Generation of optimal routes in a neural network based AGVcontroller

摘要

Due to the increasing complexity of factory floor environmentscoupled with the need for increased flexibility in automated guidedvehicle (AGV) systems, it is becoming increasingly important to be ableto dynamically alter both the AGV job queue and the AGV path. In aprevious paper, a new method based on an artificial neural network modelwas presented for evaluating the best job assignment so as to achievebetter system efficiency. This scheme generated the best set ofworkstations or loading points for a given AGV to visit, given thecurrent status of both the AGV fleet and the waiting job requests. Thenext stage in the control strategy is to find the optimal route betweenthe workstations on the list. In this paper, a new navigation techniquefor AGV's based on the A* search algorithm called `forward-reversesearch' is presented which fits into our neural network based controlstructure