A 3D Path Planning Algorithm for the UAV Based on the Improved Double-DqnAlgorithm
Authors:
- 17 November 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 6412-6417
Abstract
In this paper, in order to solve the 3D path planning problem of the unmanned aerial vehicle (UAV) in unknown environments with obstacles, an improved Double-deep Q network (DQN) algorithm is proposed. In order to solve the problem of sparse rewards in the process of deep reinforcement learning training, a mechanism of energy efficiency reward is designed, and then the 3D path of the VAV is shortened and smoothed. In addition, a mechanism of priority experience replay based on the queue is proposed to improve the sampling probability of relatively good experience, so that the training time is reduced and the success rate is improved. Simulation results show that, compared with the traditional method, the algorithm proposed in this paper can shorten the average number of steps required to reach the maximum score and improve the training success rate.Keywords
Funding Information
- National Natural Science Foundation of China (61903198)
This publication has 9 references indexed in Scilit:
- Ga-DQN: A Gravity-aware DQN Based UAV Path Planning Algorithm2022
- DRL-Based Improvement for Autonomous UAV Motion Path Planning in Unknown Environments2022
- Quality-Oriented Hybrid Path Planning Based on A* and Q-Learning for Unmanned Aerial VehicleIEEE Access, 2021
- UAV Path Planning using Global and Local Map Information with Deep Reinforcement Learning2021
- A Memetic Path Planning Algorithm for Unmanned Air/Ground Vehicle Cooperative Detection SystemsIEEE Transactions on Automation Science and Engineering, 2021
- Multi-UAV 3D Path Planning in Simultaneous Attack2020
- Travelling salesman problem for UAV path planning with two parallel optimization algorithms2017
- Deep Reinforcement Learning with Double Q-LearningProceedings of the AAAI Conference on Artificial Intelligence, 2016
- Human-level control through deep reinforcement learningNature, 2015