Deep-Reinforcement-Learning-Based Collision Avoidance in UAV Environment

被引:56
作者
Ouahouah, Sihem [1 ]
Bagaa, Miloud [1 ]
Prados-Garzon, Jonathan [2 ]
Taleb, Tarik [1 ,3 ]
机构
[1] Aalto Univ, Sch Elect Engn, Dept Commun & Networking, Espoo 00076, Finland
[2] Univ Granada, Dept Signal Theory Telemat & Commun, Granada 18014, Spain
[3] Sejong Univ, Dept Comp & Informat Secur, Seoul 05006, South Korea
关键词
Sensors; Unmanned aerial vehicles; Collision avoidance; Reinforcement learning; Vehicular ad hoc networks; Regulation; Industries; deep reinforcement learning; machine learning; multiaccess-edge computing (MEC); unmanned aerial vehicles (UAVs);
D O I
10.1109/JIOT.2021.3118949
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Unmanned aerial vehicles (UAVs) have recently attracted both academia and industry representatives due to their utilization in tremendous emerging applications. Most UAV applications adopt visual line of sight (VLOS) due to ongoing regulations. There is a consensus between industry for extending UAVs' commercial operations to cover the urban and populated area-controlled airspace beyond VLOS (BVLOS). There is ongoing regulation for enabling BVLOS UAV management. Regrettably, this comes with unavoidable challenges related to UAVs' autonomy for detecting and avoiding static and mobile objects. An intelligent component should either be deployed onboard the UAV or at a multiaccess-edge computing (MEC) that can read the gathered data from different UAV's sensors, process them, and then make the right decision to detect and avoid the physical collision. The sensing data should be collected using various sensors but not limited to Lidar, depth camera, video, or ultrasonic. This article proposes probabilistic and deep-reinforcement-learning (DRL)-based algorithms for avoiding collisions while saving energy consumption. The proposed algorithms can be either run on top of the UAV or at the MEC according to the UAV capacity and the task overhead. We have designed and developed our algorithms to work for any environment without a need for any prior knowledge. The proposed solutions have been evaluated in a harsh environment that consists of many UAVs moving randomly in a small area without any correlation. The obtained results demonstrated the efficiency of these solutions for avoiding the collision while saving energy consumption in familiar and unfamiliar environments.
引用
收藏
页码:4015 / 4030
页数:16
相关论文
共 34 条
[1]  
Albaker B.M., 2009, P INT C TECH POSTGR, DOI DOI 10.1109/TECHPOS.2009.5412074
[2]  
Amarasinghe S. V., 2014, 2014 9th International Conference on Industrial and Information Systems (ICIIS), P1, DOI 10.1109/ICIINFS.2014.7036570
[3]  
Bekkouche O, 2018, IEEE GLOB COMM CONF
[4]   Unmanned aerial vehicles using machine learning for autonomous flight; state-of-the-art [J].
Choi, Su Yeon ;
Cha, Dowan .
ADVANCED ROBOTICS, 2019, 33 (06) :265-277
[5]  
Do-Hoon Kim, 2011, Proceedings of the 2011 13th International Conference on Advanced Communication Technology (ICACT). Smart Service Innovation through Mobile Interactivity, P326
[6]   Multi-Sensor-Based Fully Autonomous Non-Cooperative Collision Avoidance System for Unmanned Air Vehicles [J].
Fasano, Giancarmine ;
Accardo, Domenico ;
Moccia, Antonio ;
Carbone, Ciro ;
Ciniglio, Umberto ;
Corraro, Federico ;
Luongo, Salvatore .
JOURNAL OF AEROSPACE COMPUTING INFORMATION AND COMMUNICATION, 2008, 5 (10) :338-360
[7]   A Review on IoT Deep Learning UAV Systems for Autonomous Obstacle Detection and Collision Avoidance [J].
Fraga-Lamas, Paula ;
Ramos, Lucia ;
Mondejar-Guerra, Victor ;
Fernandez-Carames, Tiago M. .
REMOTE SENSING, 2019, 11 (18)
[8]   UAV autonomous collision avoidance approach [J].
He, Renke ;
Wei, Ruixuan ;
Zhang, Qirui .
AUTOMATIKA, 2017, 58 (02) :195-204
[9]   Real-time implementation of moving object detection in UAV videos using GPUs [J].
Jaiswal, Deepak ;
Kumar, Praveen .
JOURNAL OF REAL-TIME IMAGE PROCESSING, 2020, 17 (05) :1301-1317
[10]  
Kim KY, 2007, 2007 INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS, VOLS 1-6, P2490