Optimal mission path planning (MPP) for an air sampling unmanned aerial system

This paper presents advanced optimization\ud techniques for Mission Path Planning (MPP) of a\ud UAS fitted with a spore trap to detect and\ud monitor spores and plant pathogens. The UAV\ud MPP aims to optimise the mission path planning\ud search and monitoring of spores and plant\ud pathogens that may allow the agricultural sector\ud to be more competitive and more reliable. The\ud UAV will be fitted with an air sampling or spore\ud trap to detect and monitor spores and plant\ud pathogens in remote areas not accessible to\ud current stationary monitor methods.\ud The optimal paths are computed using a\ud Multi-Objective Evolutionary Algorithms\ud (MOEAs). Two types of multi-objective\ud optimisers are compared; the MOEA\ud Non-dominated Sorting Genetic Algorithms II\ud (NSGA-II) and Hybrid Game are implemented to\ud produce a set of optimal collision-free\ud trajectories in three-dimensional environment.\ud The trajectories on a three-dimension terrain,\ud which are generated off-line, are collision-free\ud and are represented by using Bézier spline curves\ud from start position to target and then target to\ud start position or different position with altitude\ud constraints. The efficiency of the two\ud optimization methods is compared in terms of\ud computational cost and design quality.\ud Numerical results show the benefits of coupling\ud a Hybrid-Game strategy to a MOEA for MPP\ud tasks. The reduction of numerical cost is an\ud important point as the faster the algorithm\ud converges the better the algorithms is for an\ud off-line design and for future on-line decisions of\ud the UAV