Classical reinforcement learning mechanisms and a modular neural network are unified for conceiving an intelligent autonomous system for mobile robot navigation. The conception aims at inhibiting two common navigation deficiencies: generation of unsuitable cyclic trajectories and ineffectiveness in risky configurations. Distinct design apparatuses are considered for tackling these navigation difficulties, for instance: 1) neuron parameter for memorizing neuron activities (also functioning as a learning factor), 2) reinforcement learning mechanisms for adjusting neuron parameters (not only synapse weights), and 3) a inner-triggered reinforcement. Simulation results show that the proposed system circumvents difficulties caused by specific environment configurations, improving the relation between collisions and captures.
Modular neural network and classical reinforcement learning for autonomous robot navigation: inhibiting undesirable behaviors
2006-01-01
IEEE International Joint Conference on Neural Networks (IJCNN) ; ISSN: 1098-7576 ; ISBN: 9780780394902
Conference paper
Electronic Resource
English
DDC: | 629 |
Autonomous Quantum Reinforcement Learning for Robot Navigation
Springer Verlag | 2016
|Behaviors Coordination and Learning on Autonomous Navigation of Physical Robot
BASE | 2011
|Efficient reinforcement learning of navigation strategies in an autonomous robot
BASE | 1994
|