Machine learning method and mobile robot

A machine learning method for a neural network that causes a computer to function to output a path for a mobile robot to move to a destination, based on provided map information and detected moving body information, the method comprising:

• a first learning step which is performed by a computing device other than the mobile robot in a phase before the neural network is installed in the mobile robot and in which a stationary first obstacle is placed in a set space and the first obstacle is placed at different positions using simulation such that the neural network repeatedly learns a path from a starting point to the destination which avoids the first obstacle;
• and
• a second learning step which is performed by the mobile robot in a phase after the neural network is installed in the mobile robot and in which, when the mobile robot recognizes a second obstacle that operates around the mobile robot in a space where the mobile robot moves, the neural network repeatedly learns a path to the destination which avoids the second obstacle every time the mobile robot recognizes the second obstacle.