Method, medium, device and equipment for seeking for indoor sound source based on reinforcement learning

Abstract

The invention relates to a method, a medium, a device and equipment for seeking for an indoor sound source based on reinforcement learning. The method comprises the following steps: collecting environmental information and a target sound signal; using a target seeking model trained by a reinforcement learning algorithm for generating an addressing action according to the environmental informationand the target sound signal; driving a moving object to move to a target sound source position corresponding to the target sound signal according to the addressing action. A computer programme is stored in the medium and is used for executing the steps of the method. A seeking device comprises a storage medium and a processor. The seeking equipment comprises a sound collection module, an environment sensing module, an addressing action generation module and a control module. The method, the medium, the device and the equipment provided by the invention can automatically learn related parameters so as to finish the seeking process, can reduce human intervention, have higher fault-tolerant ability and robustness, can greatly increase the success rate of once moving the moving object to the target sound source and can increase the seeking efficiency of target sound source.

Description

technical field [0001] The present invention relates to the field of machine learning and artificial intelligence, in particular to a method, medium, equipment and device for finding indoor sound sources based on reinforcement learning. Background technique [0002] The traditional sound source localization method mainly uses the microphone array to measure the propagation direction of the sound wave, and then estimates the sound source position, and then controls the robot to move to the sound source position provided by the sound source localization through robot navigation. In an indoor environment, due to the influence of walls and various items on sound wave propagation, it is difficult for these methods to estimate the location of sound sources in various situations, and there is noise interference, which affects the accuracy of sound source localization. There are other sound source localization methods to solve the problem of sound source localization in complex envi...

AI Technical Summary

Problems solved by technology

In an indoor environment, due to the influence of walls and various items on the propagation of sound waves, these methods are difficult to estimate the position of the sound source in various situations, and there is noise interference, which affects the accuracy of sound source localization

There are other sound source localization methods to solve the problem of sound source localization in complex environments by given indoor architectural layout, these methods are not accurate and not universal

Images