pictures and further achieving realizing real-time quantification of AS thickness and surface roughness. Experiments on standard roughness plates and H&E-staining microscopy were performed as a verification.Results: As applied on the whole cycle of AS culture, our method's results show that during the air-liquid culture, the surface roughness of the skin first decreases and then exhibits an increase, which implies coincidence with the degree of keratinization under a microscope. And normal and typical abnormal samples can be differentiated by thickness and roughness parameters during the culture cycle. Conclusions:The adaptive interface detection algorithm is suitable for high-sensitivity, fast detection, and quantification of the interface with layered characteristic tissues, and can be used for non-destructive detection of the growth regularity of AS sample thickness and roughness during the culture cycle.

This paper proposes a method for automatic adjustment of PID(Proportion Integration Differentiation) based on deep reinforcement learning in order to solve the problem of smooth movement of AGV(Automated Guided Vehicle). First, based on reinforcement learning, the problem of AGV smooth operation is transformed into the solution of PID adjustment operation sequence. The action value model is constructed using the Deep Q-Learning Network(DQN) algorithm. Then, take the AGV adjustment PID as the research object. The goal is to achieve smooth movement of AGV. The specific design of AGV automatic PID adjustment method based on deep reinforcement learning is introduced. Finally, the simulation data is used to train the AGV action value network model. The method is validated in the ROS(Robot Operating System) simulation environment. Then compare with the actual environment. The results show that the automatic adjustment method of AGV’s PID based on deep reinforcement learning can adjust PID to the optimum without manual work. It can make AGV run smoothly. The feasibility and effectiveness of the method are illustrated and the problem of automatic PID determination in AGV movement control is solved.

This paper designs and implements an AGV scheduling application based on spring framework. This application consists of four modules, intelligent scheduling module, traffic control module, equipment management module and communication protocol module. Through interaction with AGV vehicle-mounted applications, the intelligent scheduling module realizes the function of automatic task allocation and vehicle body accepting tasks autonomously, which solves the problem of low efficiency of existing applications. Traffic control can avoid congestion by announcing node, path and area possession, which solves the problem of congestion that is easy to occur in multi-vehicle operation. The equipment management module realizes the management function of charging station, temporary parking point and other equipment; Communication protocol module to solve the vehicle, equipment, applications between the information encryption, protocol definition and other functions.