Research on AGV Path Planning Optimization based on Visual Positioning and Machine Learning

Machine learning method for optimizing path planning device data system is a kind of network system with limited energy and resource. The key factor of energy use balance in optimizing path planning extends the whole optimization path planning. The life cycle is an important goal of machine learning method system design for optimizing path planning device data. This study is based on the practice of the AGV visual positioning allocation system based on AGV visual positioning, and gives several optimization schemes. Among them, the current AGV visual positioning status of the key factors is regarded as a factor to evaluate the possibility of transformation, so that the sustainability of the key factors of efficient path planning in the process of optimizing path planning is enhanced. Based on the geographic location data of the key factors, these data are integrated into the calculation of the transition probability, so that the key factors can keep their direction in the process of finding the path planning. In this study, AGV visual positioning was used to simulate the optimized strategy, and then compared with the preliminary AGV visual positioning. The results of the simulation showed that the optimized strategy was optimized compared with the other two algorithms in increasing the life of key factors and ensuring the AGV visual positioning balance of optimized path planning.