Robot and control method thereof

A method of controlling a robot, the method comprising:

• identifying, based on sensing data obtained through a light detection and ranging (LiDAR) sensor of the robot, an object in a vicinity of the robot;
• identifying, based on a type of the object, a weight to apply to an audio signal received through a directional microphone of the robot corresponding to a location of the object from among plurality of directional microphones of the robot;
• obtaining context information of the robot based on the sensing data, the context information including first context information on a space in the vicinity of the robot and second context information on a driving state of the robot;
• identifying, based on the first context information and the second context information, a pre-processing model corresponding to each respective directional microphone of the plurality of directional microphones;
• applying the weight to the audio signal received through the directional microphone corresponding to the location of the object among a plurality of audio signals received through the plurality of directional microphones;
• obtaining a plurality of pre-processed audio signals by inputting the audio signal to which the weight has been applied, and a remainder of the plurality of audio signals other than the audio signal to which the weight has been applied, into the pre-processing model corresponding to the respective directional microphone;
• performing voice recognition based on the plurality of pre-processed audio signals;
• and
• controlling an operation of the robot based on a result of the voice recognition.

A non-transitory computer readable medium having instructions stored therein, which when executed by a processor cause the processor to execute a method of controlling a robot, the method comprising:

• identifying, based on sensing data obtained through a light detection and ranging (LiDAR) sensor of the robot, an object in a vicinity of the robot;
• identifying, based on a type of the object, a weight to apply to an audio signal received through a directional microphone of the robot corresponding to a location of the object from among plurality of directional microphones of the robot;
• obtaining context information of the robot based on the sensing data, the context information including first context information on a space in the vicinity of the robot and second context information on a driving state of the robot;
• identifying, based on the first context information and the second context information, a pre-processing model corresponding to each respective directional microphone of the plurality of directional microphones;
• applying the weight to the audio signal received through the directional microphone corresponding to the location of the object among a plurality of audio signals received through the plurality of directional microphones;
• obtaining a plurality of pre-processed audio signals by inputting the audio signal to which the weight has been applied, and a remainder of the plurality of audio signals other than the audio signal to which the weight has been applied, into the pre-processing model corresponding to the respective directional microphone;
• performing voice recognition based on the plurality of pre-processed audio signals;
• and
• controlling an operation of the robot based on a result of the voice recognition.