Research On Path Tracking Of Autonomous Vehicles Based On Pure Pursuit Algorithm And Salp Swarm Algorithm

With the rapid development of artificial intelligence and big data,autonomous driving technology has set off a research boom in the world,attracting the attention of all sectors of society.Autonomous driving technology is mainly divided into four parts: environment perception,behavior decision-making,path planning,and path tracking.Among them,the path tracking part controls the vehicle to accurately follow the reference path generated by the path planning part,which is an important research direction in autonomous driving technology.Therefore,it is meaningful to develop path tracking algorithms with high tracking accuracy and high real-time performance.Pure pursuit algorithm is one of the most effective path tracking methods in autonomous vehicles.Compared with other path tracking algorithms,the implementation principle of pure pursuit algorithm is simpler and the tracking effect is better.However,the tracking accuracy of existing pure pursuit algorithms are affected by the look-ahead distance.If the look-ahead distance is set too large,the tracking path of the vehicle is too smooth.The phenomenon of "shortcut" appears in some paths,and the tracking accuracy is reduced.Setting the look-ahead distance too small will cause the vehicle’s path tracking behavior to "oscillate" and the vehicles’ movement are unstable.In response to the above problems,this paper conducts a systematic study of pure pursuit algorithms,and proposes a pure pursuit algorithm based on optimized look-ahead distance.Its main innovations include the following four aspects:(1)In order to find the best look-ahead distance of pure pursuit algorithm,Salp Swarm Algorithm is introduced in pure pursuit algorithm.(2)To enhance the development and exploration capabilities of Salp Swarm Algorithm,a random particle motion mechanism named Brownian motion is introduced into Salp Swarm Algorithm.(3)In order to speed up the convergence speed of Salp Swarm Algorithm,a weighting mechanism is designed,which uses two different weights during the search process to adjust the salps closer to the food source quickly.(4)To ensure that the vehicle reaches its destination at a specified time,a velocity controller which outputs the speed of the next moment according to the distance and time interval between the look-ahead point and the current vehicle position is designed.This article conducts experiments on four different paths,including straight paths,sinusoidal paths,arched paths,and lane-changing paths,and compares the corresponding tracking results with other pure pursuit algorithms that use different look-ahead distances.Experimental results show that the tracking performance of this algorithm is better than other algorithms.Improving pure pursuit algorithm is the research focus of this article.This article mainly uses the Salp Swarm Algorithm to optimize the key parameter look-ahead distance of pure pursuit algorithm to improve the tracking accuracy of the pure pursuit algorithm.In addition,Brownian Motion is introduced into the Salp Swarm Algorithm and an adaptive weight mechanism is designed to improve the optimization performance of the algorithm.Finally,a velocity controller is added to pure pursuit algorithm to ensure that the vehicle arrives at the destination on time and improves punctuality.