Sök personal

Sök bland våra professorer, lärare och övriga medarbetare

Personal vid Högskolan

Tillbaka

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

Antonelo, Eric A., Baerveldt, Albert-Jan, Rögnvaldsson, Thorsteinn, Figueiredo, Mauricio
2006

Konferensbidrag (Refereegranskat)

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.

Nyckelord: mobile robots; neurocontrollers; path planning

Citera: Antonelo, Eric A., Baerveldt, Albert-Jan, Rögnvaldsson, Thorsteinn & Figueiredo, Mauricio, Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation Inhibiting Undesirable Behaviors, International Joint Conference on Neural Networks, 2006. IJCNN '06., s. 498-505, 2006http://hh.diva-portal.org/smash/get/diva2:239330/FULLTEXT01.pdf