GA-guided task planning for multiple-HAPS in realistic time-varying operation environments

Abstract

High-Altitude Pseudo-Satellites (HAPS) are long-endurance, fixedwing, lightweight Unmanned Aerial Vehicles (UAVs) that operate in the stratosphere and offer a flexible alternative for ground activity monitoring/imaging at specific time windows. As their missions must be planned ahead (to let them operate in controlled airspace), this paper presents a Genetic Algorithm (GA)-guided Hierarchical Task Network (HTN)-based planner for multiple HAPS. The HTN allows to compute plans that conform with airspace regulations and operation protocols. The GA copes with the exponentially growing complexity (with the number of monitoring locations and involved HAPS) of the combinatorial problem to search for an optimal task decomposition (that considers the time-dependent mission requirements and the time-varying environment). Besides, the GA offers a flexible way to handle the problem constraints and optimization criteria: the former encodes the airspace regulations, while the latter measures the client satisfaction, the operation efficiency and the normalized expected mission reward (that considers the wind effects in the uncertainty of the arrival-times at the monitoringlocations). Finally, by integrating the GA into the HTN planner, the new approach efficiently finds overall good task decompositions, leading to satisfactory task plans that can be executed reliably (even in tough environments), as the results in the paper show. CCS CONCEPTS• Theory of computation → Evolutionary algorithms; • Computing methodologies → Planning under uncertainty; Multiagent planning;

Hierarchical Mission Planning with a GA-Optimizer for Unmanned High Altitude Pseudo-Satellites

“…Changing the value of this parameter, the constraint violation can be “tightened” or “relaxed” as much as desired. This is a novelty of the planner presented in this paper, since the original version presented in [ 10 ] implemented a deterministic evaluation of the coexistence criterion where no overlapping of the start and end time range of MA# tasks was allowed.…”

“…However, although HAPSs operations can be beneficial, they can be extremely challenging, given the fragility of the platform under critical weather conditions, their lack of maneuverability, and the requirement for plans for long operations, which oblige the consideration of weather parameters that vary over time within the plan horizon [ 34 ]. Specific studies on automated planning for HAPS include [ 10 , 35 ], both aiming to reduce the operators’ workload. In particular, for a complex mission scenario as the one depicted in Figure 1 , Ref.…”

“…[ 35 ] proposes a sequential task and motion planning framework for a collective operation area, simplifying the constraints of the planning problem, while [ 10 ] uses a GA to extend the temporal hierarchical task planner for multiple HAPSs. Moreover, the current work extends the planner presented in [ 10 ] by (1) including the evaluation of the safety and coexistence constraints with the new probability based functions presented in Section 3.3.1 and Section 3.3.2 , by (2) substituting the weighted evaluation function used in [ 10 ] for the constrained multiobjective Pareto-front evaluation mechanisms of NSGA-II, and by (3) returning the set of the hierarchical plans that form part of the final best Pareto front. Besides, this paper analyzes the behavior of the new planner with new scenario and the influence of the diversity objective function and of different constraint handling techniques within our planner.…”

“…The work presented in this paper is closely related with the approach described in [ 10 ], which presented the preliminary version of our planner. The current version is improved, by (1) adopting a Multi-Objective Evolutionary Algorithm (MOEA) for constrained problems to optimize the mission plans and (2) by considering the uncertainty associated to the wind variability in the constraints.…”