Publikace
Detail publikace
Citace
University of Southern Denmark, Campusvej 55, 5230 Odense, Denmark, 2016. : Classification of Terrain based on Proprioception and Tactile Sensing for Multi-legged Walking Robot . Master Thesis,
PDF ke stažení
Další informace
Abstrakt
Proprioception and tactile sensing in insect-like legged robots is a fast, illumination insensitive and biologically inspired way of ground perception. In this thesis, 14 virtually generated terrains are classified based on the mentioned sensor types for a simulated version of hexapod robot AMOS II. A feedforward neural network framework equipped with a novel network pruning algorithm has been developed for classification. We observe over 92% classification accuracy on deterministic terrain data and 72% on manually noised data. The pruning algorithm removes unimportant synapses (generally more than 90%) from a fully-connected network, while the classification accuracy does not drop significantly. The number of input neurons is reduced by 65%, resulting in the minimal network structure for the classification problem. A theory of using minimal structures for feature selection is proposed. The thesis outcome consists of a minimal neural network capable of terrain classification based on selected features of proprioceptive and tactile sensory signals.
Detail publikace
Název: | Classification of Terrain based on Proprioception and Tactile Sensing for Multi-legged Walking Robot |
---|---|
Autor: | M. Bulín |
Název - česky: | Klasifikace terénu založená na proprioreceptorech a hmatových senzorech mnohanohého chodícího robota |
Jazyk publikace: | anglicky |
Datum vydání: | 11.6.2016 |
Rok vydání: | 2016 |
Typ publikace: | Vysokoškolská kvalifikační práce (dizertační, habilitační) |
Název knihy: | Master Thesis |
Nakladatel: | University of Southern Denmark |
Místo vydání: | Campusvej 55, 5230 Odense, Denmark |
BibTeX
@MISC{MBulin_2016_Classificationof, author = {M. Bul\'{i}n}, title = {Classification of Terrain based on Proprioception and Tactile Sensing for Multi-legged Walking Robot }, year = {2016}, publisher = {University of Southern Denmark}, address = {Campusvej 55, 5230 Odense, Denmark}, booktitle = {Master Thesis}, url = {http://www.kky.zcu.cz/en/publications/MBulin_2016_Classificationof}, }