A Real-Time meta-heuristic-based safe navigation approach for mobile robots in unknown environments

• Ano de defesa: 2025
• Autor(a) principal: Balza, Micael
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• Instituição de defesa: Universidade Federal do Rio Grande do Norte; BR; UFRN; PROGRAMA DE PÓS-GRADUAÇÃO EM ENGENHARIA ELÉTRICA E DE COMPUTAÇÃO
• Palavras-chave em Português: Autonomous navigation; Metaheuristic; Mobile robots; Path planning; Unknown environment; ENGENHARIAS::ENGENHARIA ELETRICA
• Link de acesso: https://repositorio.ufrn.br/handle/123456789/63578

Autonomous navigation in mobile robots is a complex challenge, particularly in unknown and dynamic environments where obstacle avoidance and real-time trajectory optimization are crucial. This work introduces the MetaHeuristic Real-Time Safe Navigation (MHRTSN) strategy, which integrates potential fields with population-based metaheuristics to enhance trajectory planning and navigation efficiency. The proposed strategy was evaluated through a series of simulations in different static and dynamic scenarios, comparing the performance of two versions: MetaHeuristic Real-Time Safe Navigation with Genetic Algorithm (MHRTSN-GA) and MetaHeuristic Real-Time Safe Navigation with Particle Swarm Optimization (MHRTSN-PSO). The evaluation considered key metrics such as displacement, distance traveled, CPU time, and clock time. The results indicate that both versions provide sub-optimal solutions, with MHRTSN-PSO demonstrating superior performance in terms of computational efficiency and convergence when using a small population size. Comparisons with existing approaches in the literature revealed that MHRTSN generated paths of similar length while maintaining a safer distance from obstacles. Thus, the proposed approach offers an efficient and safe solution for autonomous navigation in mobile robots, contributing to advancements in real-world robotic applications.