A UAV-Assisted Multi-Task Allocation Method for Mobile Crowd Sensing

Abstract

Mobile crowd sensing (MCS) with human participants has been proposed as an efficient way of collecting data for smart cities applications. However, there often exist situations where humans are not able or reluctant to reach the target areas, due to for example traffic jams or bad road conditions. One solution is to complement manual data collection with autonomous data collection using unmanned aerial vehicles (UAVs) equipped with various sensors. In this paper, we focus on the scenarios of UAV-assisted MCS and propose a task allocation method, called "UMA" (UAV-assisted Multi-task Allocation method) to optimize the sensing coverage and data quality. The method incentivizes human participants to contribute sensing data from nearby points of interest (PoIs), with a limited budget. Meanwhile, the method jointly considers the optimization of task assignment and trajectory scheduling. It schedules the trajectories of UAVs, considering the locations of human participants, other UAVs and PoIs which are rarely visited by human participants. In detail, UAVs take care of two tasks in our proposal. One is to calibrate the data collected by the human participants whom the UAVs come across along their trajectories. The other is to collect data from the PoIs which are not covered by other UAVs or human participants. We apply deep reinforcement learning to schedule UAVs moving trajectories and sensing activities in order to minimize the overall energy cost. We evaluate the proposed scheme via simulation using two real data sets. The results show that our proposal outperforms the compared methods, in terms of coverage completed ratio, calibrating ratio, energy efficiency, and task fairness.

UAV-Assisted Cluster-Based Task Allocation for Mobile Crowdsensing in a Space–Air–Ground–Sea Integrated Network

“…In this section, we conduct extensive simulations and evaluate the performance of our proposed UAV-assisted cluster-based task allocation (UCTA) algorithm for MCS in SAGSIN. To better validate the analysis, we compare the UCTA algorithm with the other three benchmark baselines, the UMA [ 20 ], PETA [ 44 ], and GA-TA [ 45 ] algorithms, in terms of task completion rate and task coverage rate. The UMA method concentrates on the MCS situations with UAV assistance and designs a task allocation method, aiming at acquiring the maximum sensing coverage and data quality.…”

“…Hence, human users with mobile intelligent devices still play a significant role in MCS applications, while UAVs can act as the supplementary part to help human users accomplish sensing tasks accurately. H Gao [ 20 ] concentrated on UAV-assisted MCS applications and designed a UMA (UAV-assisted multi-task allocation method), which could maximize the sensing coverage and guarantee the data quality. B Wang [ 35 ] applied UAVs to disaster relief networks and proposed a social-aware UAV-assisted MCS system to, in stochastic and dynamic environments, recruit appropriate UAVs to replace human users to complete the tasks.…”

“…In our paper, the goal is to maximize the sensing coverage quality and improve the completion rate of the two types of tasks with budget and energy constraints in urban scenarios. Therefore, we introduce the equation named coverage-completed ratio (CCR) [ 20 ] to reveal the ratio of the sensed coverage area and the required coverage area. The objective function can be expressed as where denotes the rounds of tasks.…”

“…In order to conserve and utilize the oceans, seas, and their resources for sustainable development, Moroni D [ 19 ] presented an app based on a crowdsensing approach for SAGSINs to improve safety and awareness. However, although MCS is considered an effective scheme to meet several requirements of IoT applications, it still has many essential challenges to overcome, one of which is task allocation [ 20 ].…”

VG-Swarm: A Vision-based Gene Regulation Network for UAVs Swarm Behavior Emergence

“…Recently, the research of swarm UAVs have attracted increasing attention from researchers because of its wide applicability, such as environment exploration [1], target tracking and entrapping [2], flocking [3], autonomous search and rescue [4], task allocation [5] etc, among which a special class of applications include entrapping and capturing enemy targets, or protecting targets by using multiple UAVs [6].…”