Information processing device and information processing method

An information processing method executed in an information processing device, the information processing method comprising:

• generating, by a processor, a camera-captured image corresponding to a movement of a robot, wherein the movement of the robot is by a user operation, and the movement is based on teaching data and movement position information of the robot as learning data;
• executing, by the processor, a machine learning process based on input of the learning data;
• generating, by the processor, a teaching data set including correspondence data between the camera-captured image and a behavior rule of the robot as learning result data;
• controlling, by the processor, input of the learning data and the learning result data;
• executing, by the processor, evaluation of the teaching data applied to the user operation;
• generating, by the processor, visual feedback information including one of a specific image or a graph, wherein the specific image or the graph is generated based on an evaluation result of the teaching data applied to the user operation as feedback information, and the feedback information is generated based on the evaluation result;
• generating, as the visual feedback information by the processor, one of:
• score graph display data obtained based on graph of scores corresponding to an evaluation value of the teaching data applied to the user operation,
• high score region instruction data indicating a region having a high score corresponding to the evaluation value of the teaching data,
• a color-changed image of the camera-captured image,
• first identification graph data indicating similarity or a degree of difference between the teaching data applied to the user operation and teaching data executed in a past,
• second identification graph data indicating similarity or a degree of difference between:
• latent feature data generated by compressing feature data acquired from the camera-captured image corresponding to the movement of the robot using the teaching data applied to the user operation, and
• latent feature data generated by compressing feature data acquired from the camera-captured image corresponding to the movement of the robot using the teaching data executed in the past, or
• comparison data between a movement trajectory of the robot using the teaching data applied to the user operation and a movement trajectory of the robot using the teaching data executed in the past;
• and
• controlling, by the processor, output of the visual feedback information to an output unit.

A non-transitory computer-readable medium having stored thereon, computer-executable instructions which, when executed by a computer, cause the computer to execute operations, the operations comprising:

• generating, as learning data, a camera-captured image corresponding to a movement of a robot, wherein the movement of the robot is by a user operation, and the movement is based on teaching data and movement position information of the robot;
• executing a machine learning process based on input of the learning data;
• generating a teaching data set including correspondence data between the camera-captured image and a behavior rule of the robot as learning result data;
• controlling input of the learning data and the learning result data;
• executing evaluation of the teaching data applied to the user operation;
• generating, as feedback information, visual feedback information including one of a specific image or a graph, wherein the specific image or the graph is generated based on an evaluation result of the teaching data applied to the user operation, and the feedback information is generated based on the evaluation result;
• generating, as the visual feedback information, one of:
• score graph display data obtained based on graph of scores corresponding to an evaluation value of the teaching data applied to the user operation,
• high score region instruction data indicating a region having a high score corresponding to the evaluation value of the teaching data,
• a color-changed image of the camera-captured image,
• first identification graph data indicating similarity or a degree of difference between the teaching data applied to the user operation and teaching data executed in a past,
• second identification graph data indicating similarity or a degree of difference between:
• latent feature data generated by compressing feature data acquired from the camera-captured image corresponding to the movement of the robot using the teaching data applied to the user operation, and
• latent feature data generated by compressing feature data acquired from the camera-captured image corresponding to the movement of the robot using the teaching data executed in the past, or
• comparison data between a movement trajectory of the robot using the teaching data applied to the user operation and a movement trajectory of the robot using the teaching data executed in the past;
• and
• outputting the visual feedback information to an output unit.