mirage   mirage   mirage

Learning based methods applied to the MAV control problem

DSpace/Manakin Repository

Show simple item record

dc.contributor.advisor Tumer, Kagan
dc.creator Salichon, Max
dc.date.accessioned 2009-12-17T18:24:50Z
dc.date.available 2009-12-17T18:24:50Z
dc.date.copyright 2009-12-04
dc.date.issued 2009-12-17T18:24:50Z
dc.identifier.uri http://hdl.handle.net/1957/13669
dc.description Graduation date: 2010 en
dc.description.abstract This thesis addresses Micro Aerial Vehicle (MAV) control by leveraging learning based techniques to improve robustness of the control system. Applying classical control methods to MAVs is a difficult process due to the complexity of the control laws with fast and highly non-linear dynamics. These methods are mostly based on models that are diffcult to obtain for dynamic and stochastic environments. Due to their size, MAVs are affected by wind gusts and perturbations that push the limits of model based controllers where the linear approximation no longer holds. Instead, we focus on a control strategy that learns to map MAV states (e.g., heading, altitude, velocity) to MAV actions (e.g., actuator positions) to achieve good performance (e.g., flight time, minimal altitude and heading error) by maximizing an objective function. The main difficulty with this approach is defining the objective function and tuning the learning parameters to achieve the desired results. These learning based techniques have been used with great success in many domains with similar dynamics and are shown to improve MAV robustness with respect to wind gusts, perturbations, and actuator failure. Our results show significant improvements in response times to minor altitude and heading corrections over a traditional PID controller. In addition, we show that the MAV response to maintaining altitude in the presence of wind gusts improves by a factor of five. Similarly, we show that the MAV response to maintaining heading in the presence of turbulence improves by factors of three. Finally, we show significant improvements in the case of control surface actuator failure when using a multiagent system. The multiagent control system performs up to 8 times better than the PID controller when tracking a target heading. en
dc.language.iso en_US en
dc.subject MAV en
dc.subject Learning en
dc.subject Multiagent en
dc.subject UAV en
dc.subject.lcsh Micro air vehicles en
dc.subject.lcsh Drone aircraft -- Control systems en
dc.title Learning based methods applied to the MAV control problem en
dc.type Thesis/Dissertation en
dc.degree.name Doctor of Philosophy (Ph. D.) in Mechanical Engineering en
dc.degree.level Doctoral en
dc.degree.discipline Engineering en
dc.degree.grantor Oregon State University en
dc.contributor.committeemember Batten, Belinda
dc.contributor.committeemember Paasch, Robert
dc.contributor.committeemember Bailey, Mike
dc.contributor.committeemember Haller, Merrick


The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Search ScholarsArchive@OSU


Advanced Search

Browse

My Account

Statistics