<![CDATA[This research demonstrates nature-inspired control systems for the navigation of autonomous vehicles (AVs), utilizing algorithms derived from nature Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC) to tackle challenges posed by dynamic environments. ACO is based on the pheromone trails of ants to facilitate adaptive route selection, PSO draws inspiration from bird flocking behavior for optimal pathfinding, and ABC imitates the division of labor seen in bee swarms for decentralized decision-making. A combined ACO-PSO model merges ACO's capability for local adaptability with PSO's ability for global convergence, allowing for real-time modifications to paths. Simulations conducted on the CARLA and SUMO platforms illustrate improvements in navigation stability and responsiveness, showcasing enhancements in trajectory smoothness by 15%, collision avoidance by 22%, and congestion reduction by 18% when faced with unexpected obstacles and variable traffic conditions. The findings support the notion that bio-inspired systems can serve as scalable and resilient alternatives to conventional algorithms, providing strong solutions for the emergence of next-generation AV technologies. This study connects biological concepts with artificial autonomy to develop intelligent transportation systems using hybrid algorithms and real-time adaptive learning. Biologically inspired models enhance decision-making in complex environments. However, limitations such as high computational complexity and challenges in scaling the system for real-world applications are acknowledged.]]>
Copyrights © 2025
