[go: up one dir, main page]
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
Research Progress on the Application of Multi-agent Systems
applsci-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Research Progress on the Application of Multi-agent Systems

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 31 May 2025 | Viewed by 6164

Special Issue Editors

Prof. Dr. Florin Leon

E-Mail Website
Guest Editor
Faculty of Automatic Control and Computer Engineering, “Gheorghe Asachi” Technical University of Iași, 700050 Iași, Romania
Interests: artificial intelligence; machine learning; multiagent systems; software design
Special Issues, Collections and Topics in MDPI journals
Dr. Marius Gavrilescu

E-Mail Website
Guest Editor
Faculty of Automatic Control and Computer Engineering, “Gheorghe Asachi” Technical University of Iași, 700050 Iași, Romania
Interests: machine learning; computer graphics; data analytics; gaming engines; physics simulations
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Multi-agent systems (MAS) revolve around the design and analysis of systems comprising multiple autonomous agents, each capable of independent decision making and action. The applications of multi-agent systems span various domains, such as robotics, economics, transportation, and social sciences. In robotics, multi-agent systems enable the achievement of collaborative tasks such as search and rescue missions, while in economics, they can model complex market interactions and resource allocation. In transportation systems, multi-agent approaches are beneficial for traffic management and optimization. The importance of multi-agent systems lies in their ability to solve complex problems that cannot be effectively addressed by single entities. They promote decentralized decision making, which can enhance efficiency, adaptability, and robustness in dynamic and uncertain environments. In the era of interconnected intelligent systems, multi-agent systems play an important role in overcoming real-world challenges and are key to the development of more intelligent and autonomous systems, which involve complex problem solving. This Special Issue comprises an in-depth exploration of recent MAS applications, including innovative approaches to learning, coordination, and cooperation among autonomous agents, as well as agent-based simulations, in various fields. Topics of interest include, but are not limited to:

  • Multi-agent reinforcement learning;
  • Multi-agent systems for smart cities (e.g., optimizing urban infrastructure, traffic management, energy distribution);
  • Multi-agent systems in healthcare (e.g., personalized patient care, remote monitoring, resource allocation in hospitals);
  • Multi-agent systems for cybersecurity (e.g., coordinating the actions of security agents);
  • Multi-agent systems for social networks (e.g., simulating information diffusion and opinion formation);
  • Multi-agent systems in industry;
  • Autonomous vehicles (e.g., cars, drones);
  • Swarm intelligence;
  • Multi-agent systems for e-commerce and recommendation systems;
  • Multi-agent systems for edge and fog computing and federated learning;
  • Multi-agent systems for disaster management;
  • Multi-agent systems for social simulations;
  • Multi-agent systems for environment applications.

Prof. Dr. Florin Leon
Dr. Marius Gavrilescu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • multi-agent reinforcement learning
  • cooperative multi-agent systems
  • agent-based modeling and simulation
  • game theory in multi-agent systems
  • decentralized control
  • swarm intelligence
  • multi-agent communication
  • consensus algorithms
  • conflict resolution
  • trust and reputation

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

28 pages, 1132 KiB  
Article
Comparison of Multi-Agent Platform Usability for Industrial-Grade Applications
by Zofia Wrona, Maria Ganzha, Marcin Paprzycki, Wiesław Pawłowski, Angelo Ferrando, Giacomo Cabri and Costin Bădică
Appl. Sci. 2024, 14(22), 10124; https://doi.org/10.3390/app142210124 - 5 Nov 2024
Viewed by 1728
Abstract
Modern systems often employ decentralised and distributed approaches. This can be attributed, among others, to the increasing complexity of system processes, which go beyond the capabilities of singular components. Additionally, with the growth in demand for system automation and high-level coordination, solutions belonging [...] Read more.
Modern systems often employ decentralised and distributed approaches. This can be attributed, among others, to the increasing complexity of system processes, which go beyond the capabilities of singular components. Additionally, with the growth in demand for system automation and high-level coordination, solutions belonging to the decentralised Artificial Intelligence and collaborative decision-making are often applied. It can be observed that these concerns fall within the domain of multi-agent systems. However, even though MAS concepts emerged more than 40 years ago, despite their obvious advantages and continuous efforts of the scientific community, agents remain rarely used in industrial-grade applications. In this context, the goal of this contribution is to analyse the reasons for the lack of adoption of agent solutions in the real world. During the analysis, all pertinent aspects of the modern software development life cycle are examined and compared to what is currently available in the agent system domain. Specifically, the study focuses on identifying gaps that are often overlooked when it comes to scientific applications of MAS, but are critical in terms of potential for large-scale system development in practice. Full article
(This article belongs to the Special Issue Research Progress on the Application of Multi-agent Systems)
►▼ Show Figures

Figure 1

Figure 1
<p>Stages of software development life cycle.</p> Full article ">Figure 2
<p>Chart presenting number of developers that use distinct programming languages.</p> Full article ">Figure 3
<p>Distribution of developers among different industrial sectors and job types, including development vs. research and development.</p> Full article ">Figure 4
<p>Distribution of developers based on the number of years of experience and job titles.</p> Full article ">Figure 5
<p>Bar chart summarising how often each category was placed in the top 3 selections.</p> Full article ">Figure 6
<p>Coverage importance matrix of software development categories.</p> Full article ">
15 pages, 1117 KiB  
Article
Optimal Agent-Based Pickup and Delivery with Time Windows and Electric Vehicles
by Ionuț Murarețu and Costin Bădică
Appl. Sci. 2024, 14(17), 7528; https://doi.org/10.3390/app14177528 - 26 Aug 2024
Viewed by 870
Abstract
The traditional methods of transporting goods and people in urban areas using vehicles powered by internal combustion engines are major contributors to pollution. As a result, an increasing number of logistics companies are transitioning to electric vehicles (EVs) for daily operations, replacing traditional [...] Read more.
The traditional methods of transporting goods and people in urban areas using vehicles powered by internal combustion engines are major contributors to pollution. As a result, an increasing number of logistics companies are transitioning to electric vehicles (EVs) for daily operations, replacing traditional engines. This shift opens research avenues regarding the integration of EVs into delivery workflows and how this can contribute to greener cities. This study tackles the EV routing problem, focusing on balancing battery constraints and optimizing routes. We formulated the problem as a pickup and delivery with time windows, incorporating electric energy consumption constraints, and utilized consensus mechanisms in an agent-based simulation context. Our evaluation used 15 scenarios, capturing variations in vehicle configurations, order generation rates, and battery and freight capacities. We compared two order allocation strategies: “Closest Allocation” and “Negotiation” consensus-based allocation. The results confirmed that the consensus-based strategy outperformed the “Closest Allocation” in metrics such as remaining orders, orders not handled in time, total distance traveled, total recharging cost, and total number of recharges. These findings have significant implications for urban planners, logistic companies, and policymakers, demonstrating that an agent-based simulation context for electric vehicles using consensus-based strategies can enhance delivery efficiency and promote sustainability. Full article
(This article belongs to the Special Issue Research Progress on the Application of Multi-agent Systems)
►▼ Show Figures

Figure 1

Figure 1
<p>Graphical representation of a solution for a problem instance with two pickup and two delivery points, five charging stations, and two vehicles.</p> Full article ">Figure 2
<p>Agent interactions in an agent-based simulation.</p> Full article ">Figure 3
<p>Agent-based simulation: activity diagram of vehicles handling orders in the simulation environment.</p> Full article ">Figure 4
<p>ABSM: negotiation mechanism.</p> Full article ">Figure 5
<p>Total orders generated.</p> Full article ">Figure 6
<p>Remaining orders.</p> Full article ">Figure 7
<p>Orders not handled in time.</p> Full article ">Figure 8
<p>Total distance traveled.</p> Full article ">Figure 9
<p>Number of charges.</p> Full article ">Figure 10
<p>Total recharging cost.</p> Full article ">
19 pages, 9460 KiB  
Article
Position-Based Formation Control Scheme for Crowds Using Short Range Distance (SRD)
by Jun Hyuck Son and Man Kyu Sung
Appl. Sci. 2024, 14(8), 3386; https://doi.org/10.3390/app14083386 - 17 Apr 2024
Cited by 1 | Viewed by 1209
Abstract
In crowd simulation, representing crowd behavior in complex dynamic environments is one of the biggest challenges. In this paper, we propose new algorithms to make crowds satisfy a given formation while they are moving towards a destination. For this, we apply the Position [...] Read more.
In crowd simulation, representing crowd behavior in complex dynamic environments is one of the biggest challenges. In this paper, we propose new algorithms to make crowds satisfy a given formation while they are moving towards a destination. For this, we apply the Position Based Dynamics (PBD) framework, but introduce a new formation constraint based on a so-called Short Range Destination (SRD). The SRD is a short-term goal to which an agent must move in formation. In addition, a grid structure that we use for neighbor search is also used for congestion control. Depending on the congestion value, the agents in the cell may break the formation and instead exhibit emergent behaviors such as collision avoidance, but must automatically restore the original formation once the situation is resolved. Smooth movement of agents is also achieved by adding special behaviors when they are moving along the path that the user specifies. From several experiments, we show that the proposed scheme is capable of exhibiting natural aggregate behavior of crowds in real time, even for a highly condensed environment. Full article
(This article belongs to the Special Issue Research Progress on the Application of Multi-agent Systems)
►▼ Show Figures

Figure 1

Figure 1
<p>Overview of controlling crowd formation using SRD. (<b>a</b>) There are two groups of agents, a red group and a blue group. Both groups are supposed to maintain a bird formation and are about to collide while moving to the opposite side. (<b>b</b>) The two groups are crossing and passing each other, losing their formation to avoid collisions. (<b>c</b>) After the two groups cross, the agents in each group restore the original formation automatically. (<b>d</b>) The blue group is moving to their destination with the formation restored.</p> Full article ">Figure 2
<p>Comparison of processes in dynamical systems and PBD. The * symbol means multiplication.</p> Full article ">Figure 3
<p>A flowchart of the crowd formation control method expanded from the crowd simulation using PBD.</p> Full article ">Figure 4
<p>A group that is a subset of the entire crowd.</p> Full article ">Figure 5
<p>A projection of the vertices of a 3D bird insignia model onto a 2D plane [<a href="#B19-applsci-14-03386" class="html-bibr">19</a>]. Red circles, yellow arrows, and yellow dots are represented to explain that the vertices of the model being projected onto a 2D plane. (<b>a</b>) A 3D model of bird insignia for crowd formation. (<b>b</b>) An example of a crowd formation formed by using the vertex positions of the model.</p> Full article ">Figure 6
<p>A group moves to a final destination along the path drawn by the user.</p> Full article ">Figure 7
<p>Distance constraints between two objects.</p> Full article ">Figure 8
<p>Comparison of traditional distance constraint and formation constraint: (<b>a</b>) traditional distance constraint, (<b>b</b>) formation constraint.</p> Full article ">Figure 9
<p>Movement of agents to reach their SRD. Agents away from their SRD are colored blue.</p> Full article ">Figure 10
<p>The movement of SRDs as a result of the group’s movement and each agent tracking each target. The SRDs move as much as the group has moved.</p> Full article ">Figure 11
<p>The movement of agents without formation constraints. The white lines attached to each agent are not visible in the actual simulation, but are drawn for illustration purposes. These lines represent the speed magnitude of the agent, with longer lines being faster and shorter lines being slower.</p> Full article ">Figure 12
<p>Neighborhood detection of agents in a grid space. Space 6 is shared by different agents and they perceive each other as obstacles.</p> Full article ">Figure 13
<p>An agent changes direction of travel smoothly through steering force.</p> Full article ">Figure 14
<p>Crowd formation in different ways (<b>a</b>) A 3D mesh for formation constraint; (<b>b</b>) Initial setup of crowds based on a 3D mesh; (<b>c</b>) Circle formation; (<b>d</b>) Rectangle formation.</p> Full article ">Figure 15
<p>Two groups with formation constraints are moving along the path set by user. Yellow arrows indicate the direction of travel for each group.</p> Full article ">Figure 16
<p>The simulations are shown in order from (<b>a</b>–<b>f</b>), two groups with a different formation constraints are crossing each other. There is a breakdown of the formation on the both groups in the middle, but they regain the formation automatically and then reach their respective final destinations.</p> Full article ">Figure 17
<p>Experiments in which various shapes of the crowd formations are crossed. (<b>a</b>) Two groups with the same shape formations. (<b>b</b>) Two groups with different shapes of formations from each other.</p> Full article ">Figure 18
<p>Comparisonof crowd behaviour after obstacle avoidance behaviour. (<b>a</b>) The algorithm from [<a href="#B4-applsci-14-03386" class="html-bibr">4</a>] applied, with no recovery after formation breakdown. (<b>b</b>) Proposed algorithm applied, with recovery after formation breakdown.</p> Full article ">Figure 19
<p>Performance comparison between the original PBD-based crowds and the proposed method.</p> Full article ">Figure 20
<p>A situation where two groups of agents, which regard each other as obstacles, encounter each other in proximity. (<b>a</b>) Screenshot of observation from a simulation of the method proposed by M. Xu et al. [<a href="#B22-applsci-14-03386" class="html-bibr">22</a>]. (<b>b</b>) Observation of our method. The black and white lines are the paths of travel for the blue and red groups, respectively.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop