Naslov
Autonomous control for multi-agent non-uniform spraying

Autori
Ivić, Stefan ; Andrejčuk, Aleksandr ; Družeta, Siniša

Izvornik
Applied soft computing (1568-4946) 80 (2019); 742-760

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
spraying ; area coverage ; multi-agent ; UAV ; precision agriculture

Sažetak
The use of computer controlled swarms of UAVs for crop spraying enables non-uniform coverage of high precision and time efficiency. For this purpose an algorithmic control method for autonomous UAV swarm spraying, based on multi-agent area coverage method Heat Equation Driven Area Coverage (HEDAC), is proposed. Motion control relies on suitable spraying model which enables of multi-agent spraying simulations for arbitrary agent’s trajectories. The HEDAC control method was tested in comparison with conventional (Lawnmower) and state-of-the-art (SMC) path planning methods on three numerical tests: two based on simple geometries and algebraically defined spraying goal densities, and one based on a real-world crop disease map. Additionally, the effects of spraying tool design (number of nozzles and their spraying density) on spraying accuracy were analyzed, with results consistently illustrating the direct causation between tool precision and overall spraying error. The results of the testing have shown HEDAC control to be significantly faster than Lawnmower (approximately 35%–65% less time needed) and SMC (approximately 15%–50% less time needed) in achieving convergence, while producing spraying density of comparable accuracy. Moreover, HEDAC spraying typically mitigates over-spraying by approximately 3%–8% when compared with conventional path planning. In additional tests, it is shown that an implementation of collision avoidance technique for HEDAC motion control provides collision-free UAV swarm spraying. The effect of HEDAC collision avoidance control on the spraying convergence rate and accuracy is practically insignificant. It may be concluded that in real-world application HEDAC controlled UAV spraying swarms are expected to significantly outperform UAVs operating with existing path planning methods.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Strojarstvo, Zrakoplovstvo, raketna i svemirska tehnika, Temeljne tehničke znanosti, Interdisciplinarne tehničke znanosti

POVEZANOST RADA