An integrated clustering algorithm based on firefly algorithm and self-organized neural network

Jenghara, Moslem Mohammadi; Mobarakeh, Majid Iranpour

doi:10.1007/s13748-022-00275-5

Cited by 4 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pseudocode for FA is described in Table 10. The FA has been implemented in diverse research areas, including robotics [91,92], machine learning [93], journalism [94], and cloud computing [95]. Table 11 presents a compilation of techniques proposed for FA's application in smart vehicle navigation.…”

Section: Firefly Algorithm (Fa)mentioning

confidence: 99%

Optimizing Path Planning for Smart Vehicles: A Comprehensive Review of Metaheuristic Algorithms

Mbah,

Zeeshan

2023

JEMSE

View full text Add to dashboard Cite

In the realm of smart vehicle navigation, both in known and unknown environments, the crucial aspects encompass the vehicle's localization using an array of technologies such as GPS, cameras, vision systems, laser, and ultrasonic sensors. This process is pivotal for effective motion planning within the vehicle's free configuration space, enabling it to adeptly avoid obstacles. The focal point of such navigation systems lies in devising a path from an initial to a target configuration, striving to minimize the path length and the time taken, while simultaneously circumventing obstacles. The application of metaheuristic algorithms has been pivotal in this regard. These algorithms, characterized by their ability to exploit initial solutions and explore the environment for feasible pathways, have been extensively utilized. A significant body of research in robotics and automation has focused on evaluating the efficacy of population-based algorithms including Genetic Algorithm (GA), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Firefly Algorithm (FA), and Whale Optimization Algorithm (WOA). Additionally, trajectory-based methods such as Tabu Search (TS) and Simulated Annealing (SA) have been scrutinized for their proficiency in identifying short, feasible paths among the plethora of solutions. There has been a surge in the enhancement and modification of these algorithms, with a multitude of hybrid metaheuristic algorithms being proposed. This review meticulously examines various metaheuristic algorithms and their hybridizations, specifically in their application to the path planning challenges faced by smart vehicles. The exploration extends to the comparison of these algorithms, highlighting their distinct advantages and limitations. Furthermore, the review delves into potential future directions in this evolving field, emphasizing the continual refinement of these algorithms to cater to the increasingly complex demands of smart vehicle navigation.

show abstract