METHOD FOR TRAINING MULTIPLE ARTIFICIAL NEURAL NETWORKS TO ASSIGN CALLS TO CARS OF AN ELEVATOR

Abstract: a method for training neural networks to assign calls to elevator cars simulates an environment in which first and second cars move between building floors in reaction to calls indicating desired floors, each simulation including steps: determining a current state of the environment including a current position of each car, a list of current calls and a new call; inputting first and second input data encoding at least a part of the current state into respective first and second neural networks each configured to convert the input data into output values indicating a probability and/or tendency for the cars to be assigned to the new call; determining a selected car using the output values; assigning the new call to the selected car, and determining reward values quantifying a usefulness of the assignment; training the neural networks using past simulation reward values to increase the usefulness of future assignments.

Inventor(s): Nicola Ischia, Pedro Candeias Martins

CPC Classification: B66B1/06 (ELEVATORS; ESCALATORS OR MOVING WALKWAYS ({apparatus for raising or lowering persons on theatrical stages or the like } ; funicular railbound systems with rigid ground-supported tracks and cable traction, e.g. cliff railways, ; arrangements of ammunition handlers in vessels ; hoists, lifts, or conveyors for loading or unloading in general ; braking or detent devices controlling normal movements of winding drums or barrels ; ship-lifting devices ; garages for many vehicles with mechanical means for lifting vehicles ; hoists for feeding ammunition or projectiles to launching apparatus or to loading mechanisms ))

Search for rejections for patent application number 20250171270