On-line sequence limit learning machine method possessing autonomous learning capability

Abstract

The invention relates to an on-line sequence limit learning machine method possessing an autonomous learning capability and belongs to the intelligent robot technology field. Nine portions are included and comprise an external state set, an external motion set, a rewarding signal, a value function, a state transition equation, a limit learning machine network hidden layer output set, an intermediate parameter transfer equation, a limit learning machine output set and a limit learning machine output weight transfer equation. In the on-line sequence limit learning machine method possessing the autonomous learning capability, an on-line sequence limit learning machine is taken as a framework and Q learning is combined and reinforced. The on-line sequence limit learning machine method possessing the autonomous learning capability is provided and a model is used in mobile robot path program research so that a robot realize autonomous learning navigation according to an external environment state and rewarding. An autonomous learning capability of the robot in an unknown environment is increased.

Description

technical field [0001] The invention relates to an online sequence extreme learning machine method with autonomous learning ability, belonging to the technical field of intelligent robots. Background technique [0002] In view of the problems of low initiative and convergence in the existing cognitive development methods and the slow learning speed of BP network, which is easy to fall into local optimum, this patent combines the characteristics of the extreme learning machine network to randomly obtain input weights and thresholds to speed up learning and training Speed, to avoid falling into the local optimal solution, but also improve the active learning performance of the agent. [0003] Exploring the mechanism of cognitive development, constructing the mechanism of cognitive development, and endowing these mechanisms to robots are important topics in the research of artificial intelligence and robotics, cognitive science, neurophysiology and developmental psychology. ...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problems of high dimensionality, difficult training and slow learning speed in the application of BP neural network in path planning of mobile robots, an enhanced Q-learning method (Q-learning) based on online sequence extreme learning machine is proposed and applied to mobile robots In the path planning research, through the reward (punishment) value of the external environment to the robot action, feedback is given to the robot system to complete autonomous cognitive learning

Images