计算技术与自动化2024，Vol.43Issue(2)：82-87,6.DOI:10.16339/j.cnki.jsjsyzdh.202402014
基于PBRS-SAC算法的无人车路径规划研究
Study on Path Planning for Unmanned Vehicles Using PBRS-SAC Algorithm
杨南禹 1时正华1
作者信息
- 1. 河海大学 理学院,江苏 南京 211100
- 折叠
摘要
Abstract
Aiming at the path planning problem of unmanned vehicles in complex environments,an improvement was made within the framework of the soft actor-critic algorithm.The PBRS-SAC algorithm was designed by incorporating the i-dea of potential-based reward shaping into the reward function design,and by integrating training techniques such as double concatenation frames.Subsequently,a simulation environment based on Gazebo was constructed on the Ubuntu operating system to simulate static and dynamic experimental environments for training.Finally,the effectiveness of the algorithm was assessed through ablation experiments,sensitivity testing experiments,and conducted robustness analysis experiments.关键词
强化学习/无人车/势能/奖励函数/路径规划Key words
reinforcement learning/UGV/potential energy/reward function/path planning分类
信息技术与安全科学引用本文复制引用
杨南禹,时正华..基于PBRS-SAC算法的无人车路径规划研究[J].计算技术与自动化,2024,43(2):82-87,6.
