Domestic safety protection robot and method based on deep enhanced learning

Abstract

The invention provides a domestic safety protection robot and method based on deep enhanced learning. The domestic safety protection robot based on deep enhanced learning comprises: a robot body, wherein a camera is installed on the robot body; the camera is used for collecting behavior state information of a target person and transmitting the behavior state information to a processor; the processor is also connected with a sensor module, and the sensor module is used for sensing the position of the target person and an obstacle position of an environment in which the target person is located;the processor is configured to: receive the behavior state information of the target person, the position of the target person, and the obstacle position of the environment in which the target personis located; lock the target person, avoid the obstacle and track the motion track of the target person; and an obstacle avoidance strategy is output by double high and low BP neural networks, the lower layer output is robot motion, and the high layer output is a terrain obstacle state.

Description

technical field [0001] The disclosure belongs to the field of protective robots, and in particular relates to a home security protective robot and method based on deep reinforcement learning. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] In recent years, the number of elderly empty-nest families in my country has been on the rise. When the elderly or children are alone at home, accidents are very likely to occur, and there are hidden dangers in safety issues, and they are very easy to become the target of criminals to commit crimes. Installing home monitoring has become a better choice now. Home monitoring devices continue to enter people's homes and are accepted by more people, but privacy and cost issues also need to be resolved. [0004] The inventors found that traditional home monitoring is deployed in every room of the home, wh...

AI Technical Summary

Problems solved by technology

[0004] The inventors found that traditional home monitoring is deployed in every room of the house, which is expensive and costly, with large power consumption and a large risk of large-scale leakage of family privacy.

Images