Sök bland våra professorer, lärare och övriga medarbetare
Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation : Inhibiting Undesirable Behaviors
Antonelo, Eric A., Baerveldt, Albert-Jan, Rögnvaldsson, Thorsteinn, Figueiredo, Mauricio
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.
Nyckelord: mobile robots; neurocontrollers; path planning