Time-Constrained UAV Trajectory Planning Algorithm Based on an Improved DDPG
CHEN Yiwen
XIA Jiawei
JIANG Zhidong
Abstract：This paper proposes a deep deterministic policy gradient algorithm based on Multi-Experience Replay,which aims to solve the problem of time-constrained trajectory optimization of unmanned aerial vehicles.Traditional methods often face the prob-lems of slow optimization speed and poor optimization results when dealing with time-constrained track planning problems.In order to overcome the above shortcomings,this paper innovatively introduces a multi-experience pool playback mechanism to improve the traditional DDPG algorithm.Experimental results show that compared with the traditional optimization methods,the DDPG algo-rithm based on multi-empirical pool playback proposed in this paper has significantly improved the optimization ability and can achieve convergence faster.
Keywords：deep reinforcement learningmulti-experience replaytrajectory planningunmanned aerial vehicletime-con-strained trajectory planning
Publication Date：2025-11-20
Online Publishing Date：2026-01-28(First online date of this platform, not the publication date of the document)
Pages：6( 71-75,98 )