智能科学与技术学报2025，Vol.7Issue(3)：381-395,15.DOI:10.11959/j.issn.2096-6652.202531
基于KPPO算法的四旋翼无人机飞行控制
Quadrotor UAV flight control based on the KPPO algorithm
摘要
Abstract
To address the issues of slow convergence and the difficulty of adapting to complex environments in proximal policy optimization(PPO)algorithms for quadrotor UAV flight control,an improved algorithm was proposed,KPPO,which integrated a composite regularization mechanism composed of a threshold-triggered KL divergence penalty and an L2 regularization term based on the PPO framework.The proposed KPPO algorithm was applied to quadrotor UAV flight control tasks.Physical simulation validation of quadrotor UAV flight control demonstrates that under the guidance of the KPPO strategy,the quadrotor UAV rapidly achieves policy convergence and makes correct decisions in complex environ-ments,thereby significantly enhancing the performance of conventional algorithms.Notably,the KPPO algorithm im-proves task execution efficiency,a key factor in quadrotor UAV operations.This reassures the audience of the effective-ness of the KPPO algorithm in improving quadrotor UAV flight control.关键词
近端策略优化算法/四旋翼无人机飞行控制/深度强化学习Key words
proximal policy optimization/quadrotor UAV flight control/deep reinforcement learning分类
信息技术与安全科学引用本文复制引用
武子怡,高晓楠,朱献超,赵亮,祝峰,蔡磊..基于KPPO算法的四旋翼无人机飞行控制[J].智能科学与技术学报,2025,7(3):381-395,15.基金项目
河南省自然科学基金青年项目(No.252300421806) （No.252300421806）
河南工业大学高层次人才引进项目(No.2022BS073) （No.2022BS073）
河南省高校科技创新团队项目(No.25IRTSTHN018) （No.25IRTSTHN018）
中原科技创新领军人才计划(No.254000510043) （No.254000510043）
河南省重点研发专项(No.241111110200)Natural Science Foundation of Henan(No.252300421806),Research Foundation for Advanced Talents of Henan University of Technology(No.2022BS073),Scientific and Technological Innovation Teams of Universities in Henan Province(No.25IRTSTHN018),Zhongyuan Science and Technology Innovation Leadership Talent Program(No.254000510043),Henan Provin-cial Key R&D Special Project(No.241111110200) （No.241111110200）
