Year: 2023
Type: dissertation
Abstract: A significant majority of the state of the art autonomous sensing and navigation technologies rely on good lane markings or detailed 3D maps of the environment and are more suited for urban communities. On the other hand, a large number of rural roads in the U.S. do not have lane markings and have irregular boundaries. These challenges are common to many small and rural communities (SRCs), defined as an incorporated city, town or village with a population of less than 50,000. These communities are sparsely connected and cover huge areas. The objective of this work is to develop an efficient sensing and navigation system for SRCs. To this end we develop a novel Rural Road Detection dataset for training and evaluation of sensing algorithms. We also propose road descriptors along with an initialization technique for localization that allows for fast global pose estimation on crowd sourced topological maps such as the Open Street Map (OSM). We test our algorithms on (real world) maps and benchmark them against other map based localization as well as SLAM algorithms. Our results show that the proposed method can narrow down the pose to within 50 centimeters of the ground truth significantly faster than the state of the art methods.
Author: Ninan, Stephen Thomas
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7005016493
