Display Publications by [Year] [Type] [Topic]
This paper addresses control surface segmentation in Micro Aerial Vehicles (MAVs) by leveraging neuro-evolutionary techniques that accommodate a higher number of control surfaces. A higher number of control surfaces increases the robustness of the MAV platform as well as allows for more control flexibility. This produces more efficient control strategies to improve maneuvers, stability and flight time of the MAV. 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 difficult to obtain for dynamic and stochastic environments. Moreover, these techniques could not be applied for controlling segmented control surfaces on an MAV platform since the optimal solution is unknown. Instead, we focus on segmenting the different control surfaces to allow more flexibility to the neuro-evolutionary based controller. Precise control is then achieved by neuro-evolutionary techniques that have been successfully applied in many domains with similar dynamics. Wind tunnel simulations with AVL show that MAV performances are improved both in terms of reduced deflection angles and reduced drag (up to 5\%) over a simplified model in two sets of experiments with different objective functions. Increased robustness to actuator failure is also achieved with desired roll moment values still attained with failed actuators in the system through neuro-controller reconfiguration.
@article{tumer-salichon_ijgs13,
author = {M. Salichon and K. Tumer},
title = {A Neuro-evolutionary Approach to Control Surface Segmentation for Micro Aerial Vehicles},
journal ={International Journal of General Systems} ,
publisher = {Taylor Francis},
volume={42},
pages={7},
pages = {793-805},
abstract ={This paper addresses control surface segmentation in Micro Aerial Vehicles (MAVs) by leveraging neuro-evolutionary techniques that accommodate a higher number of control surfaces. A higher number of control surfaces increases the robustness of the MAV platform as well as allows for more control flexibility. This produces more efficient control strategies to improve maneuvers, stability and flight time of the MAV. 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 difficult to obtain for dynamic and stochastic environments. Moreover, these techniques could not be applied for controlling segmented control surfaces on an MAV platform since the optimal solution is unknown. Instead, we focus on segmenting the different control surfaces to allow more flexibility to the neuro-evolutionary based controller. Precise control is then achieved by neuro-evolutionary techniques that have been successfully applied in many domains with similar dynamics. Wind tunnel simulations with AVL show that MAV performances are improved both in terms of reduced deflection angles and reduced drag (up to 5\%) over a simplified model in two sets of experiments with different objective functions. Increased robustness to actuator failure is also achieved with desired roll moment values still attained with failed actuators in the system through neuro-controller reconfiguration.},
bib2html_pubtype = {Journal Articles},
bib2html_rescat = {Robotics, Evolutionary Algorithms},
year = {2013}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 17:39:43