Intrinsically motivated extreme learning machine autonomous development system and operating method thereof

Abstract

The invention belongs to the technical field of intelligent robots, and concretely relates to an intrinsically motivated extreme learning machine autonomous development system and an operating method thereof. The autonomous development system comprises an inner state set, a motion set, a state transition function, an intrinsic motivation orientation function, a reward signal, a reinforced learning update iteration formula, an evaluation function and a motion selection probability. According to the invention, an intrinsic motivation signal is utilized to simulate an orientation cognitive mechanism of the interest of people in things so that a robot can finish relevant tasks voluntarily, thereby solving a problem that the robot is poor in self-learning. Furthermore, an extreme learning machine network is utilized to practice learning and store knowledge and experience so that the robot, if an experience fails, can use the stored knowledge and experience to keep exploring instead of learning from the beginning. In this way, the learning speed of the robot is increased, and a problem of low efficiency of reinforced learning for single-step learning is solved.

Description

technical field [0001] The invention belongs to the technical field of intelligent robots, and in particular relates to an intrinsic motivation-driven extreme learning machine self-development system and an operating method thereof. Background technique [0002] With the continuous development of intelligent technology in today's society, robot technology plays an extremely important role in people's production and life. It can not only replace humans to complete some relatively heavy tasks, but also improve work efficiency to a certain extent and save A lot of human resources. [0003] Intrinsic motivation is an extremely important concept in developmental psychology, and it is also a crucial mechanism for human open cognitive development. It drives agents to explore and manipulate the environment, cultivate their curiosity and participate in new activities of interest. This kind of motivation will be affected by many factors such as survival, curiosity, and tendency, so i...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to overcome the deficiencies in the motion control balance problem of existing two-wheeled self-balancing robots, and provides a self-development system of extreme learning machines driven by intrinsic motivation. As an intrinsic reward, drive the robot to learn, and use the extreme learning machine network as the storage space for knowledge accumulation. Through the learning model of the human brain, the robot can gradually form and improve its balance like a human through self-learning and self-organization. Control skills to solve the problem of poor initiative and low efficiency of previous reinforcement learning to single-step learning in the motion control balance problem of two-wheeled self-balancing robots

Images