南京信息工程大学学报2026，Vol.18Issue(1)：69-75,7.DOI:10.13878/j.cnki.jnuist.20241215002
基于APF-MASAC算法的多无人车路径规划研究
Multi-unmanned vehicle path planning via APF-MASAC algorithm
摘要
Abstract
To address the path planning problem for multiple unmanned vehicles in real-world environments,this paper proposes an algorithm design scheme under the Multi-Agent Soft Actor-Critic(MASAC)framework.To en-hance the algorithm's performance,we propose three improvements.First,drawing inspiration from the Artificial Po-tential Field(APF)concept,we design a dense reward function based on potential shaping techniques to provide abundant,timely and effective feedback signals during the learning process,thereby significantly accelerating con-vergence.Second,the traditional experience replay buffer is modified by adopting a double-consecutive-frame tech-nique.This approach incorporates two consecutive observation frames as unified units into the experience replay buffer,effectively capturing environmental dynamics and improving training stability.Third,a highly realistic dynam-ic obstacle environment is constructed using the Gazebo simulation platform,which provides diverse and challenging training samples,ensuring comprehensive learning and optimization under near-real conditions.Finally,the effective-ness of the proposed APF-MASAC algorithm is validated through ablation experiments and robustness tests.关键词
强化学习/多智能体/人工势场/路径规划/无人车Key words
reinforcement learning/multi-agent/artificial potential field(APF)/path planning/unmanned vehicle分类
交通工程引用本文复制引用
闫冬梅,杨南禹,许佳佳,刘磊..基于APF-MASAC算法的多无人车路径规划研究[J].南京信息工程大学学报,2026,18(1):69-75,7.基金项目
安徽省普通高校交通信息与安全重点实验室开放课题(KLAHEI180188) （KLAHEI180188）
教育部海上智能网信技术教育部重点实验室开放课题(2014AA110501) （2014AA110501）
