Graduate Thesis Or Dissertation
 

A hierarchical neuro-evolutionary approach to small quadrotor control

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/ws859j04z

Descriptions

Attribute NameValues
Creator
Abstract
  • Quadrotors are unique among Micro Aerial Vehicles in providing excellent maneuverability (as opposed to winged flight),while maintaing a simple mechanical construction (as opposed to helicopters). This mechanical simplicity comes at a cost of increased controller complexity. Quadrotors are inherently unstable, in the sense that they are essentially unflyable by a human without stability assistance. Prior work has developed model-based controllers that successfully control quadrotors operating near hover conditions, but small quadrotor dynamics make such control more difficult. In this thesis,we present a hierarchical neuro-controller for small (0.5 kg) quadrotor control. The first stage of control aims to stabilize the craft and outputs rotor speeds based on a requested attitude (pitch, roll, yaw, and vertical velocity). This controller is developed in four parts around each of the variables, initially training them to achieve results similar to a PID controller. The four parts are then combined and the controller is trained further to increase robustness. The second stage of control aims to achieve a requested(x,y,z) position by providing the first stage with the appropriate attitude. The simulation results show that stable quadrotor control is achieved through this control architecture. In addition, the results show that the hierarchical control approach recovers from discrete angle disturbances over an order of magnitude faster than a basic PID controller, and can even recover from a disturbance that knocks the craft upside down. Finally, using the average volume used to maintain a stable hover, we show that the hierarchical controller provides stable flight in the presence of 5 times more sensor noise and 8 times more actuator noise as compared to the PID controller.
License
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Publisher
Peer Reviewed
Language
Replaces

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details ShepherdJackFIII2009.pdf 2017-08-07 Public Download