The present disclosure generally relates to a robotic control system and method that utilizes active perception to gather the relevant information related to a robot, a robotic environment, and objects within the environment, and allows the robot to focus computational resources where needed, such as for manipulating an object. The present disclosure also enables viewing and analyzing objects from different distances and viewpoints, providing a rich visual experience from which the robot can learn abstract representations of the environment. Inspired by the primate visual-motor system, the present disclosure leverages the benefits of active perception to accomplish manipulation tasks using human-like hand-eye coordination.

A machine learning device in a component supply device includes: a state observation unit, a determination data acquisition unit, and a learning unit. The state observation unit observes state variables representing a current state of an environment. The state variables include (i) vibration operation parameter data representing an operation parameters for a vibration operation of a tray, (ii) component arrangement data representing an arrangement and a posture of components on the tray, and (iii) component kind data representing a kind of the components. The determination data acquisition unit acquires determination data representing a suitability determination result of the vibration operation, which represents efficiency in supply of the components. The learning unit learns the operation parameters, the component arrangement data, and the component kind data while associating the operation parameters with the component arrangement data and the component kind data, by using the state variable and the determination data.

A machine learning device included in a component supply device includes: a state observation unit that observes vibration operation parameter data representing an operation parameters for a vibration operation of a tray component arrangement data representing an arrangement and a posture of components on the tray, and component kind data representing a kind of the components, as a state variable representing a current state of an environment; a determination data acquisition unit that acquires determination data representing a suitability determination result of the vibration operation, which represents efficiency in supply of the components; and a learning unit that learns the operation parameters for the vibration operation, the component arrangement data, and the component kind data while associating the operation parameters for the vibration operation with the component arrangement data and the component kind data, by using the state variable and the determination data.