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

Antonelo, Eric Aislan; Baerlvedt, Albert-Jan; Rognvaldsson, Thorsteinn; Figueiredo, Mauricio

doi:10.1109/IJCNN.2006.246723

Reference : Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navi...


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/36482

Title :	Modular Neural Network and Classical Reinforcement Learning for Autonomous Robot Navigation: Inhibiting Undesirable Behaviors
Language :	English
Author, co-author :	Antonelo, Eric Aislan [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) >]
	Baerlvedt, Albert-Jan [> >]
	Rognvaldsson, Thorsteinn [> >]
	Figueiredo, Mauricio [> >]
Publication date :	2006
Main document title :	The 2006 IEEE International Joint Conference on Neural Network Proceedings
Pages :	498-505
Peer reviewed :	Yes
Audience :	International
ISBN :	0-7803-9490-9
City :	Vancouver, BC
Event name :	2006 International Joint Conference on Neural Networks (IJCNN)
Event date :	16-07-2006 21-07-2006
Abstract :	[en] Classical reinforcement learning mechanisms and a modular neural network are unified to conceive 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. Different design apparatuses are considered to compose a system to tackle with these navigation difficulties, for instance: 1) neuron parameter to simultaneously memorize neuron activities and function as a learning factor, 2) reinforcement learning mechanisms to adjust 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.
Permalink :	http://hdl.handle.net/10993/36482
DOI :	10.1109/IJCNN.2006.246723
Other URL :	https://ieeexplore.ieee.org/document/1716134/

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	2006_eric_ijcnn_modular.pdf		Author postprint	471.36 kB	View/Open

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices