A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles

By Adrian Carrio, Carlos Sampedro, Alejandro Rodriguez-Ramos, Pascual Campoy Cervera. J. Sensors, 2017

339 citations recorded by the source corpus.

Deep learning is recently showing outstanding results for solving a wide variety of robotic tasks in the areas of perception, planning, localization, and control. Its excellent capabilities for learning representations from the complex data acquired in real environments make it extremely suitable for many kinds of autonomous robotic applications. In parallel, Unmanned Aerial Vehicles (UAVs) are currently being extensively applied for several types of civilian tasks in applications going from security, surveillance, and disaster rescue to parcel delivery or warehouse management. In this paper, a thorough review has been performed on recent reported uses and applications of deep learning for UAVs, including the most relevant developments as well as their performances and limitations. In addition, a detailed explanation of the main deep learning techniques is provided. We conclude with a description of the main challenges for the application of deep learning for UAV-based solutions.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/58eb6ed4667dd044698d70e127577655c227ba19

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Survey on Collaborative Smart Drones and Internet of Things for Improving Smartness of Smart Cities (2019, background): “The authors of [30] designed powerful and useful devices for processing data”
A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, background): “Autonomous Vehicles Planning and Decision-Making for Autonomous Vehicles [255] A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles [256]”
Unmanned Aerial Vehicles (UAVs): A Survey on Civil Applications and Key Research Challenges (2018, positive): “and implement on-board, low power, and efficient deep learning solutions in support of SAR operations using UAVs [58].”
Recent Advances in Convolutional Neural Network Acceleration (2018, background): “rize the relevant work regarding deep neural networks in dierent applications such as computer vision, natural language processing and acoustic signal processing, among which CNN is only a component [13,14,15,16,17,18]. They make systematic introduction for various kinds of neural networks that are ”
Unmanned aerial vehicles (UAVs): practical aspects, applications, open challenges, security issues, and future trends (2023, background): “researchers should find deep-learning-based novel strategies for UAVs, particularly for SAR mission [144].”
Challenges in Deploying Machine Learning: A Survey of Case Studies (2020, background): “This notion is exemplified by the field of unmanned aerial vehicles (UAV) [35].”
A Fully-Autonomous Aerial Robot for Search and Rescue Applications in Indoor Environments using Learning-Based Techniques (2018, background): “The use of machine learning techniques, when trained on meaningful datasets, allows overcoming these limitations, providing more versatile solutions which can be executed in a wide range of environments [7].”
Adversarial Robustness vs. Model Compression, or Both? (2019, background): “Besides deployments on the cloud, deep learning has become ubiquitous on embedded systems such as mobile phones, IoT devices, personal healthcare wearables, autonomous driving [4, 11], unmanned aerial systems [6, 23], etc.”