Two potential fields fused adaptive path planning system for autonomous vehicle under different velocities

Zhixian Liu; Xiaofang Yuan; Guoming Huang; Yaonan Wang; Xizheng Zhang

doi:10.1016/j.isatra.2020.12.015

Two potential fields fused adaptive path planning system for autonomous vehicle under different velocities

ISA Trans. 2021 Jun:112:176-185. doi: 10.1016/j.isatra.2020.12.015. Epub 2020 Dec 16.

Authors

Zhixian Liu¹, Xiaofang Yuan², Guoming Huang³, Yaonan Wang⁴, Xizheng Zhang⁵

Affiliations

¹ College of Electrical and Information Engineering, Hunan University, Changsha, Hunan 410082, China. Electronic address: liuzhixian@hnu.edu.cn.
² College of Electrical and Information Engineering, Hunan University, Changsha, Hunan 410082, China. Electronic address: yuanxiaofang@hnu.edu.cn.
³ College of Electrical and Information Engineering, Hunan University, Changsha, Hunan 410082, China. Electronic address: huangguoming@hnu.edu.cn.
⁴ College of Electrical and Information Engineering, Hunan University, Changsha, Hunan 410082, China. Electronic address: yaonan@hnu.edu.cn.
⁵ Hunan Provincial Key Laboratory of Vehicle Power and Transmission System, Hunan Institute of Engineering, Xiangtan, Hunan, 411104, China. Electronic address: z_x_z2000@163.com.

PMID: 33349454
DOI: 10.1016/j.isatra.2020.12.015

Abstract

Path planning is a basic function for autonomous vehicle (AV). However, it is difficult to adapt to different velocities and different types of obstacles including dynamic obstacle and static obstacle (such as road boundary) for AV. To solve the problem of path planning under different velocities and different types of obstacles, a two potential fields fused adaptive path planning system (TPFF-APPS) which includes two parts, a potential field fusion controller and an adaptive weight assignment unit, is presented in this work. In the potential field fusion controller, a novel potential velocity field is built by velocity information and fused with a traditional artificial potential field for adapting various velocities. The adaptive weight assignment unit is designed to distribute adaptively the weights of two potential fields for adapting different types of obstacles at the same time, including road boundary and dynamic obstacles. The simulation is carried on the Carsim-Matlab co-simulation platform, and the simulation results indicate that the proposed TPFF-APPS has excellent performance for path planning adapting to different velocities and different types of obstacles.

Keywords: Adaptive weight assignment; Path planning; Potential field fusion; Potential velocity field.