CMSV: a New Cloud Multi-Agents for Self-Driving Vehicles as a Services

The development of autonomous vehicles has changed the way of transmitting goods to users, with the potential to improve road safety and efficiency. One of the effective issues of self-driving vehicles is path planning issue. In this paper, a new system is proposed for addressing the potential of us...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of grid computing Jg. 22; H. 1; S. 11
1. Verfasser: Nasr, Aida A.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Dordrecht Springer Netherlands 01.03.2024
Springer Nature B.V
Schlagworte:
Algorithms
Ant colony optimization
Autonomous cars
Autonomous vehicles
Computer Science
Genetic algorithms
Management of Computing and Information Systems
Multiagent systems
Particle swarm optimization
Path planning
Processor Architectures
Traffic safety
User Interfaces and Human Computer Interaction
Vehicles
Cloud computing
CMSV
Path planning
Self-driving vehicles
Multi-agents’ system
ISSN:1570-7873, 1572-9184
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The development of autonomous vehicles has changed the way of transmitting goods to users, with the potential to improve road safety and efficiency. One of the effective issues of self-driving vehicles is path planning issue. In this paper, a new system is proposed for addressing the potential of using multi-agent systems (MAS) to address path planning problems in autonomous vehicles. The system is called Cloud Multi-Agents for Self-Driving Vehicles as A Services (CMSV). It is used to solve the dependent delivery problem, where the vehicle transmits the goods/deliveries, that are dependent on each other, to specific locations in ordering or with specific directions. The new system consists of three phases: (1) converting the problem into TSP sub problems according to deliveries dependency, (2) applying GDC to select the good solutions (3) applying multi-agent system to select the optimal solution. The proposed system is compared with systems that use a genetic algorithm, Ant Colony algorithm, Particle Swarm Optimization and The Harris hawk optimization (HHO) algorithm. From the findings, we find that the proposed system is more efficient than the other systems.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1570-7873
1572-9184
DOI:10.1007/s10723-023-09734-2