Lokalizacija mobilnega robota s pomočjo večsmerne kamere

diplomsko delo

Iztok Oder (Author), Danijel Skočaj (Mentor)

Abstract

Roboti bodo v prihodnosti v veliki meri zamenjali človeško delovno silo. Biti bodo morali čimbolj avtonomni, kar vklučuje tudi samostojno navigacijo po prostoru. Za uspešno navigacijo je potrebno najprej poznati svojo pozicijo v svetu. Obstaja veliko metod, ki se ukvarjajo z lokalizacijo. Običajno te metode uporabljajo podatke zajete z globinskimi senzorji. V diplomskem delu se osredotočimo na lokalizacijo s pomočjo panoramskih slik zajetih z večsmerno kamero. Lokalizacijo izvajamo s pomočjo statističnih metod PCA, KPCA, CCA in KCCA. Iz učnih slik s temi metodami izračunamo nizkodimenzionalne podprostore na katere jih potem tudi projeciramo. Tako dobimo model okolja, v katerem se robot nahaja. S tem modelom lahko napovemo predvidene lokacije testnih slik. Vse metode implementiramo za interaktivno lokalizacijo s pomočjo robota ATRV mini. Natančnost lokalizacije v delu tudi ovrednotimo in podamo nekaj predlogov za izboljšavo celotnega sistema.

Keywords

lokalizacija;panoramske slike;PCA;KPCA;CCA;KCCA;robot;robotski operacijski sistem;večsmerna kamera;računalništvo;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2014
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[I. Oder]
UDC:	004.8(043.2)
COBISS:	1536094147
Views:	2328
Downloads:	513
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Mobile robot localization using an omnidirectional camera
Secondary abstract:	In future, robots will largely replace human labour. They will have to be as autonomous as possible. This includes the ability to self-navigate through space. A successful navigation requires the knowledge of one's location in space. Many methods that deal with the problem of self-localization exist. Usually these methods use data acquired with a depth sensor. In this thesis we explore the possibilities of self-localization using only panoramic images obtained with omnidirectional camera. Localization is performed using statistical methods PCA, KPCA, CCA and KCCA. These methods produce a low-dimensional subspace from high-dimensional input images. These images are than projected onto the subspace, which gives us an alternative representation of the environment that can be used for predicting the locations of test images. All methods are implemented for use with mobile robot ATRV mini. The accuracy of self-localization is evaluated and few suggestions for the improvement are proposed.
Secondary keywords:	self-localization;panoramic images;PCA;KPCA;CCA;KCCA;robot;robot operating system;omnidirectional camera;computer science;computer and information science;diploma;
File type:	application/pdf
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000468
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	75 str.
ID:	8739438