To improve the finding path accuracy of the ant colony algorithm and reduce the number of turns, a jump point search improved ant colony optimization hybrid algorithm has been proposed in this article. Firstly, the initial pheromone concentration distribution gets from the jump points has been introduced to guide the algorithm in finding the way, thus accelerating the early iteration speed. The turning cost factor in the heuristic function has been designed to improve the smoothness of the path. Finally, the adaptive reward and punishment factor, and the Max–Min ant system have been introduced to improve the iterative speed and global search ability of the algorithm. Simulation through three maps of different scales is carried out. Furthermore, the results prove that the jump point search improved ant colony optimization hybrid algorithm performs effectively in finding path accuracy and reducing the number of turns.
In this paper, a vehicle-to-vehicle (V2V) trajectory planning algorithm for two vehicles driving in an arc-shaped road is represented, in which the characteristics of human drivers are taken into consideration. Safety constraints including vehicle stability, road boundaries, and vehicles collision avoidance are considered. The boundary constraint of the arc-shaped road is realized with a potential field method. The potential field method is also employed to realize the vehicles collision avoidance constraint and vehicle distance margin. The concept of partial cooperative control is presented, which can depict the collaboration of the vehicles more accurately. The algorithm is designed with a partial cooperative control pattern, employing model predictive control (MPC). The effectiveness of the algorithm is verified by software simulation in a scenario of overtaking in arc-shaped roads. The algorithm can accomplish the V2V collaboration trajectory planning task successfully. The performance of the algorithm representing different collaboration degrees and phases grouping in complex scenarios is also studied.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.