An Optimization-Based Path Planning Approach for Autonomous Vehicles Using the DynEFWA-Artificial Potential Field

With the rapid development of autonomous driving technology, collision avoidance has become a research hotspot since it has the potential to increase safety. To obtain a collision-free path, the artificial potential field (APF) is widely used as a path planning method. APF is capable of establishing functional relationships between the vehicle and surrounding objects. However, the function features of the traditional APF method can cause autonomous vehicles to fall into the local minimum, and the generated zigzag path may be difficult to follow. Motivated by these challenges, this paper proposes a real-time path planning method for autonomous vehicles using the dynamic enhanced firework algorithm-APF. Firstly, to improve the safety and smoothness of the planned path by the traditional APF method, the constraints of the vehicle dynamics and different types of obstacles are taken into consideration. Secondly, an optimization problem is formulated to find an optimal path with the least cost in the driving area. Finally, the proposed method is verified with both a simulation and a hardware-in-loop test environment. The results show that the studied autonomous vehicle successfully avoids obstacles and arrives at the goal position by using the proposed path-planning method, and the path smoothness is improved.

I. Introduction

Alarge number of traffic accidents have happened in recent years, and as a result, thousands of people have gotten injured [1]. Moreover, the rising number of drivers on the road is leading to increased traffic congestion [2]. Therefore, traffic safety and efficiency are urgent problems. Emerging technologies like vehicle-to-vehicle (V2V)communication in autonomous vehicles have the capacity to reduce the occurrence of traffic accidents and improve traffic efficiency [3], [4], and have thus attracted significant attention from academia and industry [5]. Generally, there are four aspects of autonomous driving technology: environment perception, behavior decision, path planning, and motion control [6]. The function of path planning is to generate a collision-free path that meets the road regulations. Designing a proper path planning method to effectively enhance the driving safety of autonomous vehicles and also improve traffic efficiency is a complicated problem.