Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation: Inhibiting Undesirable Behaviors

Abstract

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.