Kagan Tumer's Publications

Display Publications by [Year] [Type] [Topic]


A Learning Based Approach to Robust Micro Aerial Vehicle Control. M. Salichon and K. Tumer. IEEE Transactions on System, Man and Cybernetics--Part C, 42:1772–1783, 2012.

Abstract

Micro Aerial Vehicles (MAVs) are notoriously difficult to control as they are light, susceptible to minor fluctuations in the environment, and obey highly non-linear dynamics. Indeed, traditional control methods, particularly those relying on difficult to obtain models of the interaction between an MAV and its environment have been unable to provide adequate control beyond simple maneuvers. In this paper, we address the problem of controlling an MAV (which has segmented control surfaces) by evolving a neuro-controller and fine-tuning it using multiagent coordination techniques. This approach is based on a control strategy that learns to map MAV states (position, velocity) to MAV actions (e.g., actuator position) to achieve good performance (e.g., flight time) by maximizing an objective function. The main difficulty with this approach is defining the objective functions at the MAV level that allow good performance. In addition, to provide added robustness, we investigate a multiagent approach to control where each control surface aims to optimize a local objective. Our results show that this approach not only provides good MAV control, but provides robustness to (i) wind gusts by a factor of six; (ii) turbulence by a factor of four; and (iii) hardware failures by a factor of eight over a traditional control method.

Download

[PDF]905.3kB  

BibTeX Entry

@article{tumer-salichon_ieeesmc12,
author = {M. Salichon and K. Tumer},
title = {A Learning Based Approach to Robust Micro Aerial Vehicle Control},
journal ={IEEE Transactions on System, Man and Cybernetics--Part C} ,
volume={42},
pages={6},
pages ={1772-1783},
abstract={Micro Aerial Vehicles (MAVs) are notoriously difficult to control as they are light, susceptible to minor fluctuations in the environment, and obey highly non-linear dynamics. Indeed, traditional control methods, particularly those relying on difficult to obtain models of the interaction between an MAV and its environment have been unable to provide adequate control beyond simple maneuvers. In this paper, we address the problem of controlling an MAV (which has segmented control surfaces) by evolving a neuro-controller and fine-tuning it using multiagent coordination techniques. This approach is based on a control strategy that learns to map MAV states (position, velocity) to MAV actions (e.g., actuator position) to achieve good performance (e.g., flight time) by maximizing an objective function.  The main difficulty with this approach is defining the objective functions at the MAV level that allow good performance. In addition, to provide added robustness, we investigate a multiagent approach to control where each control surface aims to optimize a local objective.  Our results show that this approach not only provides good MAV control, but provides robustness  to (i) wind gusts by a factor of six; (ii) turbulence by a factor of four; and (iii) hardware failures by a factor of eight over a traditional control method. },
bib2html_pubtype = {Journal Articles},
bib2html_rescat = {Evolutionary Algorithms, Robotics},
 year = {2012}
 }

Generated by bib2html.pl (written by Patrick Riley ) on Tue Jun 26, 2018 19:10:42