Abstract

We propose a Multi-Objective Shuffled Frog-Leaping Algorithm (MOSFLA) and Genetic Algorithm (GA) based task assignment and sequencing method, for multi-Unmanned Aerial Vehicles (multi-UAVs) plant-protection operation optimization. Based on full coverage of spray area, a dual decision model of non-operation flight distance and total operation time is developed considering energy consumption and operation efficiency. The proposed optimization method is hybridized using MOSFLA and GA: we first use modified MOSFLA for multi-UAVs operation assignment optimization, shrinking multi-UAVs operation cost including fields allocation, non-operation flight distance and operation time difference; we then employ GA for fields operation sequencing optimization, reducing the total operation time. Considering multi-UAVs’ take-off preparation delay effect, we established a latency time calculation model to determine total operation time for multi-UAVs. The test results show that: ① the non-operation flight distance cost for multi-UAVs using MOSFLA is less than that of single-UAV, which also performs better than that for multi-UAVs in traditional modes; ② the total operation time shrinks by using GA with known assignment matrix (including MOSFLA), which could save over 20 min compared with traditional modes; ③ the total operation time cost in MOSFLA–GA is less than that in traditional modes and optimized traditional modes, with same UAV number and preparation time for take-off; ④ the minimum iteration when assignment fitness value of MOSFLA attains maximum is small (< 20); the minimum iteration when sequencing fitness value of GA attains maximum is less than 100, but is 5 in certain cases.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.