Vision-based Autonomous Navigation and Active Sensing with Micro Aerial Vehicles

Author: 
Date created: 
2017-08-21
Identifier: 
etd10315
Keywords: 
Micro aerial vehicle
Visual odometry
Visual SLAM
Target following
Image-based modeling
Next best views
Abstract: 

Micro aerial vehicles (MAVs) equipped with cameras provide a new perspective on the world. As MAVs have found important roles in industrial and recreational applications, they are actively studied in the research community. The focus has been the autonomy level. In other words, the MAV should be able to perform tasks autonomously to free human from laborious and risky work. At the basis of an autonomous system, there is the problem of autonomous navigation. In outdoor spaces, MAVs usually use GPS signals for self-localization. In indoor GPS-denied environments, autonomous navigation of MAVs is still an open research question. At the high level of an autonomous system, there is the problem of active sensing. An autonomous platform needs to actively optimize its navigation based on its current state and the environment. The constraints of vision sensors and complex environments pose challenges to this task. In this thesis, we propose our solutions to the two problems: vision based navigation and active sensing. In the first half of the thesis, we propose solutions of vision based navigation on two platforms. First, we present an ultra-light and -small MAV platform which can perform autonomous navigation in an unknown indoor environment. Secondly, we aim at a toy MAV. Accurate path following is achieved using the camera as the major sensor. In the second half, we address the active sensing problem in two interesting applications. We first investigate the active target sensing and following using a multi-robot collaborative system. The only sensors are cameras and the constraints of vision algorithms are taken into consideration while we design the motion controller. Lastly, we demonstrate an active image data acquisition system in the image based modeling application. The camera placement is optimized in the loop and online feedback is provided for the sensor planning. We demonstrate the fully autonomous active image based modeling system in simulated, indoor and outdoor environments.

Document type: 
Thesis
Rights: 
This thesis may be printed or downloaded for non-commercial research and scholarly purposes. Copyright remains with the author.
File(s): 
Supervisor(s): 
Ping Tan
Richard Vaughan
Department: 
Applied Sciences: School of Computing Science
Thesis type: 
(Thesis) Ph.D.
Statistics: