Incremental Evolution of Autonomous Controllers for
Unmanned Aerial Vehicles using Multi-objective Genetic
Programming
G. Barlow, C. Oh, and E. Grant. Proceedings of the 2004 IEEE Conference on Cybernetics
and Intelligent Systems (CIS), page 688--693. Singapore, IEEE, (1-3 December 2004)
Abstract
Autonomous navigation controllers were developed for
fixed wing unmanned aerial vehicle (UAV) applications
using incremental evolution with multi-objective
genetic programming (GP). We designed four fitness
functions derived from flight simulations and used
multi-objective GP to evolve controllers able to locate
a radar source, navigate the UAV to the source
efficiently using on-board sensor measurements, and
circle closely around the emitter. We selected
realistic flight parameters and sensor inputs to aid in
the transference of evolved controllers to physical
UAVs. We used both direct and environmental incremental
evolution to evolve controllers for four types of
radars: 1) continuously emitting, stationary radars, 2)
continuously emitting, mobile radars, 3) intermittently
emitting, stationary radars, and 4) intermittently
emitting, mobile radars. The use of incremental
evolution drastically increased evolution's chances of
evolving a successful controller compared to direct
evolution. This technique can also be used to develop a
single controller capable of handling all four radar
types. In the next stage of research, the best evolved
controllers will be tested by using them to fly real
UAVs.
%0 Conference Paper
%1 barlow2004-cis
%A Barlow, Gregory J.
%A Oh, Choong K.
%A Grant, Edward
%B Proceedings of the 2004 IEEE Conference on Cybernetics
and Intelligent Systems (CIS)
%C Singapore
%D 2004
%I IEEE
%K algorithms, evolution, genetic incremental multi-objective optimisation programming,
%P 688--693
%T Incremental Evolution of Autonomous Controllers for
Unmanned Aerial Vehicles using Multi-objective Genetic
Programming
%U http://www.cs.cmu.edu/~gjb/includes/publications/conference/barlow2004-cis/barlow2004-cis.pdf
%X Autonomous navigation controllers were developed for
fixed wing unmanned aerial vehicle (UAV) applications
using incremental evolution with multi-objective
genetic programming (GP). We designed four fitness
functions derived from flight simulations and used
multi-objective GP to evolve controllers able to locate
a radar source, navigate the UAV to the source
efficiently using on-board sensor measurements, and
circle closely around the emitter. We selected
realistic flight parameters and sensor inputs to aid in
the transference of evolved controllers to physical
UAVs. We used both direct and environmental incremental
evolution to evolve controllers for four types of
radars: 1) continuously emitting, stationary radars, 2)
continuously emitting, mobile radars, 3) intermittently
emitting, stationary radars, and 4) intermittently
emitting, mobile radars. The use of incremental
evolution drastically increased evolution's chances of
evolving a successful controller compared to direct
evolution. This technique can also be used to develop a
single controller capable of handling all four radar
types. In the next stage of research, the best evolved
controllers will be tested by using them to fly real
UAVs.
@inproceedings{barlow2004-cis,
abstract = {Autonomous navigation controllers were developed for
fixed wing unmanned aerial vehicle (UAV) applications
using incremental evolution with multi-objective
genetic programming (GP). We designed four fitness
functions derived from flight simulations and used
multi-objective GP to evolve controllers able to locate
a radar source, navigate the UAV to the source
efficiently using on-board sensor measurements, and
circle closely around the emitter. We selected
realistic flight parameters and sensor inputs to aid in
the transference of evolved controllers to physical
UAVs. We used both direct and environmental incremental
evolution to evolve controllers for four types of
radars: 1) continuously emitting, stationary radars, 2)
continuously emitting, mobile radars, 3) intermittently
emitting, stationary radars, and 4) intermittently
emitting, mobile radars. The use of incremental
evolution drastically increased evolution's chances of
evolving a successful controller compared to direct
evolution. This technique can also be used to develop a
single controller capable of handling all four radar
types. In the next stage of research, the best evolved
controllers will be tested by using them to fly real
UAVs.},
added-at = {2008-06-19T17:35:00.000+0200},
address = {Singapore},
author = {Barlow, Gregory J. and Oh, Choong K. and Grant, Edward},
biburl = {https://www.bibsonomy.org/bibtex/2a8393a44dfcc1ce99771bf2d1efa2053/brazovayeye},
booktitle = {Proceedings of the 2004 IEEE Conference on Cybernetics
and Intelligent Systems (CIS)},
interhash = {1773eb4a9aced6fb2c450ffd7fd30015},
intrahash = {a8393a44dfcc1ce99771bf2d1efa2053},
keywords = {algorithms, evolution, genetic incremental multi-objective optimisation programming,},
month = {1-3 December},
notes = {IEEE CIS RAM 2004 http://cis-ram.nus.edu.sg/},
pages = {688--693},
publisher = {IEEE},
timestamp = {2008-06-19T17:36:17.000+0200},
title = {Incremental Evolution of Autonomous Controllers for
Unmanned Aerial Vehicles using Multi-objective Genetic
Programming},
url = {http://www.cs.cmu.edu/~gjb/includes/publications/conference/barlow2004-cis/barlow2004-cis.pdf},
year = 2004
}