Using Differential Evolution to Improve Pheromone-based Coordination of Swarms of Drones for Collaborative Target Detection

Abstract

In this paper we propose a novel algorithm for adaptive coordination of drones, which performs collaborative target detection in unstructured environments. Coordination is based on digital pheromones released by drones when detecting targets, and maintained in a virtual environment. Adaptation is based on the Differential Evolution (DE) and involves the parametric behaviour of both drones and environment. More precisely, attractive/repulsive pheromones allow indirect communication between drones in a flock, concerning the availability/unavailability of recently found targets. The algorithm is effective if structural parameters are properly tuned. For this purpose DE combines different parametric solutions to increase the swarm performance. We focus first on the study of the principal parameters of the DE, i.e., the crossover rate and the differential weight. Then, we compare the performance of our algorithm with three different strategies on six simulated scenarios. Experimental results show the effectiveness of the approach

Design and simulation of the emergent behavior of small drones swarming for distributed target localization

“…The component of a child vector is taken with probability CR from the mutant vector and with probability 1-CR from the target vector. In [31] an early application of DE is studied and proposed to parameterize the coordination of a group of drones whose schema is obtained by employing flocking and digital pheromones. The provided results reveal as good value for CR and F are respectively 0.5 and 0.7.…”

“…3b) has been incorporated into the separate flocking procedure (Fig. 4) [31]; (iv) in the F ASS S AR E the repulsive pheromone has been also added [12]; (v) in the F ASS S ARO E, to further speed the search, the olfactory habituation procedure has been added. Table 4 shows the performance of the different variants, in terms of 95% confidence interval over 10 trials of completion time (ticks) on each scenario.…”

“…The pheromone acts as a stimulus, i.e. other agents that perceive it will follow the pheromone trail toward the area where the target is located [29], [30], [31].…”

“…It can be observed that adaptation sensibly improves performances. As a final outcome, a performance comparison with previous approaches based on flocking and stigmergy is presented in Table 7, namely Basic S+F [12] and Adaptive S+F* [31]. Considering the average performance over all scenarios, the improvement from the best performance (provided by AdaptiveS+F* ) and the proposed approach is 26%.…”

Enhancing biologically inspired swarm behavior: Metaheuristics to foster the optimization of UAVs coordination in target search

“…In the biological behavior, the pheromone is released on a single cell and diffused progressively on neighbor cells according to a chemical expansion model. Such expansion introduces transmission delay and complex dynamics that make the cooperation inefficient (Cimino et al, 2016). In the computational behavior, the pheromone deposit is instantly diffused, with a shape whose gradient is designed to attract UAVs towards a certain area around the target (Cimino et al, 2016).…”