0
Research Papers

UAS Mission Path Planning System (MPPS) Using Hybrid-Game Coupled to Multi-Objective Optimizer

[+] Author and Article Information
DongSeop Lee, Jacques Periaux

International Center for Numerical Methods in Engineering (CIMNE),  UPC, Barcelona 08034, Spain

Luis Felipe Gonzalez

Australian Research Centre Aerospace Automation (ARCAA), School of System Engineering, Queensland University Technology (QUT), Brisbane 4001, Australia

J. Dyn. Sys., Meas., Control 132(4), 041005 (Jun 16, 2010) (11 pages) doi:10.1115/1.4001336 History: Received May 29, 2009; Revised December 15, 2009; Published June 16, 2010; Online June 16, 2010

This paper presents the application of advanced optimization techniques to unmanned aerial system mission path planning system (MPPS) using multi-objective evolutionary algorithms (MOEAs). Two types of multi-objective optimizers are compared; the MOEA nondominated sorting genetic algorithm II and a hybrid-game strategy are implemented to produce a set of optimal collision-free trajectories in a three-dimensional environment. The resulting trajectories on a three-dimensional terrain are collision-free and are represented by using Bézier spline curves from start position to target and then target to start position or different positions with altitude constraints. The efficiency of the two optimization methods is compared in terms of computational cost and design quality. Numerical results show the benefits of adding a hybrid-game strategy to a MOEA and for a MPPS.

Copyright © 2010 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.

References

Figures

Grahic Jump Location
Figure 1

Algorithm for NSGA-II

Grahic Jump Location
Figure 2

Algorithm for hybrid-game on NSGA-II

Grahic Jump Location
Figure 3

(a) Random solutions and true Pareto-front obtained by NSGA-II and hybrid-game on NSGA-II after 500 generations. (b) Initial population obtained by NSGA-II for MOP4. (c) Initial population obtained by hybrid-game on NSGA-II and elite design obtained by Nash-game (marked by circle) for MOP4. (d) Comparison of Pareto-front obtained by NSGA-II (circle dots and line) and hybrid-game on NSGA-II (pentagonal dots and broken-line) after 200 generations.

Grahic Jump Location
Figure 4

(a) Initial population obtained by NSGA-II for ZDT6. (b) Initial population obtained by hybrid-game on NSGA-II and elite design obtained by Nash-game (marked by circle) for ZDT6. (c) Comparison of Pareto-front obtained by NSGA-II and hybrid-game on NSGA-II after 100 generations. (d) Comparison of Pareto-front obtained by NSGA-II and hybrid-game on NSGA-II after 400 generations.

Grahic Jump Location
Figure 5

(a) Baseline terrain. (b) Baseline terrain with altitude constraints (Test 1: Sec. 5).

Grahic Jump Location
Figure 6

Baseline terrain with altitude constraints (Test 2: Sec. 5)

Grahic Jump Location
Figure 7

(a) Trajectory for minimum distance (Test 1: Sec. 5). (b) Trajectory for minimum distance (Test 2: Sec. 5).

Grahic Jump Location
Figure 8

(a) Comparison of performance (time: min) between NSGA-II and hybrid-game applied to NSGA-II. Note that AVG represents the average computational cost of NSGA-II and hybrid-game for five tests. (b) Comparison of performance (generations) between NSGA-II and hybrid-game applied to NSGA-II.

Grahic Jump Location
Figure 9

Trajectories obtained by NSGA-II (T1)

Grahic Jump Location
Figure 10

Trajectories obtained by hybrid-game (T4)

Grahic Jump Location
Figure 11

(a) Comparison of performance (time: min) between NSGA-II and hybrid-game applied to NSGA-II. (b) Comparison of performance (generations) between NSGA-II and hybrid-game applied to NSGA-II.

Grahic Jump Location
Figure 12

Comparison of Pareto-front between NSGA-II, hybrid-game applied to NSGA-II, and Nash-game

Grahic Jump Location
Figure 13

(a) Trajectories obtained by NSGA-II (T3: 17 members). (b) Trajectories obtained by NSGA-II (T3).

Grahic Jump Location
Figure 14

(a) Trajectories obtained by hybrid-game on NSGA-II (T2: 20 members). (b) Trajectories obtained by hybrid-game on NSGA-II (T2).

Grahic Jump Location
Figure 15

(a) Population of hybrid-game on NSGA-II at 0 generation. (b) Population of NSGA-II at 0 generation.

Grahic Jump Location
Figure 16

(a) Population of hybrid-game on NSGA-II at tenth generation. (b) Population of NSGA-II at tenth generation.

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In