System and method for pet automatic feeding control on basis of reinforcement learning

Abstract

The invention discloses a system and a method for pet automatic feeding control on the basis of reinforcement learning. The system mainly comprises a base body and a controller, wherein the controllerobtains an optimal feeding strategy through the following method: A, establishing a pet feeding model; B, modeling a pet feeding problem into a Markov decision process model, and modeling a state, anaction, a state transfer function and an immediate reward function in the Markov decision process model; C, establishing a return value function model; and D, solving the optimal feeding strategy byutilizing a Sarsa reinforcement learning algorithm; and the controller controls the amount of feeding every time according to the optimal feeding strategy. The system and the method provided by the invention facilitate saving food, is applicable to eating habits of various pets, can acquire general feeding data of various pets by self-learning without the need of supplying, can obtain the optimalfeeding strategy which is more accurate than a conventional feeding manner, and can dynamically amend the optimal feeding strategy according to changes of the environment.

Description

technical field [0001] The invention relates to a pet automatic feeding control system and method based on reinforcement learning. Background technique [0002] In today's society, more and more people keep pets at home. Many people are often away from home for a long time due to personal reasons, such as work, travel, etc., and have no time to feed the pets at home. So people invented the pet feeder. From the simple version of the funnel-type feeding device to the current device that the owner of the camera can interact with and remotely feed at any time. Although the pet feeder has undergone several generations of changes, the calculation of the food intake of the pet feeder is still unsatisfactory. Whether it is setting the amount of timed feeding or remote control feeding, there are many problems. Such as food waste and food staleness caused by prolonged exposure to air. Stale food cannot guarantee the health of pets, nor can it make the owners who go out really fee...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this system is that feeding pets quantitatively may cause food waste and deterioration caused by pet starvation or overfeeding

In addition, the system only controls the amount of food delivered through the opening and closing of a solenoid valve. When in use, the solenoid valve may be stuck by the pet food and cannot be completely closed, which will cause the pet food and air in the container to grow. Time contact, easy to cause deterioration

Images