![](bg8.png)
5 CONCLUSIONS
This paper introduced an multiobjective multi-stage
approach combining EA with simulated annealing for
planning minehunting operations in static 3D environ-
ment with predictable terrain. Our algorithm main-
tains a diverse population of feasible solutions in or-
der to explore the search space and uses simulated an-
nealing to improve the best solutions found and pro-
duce new solutions in the neighbourhood. Our exper-
iments showed that the integration an ANN model to
guide the search is beneficial and that the proposed lo-
cal optimization phase significantly helps to improve
the quality of the solutions, however at the cost of a
higher computational time. We also exemplified what
would be the typical output of the execution of our
planning algorithm and demonstrated the role that the
decision maker may have to play when planning a
minehunting mission with an AUV.
In the near future we are going to explore mission
planning with distinct priorities for specific areas and
study mission replanning. The idea is to use these al-
gorithms to obtain a Pareto front for each area (when
replanning a mission these areas are automatically de-
fined according to mission performance) an then to
efficiently try to interconnect the coverage paths, thus
becoming a variant of the travelling salesman prob-
lem.
ACKNOWLEDGEMENTS
This work is financed by the ERDF – European Re-
gional Development Fund through the COMPETE
Programme (operational programme for competi-
tiveness) and by National Funds through the FCT
– Fundação para a Ciência e a Tecnologia (Por-
tuguese Foundation for Science and Technology)
within project FCOMP-01-0124-FEDER-037281.
REFERENCES
Choset, H. (2001). Coverage for robotics - a survey of re-
cent results. In Ann. Math. Artif. Intell. SCITEPRESS.
Darwin, C. (1859). On the Origin of Species by Means
of Natural Selection, or the Preservation of Favoured
Races in the Struggle for Life. John Murray, London,
UK.
Deb, K. (2001). Multi-objective optimization using evolu-
tionary algorithms. Wiley, UK.
Fang, C. and Anstee, S. (2010). Coverage path planning
for harbour seabed surveys using an autonomous un-
derwater vehicle. In OCEANS 2010 IEEE - Sydney,
pages 1–8. IEEE.
Fujimura, K. (1996). Path planning with multiple objec-
tives. Robot Autom. Mag., 3(1):33–38.
Huang, G. (2003). Learning capability and storage capac-
ity of two-hidden-layer feedforward networks. Neural
Networks, IEEE Transactions on, 14(2):274–281.
Koopman, B. (1999). Search and Screening: General Prin-
ciples with Historical Applications. The Military Op-
erations Research Society, Virginia, USA.
Land, S. and Choset, H. (1998). Coverage path planning for
landmine location. In 3rd International Symposium on
Technology and the Mine Problem.
Metropolis, N., Rosenbluth, A., Rosenbluth, M., Teller,
A., and Teller, E. (1953). Equation of state calcula-
tions by fast computing machines. J. Chem. Phys.,
21(6):1087–1092.
Nash, L., Hover, G., and Burns, R. (1982). Additional anal-
yses of probability of detection (pod) in search and
rescue (sar) project data. Technical report.
Stack, J. and Smith, C. (2003). Combining random and
data-driven coverage planning for underwater mine
detection. In OCEANS 2003. Proceedings, volume 5,
pages 2463–2468 Vol.5. IEEE.
Williams, D. (2010). On optimal auv track-spacing for un-
derwater mine detection. In Robotics and Automa-
tion (ICRA), 2010 IEEE International Conference on,
pages 4755–4762. IEEE.
Xiao, J., Michalewicz, Z., Zhang, L., and Trojanowski,
K. (1997). Adaptive evolutionary planner/navigator
for mobile robots. Evolutionary Computation, IEEE
Transactions on, 1(1):18–28.
Zitzler, E., Laumanns, M., and Thiele, L. (2001). Spea2:
Improving the strength pareto evolutionary algorithm.
Technical report.
UsingEvolutionaryAlgorithmstoPlanAutomaticMinehuntingOperations
235