doctoral dissertation, tech. report CMU-RI-TR-12-11, Robotics Institute, Carnegie Mellon University, June, 2012
|An urban operation of unmanned aerial vehicles (UAVs) demands a high level of autonomy for tasks presented in a cluttered environment. While ﬁxed-wing UAVs are well suited for long-endurance missions at a high altitude, enabling them to navigate inside an urban area brings another level of challenges. Their inability to hover and low agility in motion cause more difficulties on ﬁnding a feasible path to move safely in a compact region, and the limited payload allows only low-grade sensors for state estimation and control.
We address the problem of achieving vision-based autonomous navigation for a small ﬁxed-wing in an urban area with contributions to the following several key topics. Firstly, for robust attitude estimation during dynamic maneuvering, we take advantage of the line regularity in an urban scene, which features vertical and horizontal edges of man-made structures. The sensor fusion with gravity-related line segments and gyroscopes in a Kalman ﬁlter can provide driftless and realtime attitude for ﬂight stabilization. Secondly, as a prerequisite to sensor fusion, we present a convenient self-calibration scheme based on the factorization method. Natural references such as gravity, vertical edges, and distant scene points, available in urban ﬁelds, are suﬃcient to ﬁnd intrinsic and extrinsic parameters of inertial and vision sensors. Lastly, to generate a dynamically feasible motion plan, we propose a discrete planning method that encodes a path into interconnections of ﬁnite trim states, which allow a signiﬁcant dimension reduction of a search space and result in naturally implementable paths integrated with ﬂight controllers. The most probable path to reach a target is computed by the Markov Decision Process with motion uncertainty due to wind, and a minimum target observation time is imposed on the ﬁnal motion plan to consider a camera’s limited ﬁeld-of-view.
In this thesis, the effectiveness of our vision-based navigation system is demonstrated by what we call an ”air slalom” task in which the UAV must autonomously search and localize multiple gates, and pass through them sequentially. Experiment results with a 1m wing-span airplane show essential navigation capabilities demanded in urban operations such as maneuvering passageways between buildings.
|Unmanned aerial vehicle, ﬁxed-wing airplane, autonomous navigation, vision-based attitude estimation, sensor calibration, sampling-based motion planning, air-slalom task|
Number of pages: 143
|Myung Hwangbo, "Vision-Based Navigation for a Small Fixed-Wing Airplane in Urban Environment ," doctoral dissertation, tech. report CMU-RI-TR-12-11, Robotics Institute, Carnegie Mellon University, June, 2012|
author = "Myung Hwangbo",
title = "Vision-Based Navigation for a Small Fixed-Wing Airplane in Urban Environment ",
booktitle = "",
school = "Robotics Institute, Carnegie Mellon University",
month = "June",
year = "2012",
address= "Pittsburgh, PA",
|The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.|
Contact Us | Update Instructions