Multi-Agent Dynamic Area Coverage Based on Reinforcement Learning with Connected Agents

Dynamic area coverage with small unmanned aerial vehicle(UAV)systems is one of the major research topics due to limited payloads and the difficulty of decentralized decision-making process.Collaborative behavior of a group of UAVs in an unknown environment is another hard problem to be solved.In this paper,we propose a method for decentralized execution of multi-UAVs for dynamic area coverage problems.The proposed decentralized decision-making dynamic area coverage(DDMDAC)method utilizes reinforcement learning(RL)where each UAV is represented by an intelligent agent that learns policies to create collaborative behaviors in partially observable environment.Intelligent agents increase their global observations by gathering information about the environment by connecting with other agents.The connectivity provides a consensus for the decision-making process,while each agent takes decisions.At each step,agents acquire all reachable agents’states,determine the optimum location for maximal area coverage and receive reward using the covered rate on the target area,respectively.The method was tested in a multi-agent actor-critic simulation platform.In the study,it has been considered that each UAV has a certain communication distance as in real applications.The results show that UAVs with limited communication distance can act jointly in the target area and can successfully cover the area without guidance from the central command unit.

Ruppert's Delaunay Triangulation Refinement Scheme for Optimal RSUs Placement in Vehicle to Infrastructure Communication Network

Road Side Units(RSUs)are the essential component of vehicular communication for the objective of improving safety and mobility in the road transportation.RSUs are generally deployed at the roadside and more specifically at the intersections in order to collect traffic information from the vehicles and disseminate alarms and messages in emergency situations to the neighborhood vehicles cooperating with the network.However,the development of a predominant RSUs placement algorithm for ensuring competent communication in VANETs is a challenging issue due to the hindrance of obstacles like water bodies,trees and buildings.In this paper,Ruppert’s Delaunay Triangulation Refinement Scheme(RDTRS)for optimal RSUs placement is proposed for accurately estimating the optimal number of RSUs that has the possibility of enhancing the area of coverage during data communication.This RDTRS is proposed by considering the maximum number of factors such as global coverage,intersection popularity,vehicle density and obstacles present in the map for optimal RSUs placement,which is considered as the core improvement over the existing RSUs optimal placement strategies.It is contributed for deploying requisite RSUs with essential transmission range for maximal coverage in the convex map such that each position of the map could be effectively covered by at least one RSU in the presence of obstacles.The simulation experiments of the proposed RDTRS are conducted with complex road traffic environments.The results of this proposed RDTRS confirmed its predominance in reducing the end-to-end delay by 21.32%,packet loss by 9.38%with improved packet delivery rate of 10.68%,compared to the benchmarked schemes.

Mapping Spatial Distribution Characteristics of Lineaments Extracted from Remote Sensing Image Using Fractal and Multifractal Models

Mapping mineral prospectivity in vegetated areas is a challenge. For this reason, we aimed to map spatial distribution characteristics of linear structures detected in remote sensing images using fractal and multifractal models. The selected study area was the Pinghe District of the Fujian Province（China）, located in the Shanghang-Yunxiao polymetallic and alunite ore belt（within the Wuyishan polymetallic belt）, where mineral resources such as copper, molybdenum, gold, silver, iron, lead, zinc, alunite and pyrophyllite have been discovered. The results of our study showed that：（1） the values of fractal dimension for all lineaments, NW-trending lineaments, and NE-trending lineaments, are 1.36, 1.32, and 1.23, respectively, indicating that these lineaments are statistically self-similar;（2） the fractal dimensions of the spatial distribution of the linear structures in the four selected hydrothermal-type ore deposits of the Pinghe District, named Zhongteng, Panchi, Xiaofanshan and Fanshan, are 1.43, 1.52, 1.37 and 1.37, respectively, which are higher than the mean value in South China;（3） the spatial distribution of the linear structures extracted from the remote sensing image and displayed by the contour map of fractal dimensions, correlates well with the known hydrothermal ore deposits; and（4） the results of the anomaly map decomposed by the spectrum-area（S-A） multifractal model is much better than the original fractal dimension contour map, which showed most of the known hydrothermal-type deposits occur in the high anomalous area. It is suggested that a high step tendency possibly matches with the boundary of the volcanic edifice and the deep fault controlling the development of the rock mass and the volcanic edifice. The complexity of the spatial distribution of mapped lineations（faults） in the Pinghe District, characterized by high values in the anomaly map, may be associated with the hydrothermal polymetallic ore mineralization in the study area.