Obstacle Avoidance Path Planning Strategy for Autonomous Vehicles Based on Genetic Algorithm

In order to enhance the driving ability of autonomous vehicles on structured roads and enable them to plan safe and comfortable paths, we propose an obstacle avoidance path strategy for autonomous vehicles based on genetic algorithm. The use of Frenet-Serret enhances the adaptability of the algorith...

Full description

Saved in:
Bibliographic Details
Published in:Promet Vol. 36; no. 4; pp. 733 - 748
Main Authors: WENG, Xiaofeng, LIU, Fei, ZHOU, Sheng, MAI, Jiacheng, FENG, Shaoxiang
Format: Journal Article Paper
Language:English
Published: Sveučilište u Zagrebu Fakultet prometnih znanosti 01.01.2024
University of Zagreb, Faculty of Transport and Traffic Sciences
Subjects:
anti-collision model
autonomous vehicle
genetic algorithm
path planning
sequential quadratic programming (SQP)
ISSN:0353-5320, 1848-4069
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to enhance the driving ability of autonomous vehicles on structured roads and enable them to plan safe and comfortable paths, we propose an obstacle avoidance path strategy for autonomous vehicles based on genetic algorithm. The use of Frenet-Serret enhances the adaptability of the algorithm in complex environments. In order to improve the generation and optimisation of obstacle avoidance trajectory, we establish an anti-collision model. When the vehicle faces a potential collision with an obstacle, the genetic algorithm quickly iterates and selects the first nine genes to generate the rough solution and convex space of the path. Combined with convex space, the quadratic programming method will numerically optimise the generated rough solution to generate an accurate path that satisfies the constraints. In addition, in order to ensure the safety and comfort in the process of obstacle avoidance, based on the dynamic constraints of the vehicle, the speed planning is used to determine the speed curve. We simulate in various scenarios involving moving obstacles. The real-time simulation based on the HIL platform proves that the proposed path planning strategy is effective in various driving scenarios.
Bibliography:320281
ISSN:0353-5320
1848-4069
DOI:10.7307/ptt.v36i4.528