Research On Intelligent Vehicle Path Planning Method Based On Swarm Intelligence Algorithm

The intelligent vehicle offers a promising solution to enhance car safety and alleviate traffic congestion issues,expanding its application in various fields.Path planning,as an essential component bridging perception and control systems within intelligent vehicles,serves as a fundamental prerequisite to realize autonomous driving and embodies one of the core technologies fundamental to intelligent vehicles.In this context,research aimed at achieving intelligent vehicle path planning stands as a crucial enabler towards boosting the application of intelligent driving technology and enhancing vehicle driving safety performance.The present study places a special emphasis on examining intelligent vehicle global path planning and obstacle avoidance trajectory planning in dynamic environments using swarm intelligence algorithms.The main objectives of this research article are outlined as follows:(1)A Gaussian projection-based campus topology map generation method is studied.Topology maps are frequently employed in global path planning for intelligent vehicles,given their capacity to represent node connection relationships via a simple structure.To obtain high-precision longitudinal and latitudinal coordinates of campus roads,we adopt advanced combination navigation equipment and convert them into geodetic coordinates using a Gaussian projection.Next,we establish the adjacency matrix of the topology map following the connection relationships and road traffic rules.(2)A global path planning method based on improved ant colony algorithm is established.The traditional ant colony algorithm is prone to slow convergence and may become trapped in locally optimal solutions.Hence,we design an innovative global pheromone update strategy and heuristic function to address these issues.Through simulation experiments,we demonstrate that the improved ant colony algorithm outperforms traditional ant colony algorithms and two other global planning algorithms in terms of the minimal path length,the lowest number of convergence iterations,and the optimized algorithm reduced the running time from 3.2s to 1.52s,resulting in higher efficiency.(3)A local path planning method based on improved artificial bee colony algorithm is constructed.By applying velocity planning in ST space based on the Frenet coordinate system,we improve the algorithm for intelligent vehicle local path planning using the honey source search and update strategies.With respect to dynamic obstacle avoidance,simulation results indicate that the planned trajectory produces maximum lateral acceleration of,and the maximum lateral impact degree,meets the requirements for comfortable seating validation.(4)The joint simulation experiment and actual vehicle test of intelligent vehicle obstacle avoidance trajectory planning were carried out.A Simulink-Pre Scan-Car Sim joint simulation platform was constructed,and the results show that the proposed algorithm can real-time plan reference trajectories that meet vehicle kinematic constraints,and the lateral and longitudinal acceleration and impact degree of the trajectory all meet the requirements of comfort.In the actual vehicle test,verified the effectiveness of improved Artificial Bee Colony algorithm in obstacle avoidance for static and low-speed dynamic obstacles,and the maximum lateral jerk for trajectory planning for two types of obstacles are 0.78m/s~3 and0.11m/s~3,meeting the comfort verification requirements.