A Generic Spatiotemporal UAV Scheduling Framework for Multi-Event Applications

Ghazzai, Hakim; Kadri, Abdullah; Ghorbel, Mahdi Ben; Menouar, Hamid; Massoud, Yehia

doi:10.1109/access.2018.2885321

Cited by 25 publications

(12 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We notice that, after increasing the battery capacity level higher than 5000 mAh, the UAV is enable to exceed a certain coverage percentage, around 40% for the optimal solution, and this is explained by the fact that in scenario D, several events are overlapping which makes it impossible for a solo UAV to successfully cover the whole events. The figure also compares the performance of the QL approach with an optimal MILP based solution proposed in [17]. The QL solution achieves satisfactory results known that the proposed solution is compromising the efficiency in order to gain speed, which is a crucial factor that optimal solution can not provide.…”

Section: Simulation Resultsmentioning

confidence: 99%

“…The objective was to find a path for a single UAV with minimum fuel consumption such that each target is visited at least once by the vehicle without violating the fuel constraint. In [17] and [18], the authors solved MILP problem implementing a generic scheduling framework to manage a fleet of micro-UAVs to cover spatially and temporally distributed events. An extension of the later work, using low complexity algorithms, is presented in [19].…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Generic Spatiotemporal Scheduling for Autonomous UAVs: A Reinforcement Learning-Based Approach

Bouhamed

Ghazzai

Besbes

et al. 2020

IEEE Open J. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

Considerable attention has been given to leverage a variety of smart city applications using unmanned aerial vehicles (UAVs). The rapid advances in artificial intelligence can empower UAVs with autonomous capabilities allowing them to learn from their surrounding environment and act accordingly without human intervention. In this paper, we propose a spatiotemporal scheduling framework for autonomous UAVs using reinforcement learning. The framework enables UAVs to autonomously determine their schedules to cover the maximum of pre-scheduled events spatially and temporally distributed in a given geographical area and over a predetermined time horizon. The designed framework has the ability to update the planned schedules in case of unexpected emergency events. The UAVs are trained using the Q-learning (QL) algorithm to find effective scheduling plan. A customized reward function is developed to consider several constraints especially the limited battery capacity of the flying units, the time windows of events, and the delays caused by the UAV navigation between events. Numerical simulations show the behavior of the autonomous UAVs for various scenarios and corroborate the ability of QL to handle complex vehicle routing problems with several constraints. A comparison with an optimal deterministic solution is also provided to validate the performance of the learning-based solution.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: A Related Workmentioning

confidence: 99%

A Generic Spatiotemporal Scheduling for Autonomous UAVs: A Reinforcement Learning-Based Approach

Bouhamed

Ghazzai

Besbes

et al. 2020

IEEE Open J. Veh. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this section, we study the behavior of the autonomous scheduling framework for selected scenarios. Also, a comparison between the performance of the QL-based approach and an optimal MILP-based solution is provided [45]. For the sake of clarity and to be able to visualize the behavior of the UAV, we assume that K = 5 sensing nodes are randomly generated locations within 5 × 5 km 2 area.…”

Section: B Autonomous Schedulingmentioning

confidence: 99%

A UAV-Assisted Data Collection for Wireless Sensor Networks: Autonomous Navigation and Scheduling

et al. 2020

Self Cite

View full text Add to dashboard Cite

Nowadays, Wireless Sensor Networks (WSNs) are playing a vital and sustainable role in many verticals touching different aspects of our lives including civil, public, and military applications. WSNs majorly consist of a few to several sensor nodes, that are connected to each other via wireless communication links and require real-time or delayed data transfer. In this paper, we propose an autonomous Unmanned Aerial Vehicle (UAV)-enabled data gathering mechanism for delay-tolerant WSN applications. The objective is to employ a self-trained UAV as a flying mobile unit collecting data from ground sensor nodes spatially distributed in a given geographical area during a predefined period of time. In this approach, two Reinforcement Learning (RL) approaches, specifically Deep Deterministic Gradient Decent (DDPG) and Q-learning (QL) algorithms, are jointly employed to train the UAV to understand the environment and provide effective scheduling to accomplish its data collection mission. The DDPG is used to autonomously decide the best trajectory to adopt in an obstacle-constrained environment, while the QL is developed to determine the order of nodes to visit such that the data collection time is minimized. The schedule is obtained while considering the limited battery capacity of the flying unit, its need to return the charging station, the time windows of data acquisition, and the priority of certain sensor nodes. Customized reward functions are designed for each RL model and, through numerical simulations, we investigate their training performances. We also analyze the behavior of the autonomous UAV for different selected scenarios and corroborate the ability of the proposed approach in performing effective data collection. A comparison with the deterministic optimal solution is provided to validate the performance of the learning-based approach. INDEX TERMS Internet-of-things, data gathering, reinforcement learning, scheduling, unmanned areal vehicles

show abstract

“…Supposing pre-known trajectories and splitting them into multiple sub-missions simplify the problem formulation and leads to suboptimal solutions since the instants of decision making are neither time flexible nor optimized. In our previous work [28], we have designed a scheduling framework for UAVs where only one docking station is used to reload all the flying units.…”

Section: A Related Workmentioning

confidence: 99%

“…However, it is possible to convert it to a linear one by adopting some linearization techniques such as the use of multiple linear constraints to model the products of decision variables, the big-M linearization technique, and the introduction of some slack variables to linearize some of the constraints. More details about the linearize techniques that are adopted can be found in [28].…”

Section: ) Time Interval Constraintmentioning

confidence: 99%

Future UAV-Based ITS: A Comprehensive Scheduling Framework

et al. 2019

Self Cite

View full text Add to dashboard Cite

Multi-rotor unmanned aerial vehicles (UAVs) have been recently recognized as one of the top emerging technologies to be utilized in various smart city domains such as intelligent transportation systems (ITS). They represent an innovative mean to complement existing technologies to surveil transportation network, control traffic, and monitor incidents. The UAVs usually operate for time-limited missions due to their limited battery capacity. Hence, they need to frequently return to their docking stations to recharge their batteries, which handicaps their mission coverage and performance. When designing a UAV-based ITS infrastructure, it is crucial to leverage the UAV fleet effectively. In this paper, a generic management framework of UAVs for ITS applications is developed. The problem of docking/charging station placement is first investigated to find optimized locations for a given number of stations to be installed by the ITS operator. To this end, two fundamental criteria are taken into account: i) the flying time required by the UAV to reach the mission/incident location and ii) the risk of battery failure during the UAV operation. The two algorithms, namely a penalized weighted k-means algorithm and the particle swarm optimization algorithm, are designed for this purpose. Once the docking stations are placed, a UAV scheduling program is formulated to optimally cover the pre-known missions while minimizing the total energy consumption of the fleet and respecting a coverage efficiency targeted by the ITS operator. The proposed proactive scheduling approach employs multiple UAVs in sequential and parallel ways to cover spatially and temporally distributed events in the geographical area of interest over a long period. INDEX TERMS Intelligent transportation system, planning, scheduling, unmanned aerial vehicles.

show abstract

A Generic Spatiotemporal UAV Scheduling Framework for Multi-Event Applications

Cited by 25 publications

References 30 publications

A Generic Spatiotemporal Scheduling for Autonomous UAVs: A Reinforcement Learning-Based Approach

A Generic Spatiotemporal Scheduling for Autonomous UAVs: A Reinforcement Learning-Based Approach

A UAV-Assisted Data Collection for Wireless Sensor Networks: Autonomous Navigation and Scheduling

Future UAV-Based ITS: A Comprehensive Scheduling Framework

Contact Info

Product

Resources

About