Year: 2012
Type: dissertation
Abstract: [eng] This part presents the motivation and the necessary background to introduce the reader in the main issues of this dissertation. Chapter 1 proceeds with the general motivation that lead to understand the importance of the algorithms presented in this dissertation, circumscribed in the context of navigation strategies for autonomous robots. Next, the principal requirements for the new algorithms are outlined. The aim is overcoming several limitations encountered in other visual approaches, and designing a system suitable in environmental conditions as general as possible. Chapter 2 examines in the first section the different types of control architectures for mobile robots, emphasizing and reviewing the concepts of deliberative, reactive, map-based or mapless systems. The second section of this chapter introduces the background of the localization problem. Chapter 3 surveys the most outstanding approaches on visual navigation from the final eighties up to nowadays. The review of all these pieces of work places the reader into the main problems encountered during all these years concerning how to extract and interpret the environmental information from digital images. Reviewing a wide range of visual navigation approaches leads to a complete comprehension of what has been done until the moment and what is still remaining to be done. Of course, all these pieces of work have been an important source of inspiration for this research.
Author: Francisco Jesús Bonin Font
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2530884111