Modular neural network and classical reinforcement learning for autonomous robot navigation: inhibiting undesirable behaviors

Sie sind hier: Homepage > Suche

Modular neural network and classical reinforcement learning for autonomous robot navigation: inhibiting undesirable behaviors

Freier Zugriff

Antonelo, Eric / 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.

Zugriff

Download

Exportieren, teilen und zitieren

Dokumentinformationen

Titel :

Modular neural network and classical reinforcement learning for autonomous robot navigation: inhibiting undesirable behaviors

Beteiligte:

Antonelo, Eric (Autor:in) / Baerveldt, Albert-Jan (Autor:in) / Rögnvaldsson, Thorsteinn (Autor:in) / Figueiredo, Mauricio (Autor:in)

Erscheinungsdatum :

2006-01-01

Anmerkungen:

IEEE International Joint Conference on Neural Networks (IJCNN) ; ISSN: 1098-7576 ; ISBN: 9780780394902

DOI :

https://doi.org/10.1109/IJCNN.2006.1716134

Medientyp :

Aufsatz (Konferenz)

Format :

Elektronische Ressource

Sprache :

Englisch

Schlagwörter :

Technology and Engineering , neural networks , autonomous robot navigation , reinforcement learning

Klassifikation :

DDC:

629

Modular neural network and classical reinforcement learning for autonomous robot navigation: inhibiting undesirable behaviors

Modular neural network and classical reinforcement learning for autonomous robot navigation: inhibiting undesirable behaviors

Zugriff

Exportieren, teilen und zitieren

Dokumentinformationen

Ähnliche Titel

Zugriff

Seitennavigation

Exportieren, teilen und zitieren