A method according to the present disclosure includes (a) estimating pixel coordinate values of a plurality of characteristic points set in advance in a robot arm from an image of the robot arm taken by a camera using a first machine learning model, (b) estimating first coordinate values of the plurality of characteristic points in a 3D camera coordinate system from the pixel coordinate values of the plurality of characteristic points using a second machine learning model, (c) calculating second coordinate values of the plurality of characteristic points in a 3D robot coordinate system using an encoder value of the robot arm, and (d) executing the steps (a) through (c) with respect to a plurality of postures of the robot arm to estimate calibration parameters including an external parameter of the camera using the first coordinate values and the second coordinate values of the plurality of characteristic points in the plurality of postures.