UAV 3D online track planning based on improved SAC algorithm

被引：0
作者：
Yuxiang Zhou
Jiansheng Shu
Hui Hao
Huan Song
Xiaochang Lai
机构：
[1] Xi’an Research Institute of High Technology,
来源：
Journal of the Brazilian Society of Mechanical Sciences and Engineering | 2024年 / 46卷
关键词：
UAV; Online track planning; SAC algorithm; Self-attention; Artificial potential field;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Online track planning technology is a key technology to improve the survivability and intelligence of UAVs. In this paper, a Soft Actor-Critic (SAC)-based online track planning algorithm is proposed by combining Artificial Potential Field (APF) algorithm and self-attentive mechanism. First, for the characteristics of high-dimensional complexity of environmental states presented in the 3D environmental space, the self-attention mechanism is introduced in the Actor network of SAC algorithm in order to analyze and process the state information. Secondly, the artificial potential field method is combined with the reward function of SAC algorithm to solve the problem of reward sparsity in online track planning. Finally, the observation, action, and reward functions of the algorithm are designed according to the characteristics of UAV online track planning. The experimental results show that the algorithm convergence speed and success rate of the improved SAC algorithm are significantly improved, which can realize the 3D online track planning of UAVs.
引用
收藏
相关论文
共 81 条
[1]  
Zhu M(2018)Human-like autonomous car-following model with deep reinforcement learning Transportation Research Part C: Emerging Technologies 97 348-368
[2]  
Wang X(2022)UAV path planning using optimization approaches: a survey Arch Computat Methods Eng 33 431-450
[3]  
Wang Y(2016)Autonomous, vision-based flight and live dense 3d mapping with a quadrotor micro aerial vehicle J Field Robotics 33 189-214
[4]  
AitSaadi A(2012)River mapping from a flying robot: state estimation, river detection, and obstacle mapping Auton Robot 9 59486-59497
[5]  
Soukane A(2021)UAV path planning based on multi-layer reinforcement learning technique IEEE Access 25 335-348
[6]  
Meraihi Y(1989)Model predictive control: theory and practice—a survey Automatica 71 231-253
[7]  
BenmessaoudGabis A(2013)A probabilistically robust path planning algorithm for UAVs using rapidly-exploring random trees J Intell Robot Syst 22 1558-33
[8]  
Mirjalili S(2022)Modified artificial potential field for the path planning of aircraft swarms in three-dimensional environments Sensors 2019 70-1063
[9]  
Ramdane-Cherif A(2019)Obstacle avoidance of mobile robots using modified artificial potential field algorithm J Wireless Com Network 4 23-430
[10]  
Faessler M(1997)The dynamic window approach to collision avoidance IEEE Robot Automat Mag 31 1058-444
123456789