Data Collection System of IoT Based on the Coordination of Drones and Unmanned Surface Vehicle

Wang, Zhigang; Tian, Li; Lin, Lianhai; Xie, Jianfei; Wu, Wenxing; Tong, Yinghua

doi:10.1155/2023/3426932

Cited by 4 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This solution allows the water sampler to protect the sorbent phase from external contamination. The drone flight heuristic algorithm [14] can not only quickly solve the large-scale joint optimization problem but also rationally use the total energy consumption of the water sampling equipment. Article [15] illustrates the possibility of combining the functions of a multipurpose flying drone and a floating mechanism for water quality monitoring, and the study [16] confirms the feasibility of using drones to collect hydro-chemical data from freshwater environments for biological and physicochemical water sampling.…”

Section: Prerequisites and Means For Solving The Problemmentioning

confidence: 99%

Improvement of technological equipment drone for water sampling: Design and modeling

Polishchuk,

Rolik

2024

FME Transactions

View full text Add to dashboard Cite

One of the modern problems in the field of ecology is the creation of environmentally friendly equipment for monitoring the state of various reservoirs by taking water for further laboratory analysis. Water quality monitoring is needed to record changes in water quality over time, as well as to detect contamination from storm water runoff, which may contain microorganisms, minerals, debris, and fuel residues. One of the promising ways to solve this problem is using drones to collect hydro-chemical data on the spot and take water samples from freshwater environments. This approach makes it possible to perform the aspects of biological and physical-chemical water sampling that are necessary for implementing large-scale water sampling programs and makes these programs more efficient, safe, and economically profitable. However, in modern times, the use of drones for water quality monitoring is held back by a number of important limitations, namely the low level of objective sampling and the relatively small volume of water samples. The article proposes a fundamentally new design of the technological equipment of a drone for taking water samples, namely a new design of a bathometer - a device for taking water samples and installing them on the Cardan suspension. These structural differences ensure the orientation of the bathometer only under the influence of gravitational force, which in turn significantly increases the objectivity of water sampling. The article also provides kinematic and dynamic models of the bathometer's movement on the Cardan suspension rings. It presents the modeling results in the form of graphical and analytical dependencies of kinematic analysis, which constitutes the scientific aspect of the problem. The main motivation of the conducted research is the creation of environmentally friendly equipment in the form of an unmanned aerial vehicle, which is designed to increase the objectivity of water sampling.

show abstract

Section: Prerequisites and Means For Solving The Problemmentioning

confidence: 99%

Improvement of technological equipment drone for water sampling: Design and modeling

Polishchuk,

Rolik

2024

FME Transactions

View full text Add to dashboard Cite

show abstract

“…The design of UAVs aims to execute specific tasks that cannot be cost-effectively performed by other kinds of vehicles [2], [3]. These tasks include supporting search and rescue operations [4], capturing detailed aerial data for urban planning [5], construction [6], land surveying, and other mapping-related activities [7], as well as facilitating data collection for various industries and research purposes [8], [9].…”

mentioning

confidence: 99%

Distributed TDMA Scheduling for Autonomous Aerial Swarms: A Self-Organizing Approach

Aydin,

Akcasoy,

Cakir

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Self-organization is a key strategy for improving the performance of an aerial swarm ad hoc network. The proliferation of low-cost VTOL drones has broadened the application domain of aerial swarms, and the need for synchronized communication among network entities has become crucial. However, existing ad hoc approaches struggle to maintain multi-hop connections in contested environments characterized by frequent topology changes and intermittent links. To overcome these limitations, we introduced STDMA protocol, which enables the self-configuration of drones without reliance on a ground controller. In continuation of the earlier work, we conduct extensive experiments to evaluate the performance of the proposed protocol.Comparative simulation experiments cover various scenarios with different network sizes, frame lengths, and traffic loads. The STDMA protocol achieves optimal access delay in highly contested environments and reduces delay by approximately 19.181%. Moreover, it exhibits improved channel utilization compared to the E-ASAP/SM protocol, with a 4.5 times increase.INDEX TERMS ad hoc networks, autonomous control, decentralized control, distributed systems, reliable communication, self-organizing network management, swarm intelligence, UAV swarm I. INTRODUCTION

show abstract

Decoupling Patrolling Tasks for Water Quality Monitoring: A Multi-Agent Deep Reinforcement Learning Approach

Diop,

Luis,

Esteve

et al. 2024

IEEE Access

View full text Add to dashboard Cite

This study proposes the use of an Autonomous Surface Vehicle (ASV) fleet with water quality sensors for efficient patrolling to monitor water resource pollution. This is formulated as a Patrolling Problem, which consists of planning and executing efficient routes to continuously monitor a given area. When patrolling Lake Ypacaraí with ASVs, the scenario transforms into a Partially Observable Markov Game (POMG) due to unknown pollution levels. Given the computational complexity, a Multi-Agent Deep Reinforcement Learning (MADRL) approach is adopted, with a common policy for homogeneous agents. A consensus algorithm assists in collision avoidance and coordination. The work introduces exploration and reinforcement phases to the patrolling problem. The Exploration Phase aims at homogeneous map coverage, while the Intensification Phase prioritizes high polluted areas. The innovative introduction of a transition variable, ν, efficiently controls the transition from exploration to intensification. Results demonstrate the superiority of the method, which outperforms a Single-Phase (trained on a single task) Deep Q-Network (DQN) by an average of 17% on the intensification task. The proposed multitask learning approach with parameter sharing, coupled with DQN training, outperforms Task-Specific DQN (two DQNs trained on separate tasks) by 6% in exploration and 13% in intensification. It also outperforms the heuristic-based Lawn Mower Path Planner (LMPP) and Random Wanderer Path Planner (RWPP) algorithms, by 35% and 20% on average respectively. Additionally, it outperforms a Particle Swarm Optimization-based Path Planner (PSOPP) by an average of 26%. The algorithm demonstrates adaptability in unforeseen scenarios, giving users flexibility in configuration.

show abstract

Data Collection System of IoT Based on the Coordination of Drones and Unmanned Surface Vehicle

Cited by 4 publications

References 44 publications

Improvement of technological equipment drone for water sampling: Design and modeling

Improvement of technological equipment drone for water sampling: Design and modeling

Distributed TDMA Scheduling for Autonomous Aerial Swarms: A Self-Organizing Approach

Decoupling Patrolling Tasks for Water Quality Monitoring: A Multi-Agent Deep Reinforcement Learning Approach

Contact Info

Product

Resources

About