Deep Learning for Unmanned Systems/Глубокое обучение по беспилотным системам

Издание на английском языке
Deep learning (DL) has been applied to awide range of research areas, such as prediction, classification, image/talk recognition, and vision, and has greatly surpassed conventional methodologies. The main difference between other approaches and indepth research is the computational simulation of neural network layers by learning and multilevel representation. Therefore, the dynamic nature of large data sets can be easily understood by deep learning. Deep learning models can therefore provide insights into the complex structures of large data sets. Deep learning methods have been shown to outperform previous state-of-the-art techniques in several tasks because of the abundance of complex data from various sources (e.g., visual, audio, medical, social, and sensor).

Contents
Deep Learning for Unmanned Autonomous Vehicles: A Comprehensive Review. Alaa Khamis, Dipkumar Patel, and Khalid Elgazzar
Deep Learning and Reinforcement Learning for Autonomous Unmanned Aerial Systems: Roadmap for Theory to Deployment. Jithin Jagannath, Anu Jagannath, Sean Furman, and Tyler Gwin
Reactive Obstacle Avoidance Method for a UAV. Zhaowei Ma, Jia Hu, Yifeng Niu, and Hongbo Yu
Guaranteed Performances for Learning-Based Control Systems Using Robust Control Theory. Balazs Nemeth and Peter Gaspar
A Cascaded Deep Neural Network for Position Estimation of Industrial Robots. Weiyang Lin, Chao Ye, Jiaoju Zhou, Xinyang Ren, and Mingsi Tong
Managing Deep Learning Uncertainty for Unmanned Systems. Armando Plasencia Salgueiro, Lynnette Gonzalez Rodriguez, and Ileana Suarez Blanco
Uncertainty-Aware Autonomous Mobile Robot Navigation with Deep Reinforcement Learning. Lynnette Gonzalez-Rodriguez and Armando Plasencia-Salgueiro
Deep Reinforcement Learning for Autonomous Mobile Networks in Micro-grids. Marco Miozzo, Nicola Piovesan, Dagnachew Azene Temesgene, and Paolo Dini
Reinforcement Learning for Autonomous Morphing Control and Cooperative Operations of UAV Cluster. Dan Xu and Gang Chen
Bioinspired Robotic Arm Planning by t-Jerk Theory and Recurrent Multilayered ANN. I. Carvajal, E. A. Martinez-Garcia, R. Torres-Cordoba, and V. M. Carrillo-Saucedo
Deep Learning Based Formation Control of Drones. Kader M. Kabore and Samet Guler
Image-Based Identification of Animal Breeds Using Deep Learning. Pritam Ghosh, Subhranil Mustafi, Kaushik Mukherjee, Sanket Dan, Kunal Roy, Satyendra Nath Mandal, and Santanu Banik
Image Registration Algorithm for Deep Learning-Based Stereo Visual Control of Mobile Robots. Zoran Miljkovic, Aleksandar Jokic, and Milica Petrovic
Search-Based Planning and Reinforcement Learning for Autonomous Systems and Robotics. Than Le, Bui Thanh Hung, and Pham Van Huy
Playing Doom with Anticipator-A3C Based Agents Using Deep Reinforcement Learning and the ViZDoom Game-AI Research Platform. Adil Khan, Muhammad Naeem, Asad Masood Khattak, Muhammad Zubair Asghar, and Abdul Haseeb Malik
Deep Reinforcement Learning for Quadrotor Path Following and Obstacle Avoidance. Bartomeu Rubi, Bernardo Morcego, and Ramon Perez
Playing First-Person Perspective Games with Deep Reinforcement Learning Using the State-of-the-Art Game-AI Research Platforms. Adil Khan, Asad Masood Khattak, Muhammad Zubair Asghar, Muhammad Naeem, and Aziz Ud Din
Language Modeling and Text Generation Using Hybrid Recurrent Neural Network. Samreen, Muhammad Javed Iqbal, Iftikhar Ahmad, Suleman Khan, and Rizwan Khan
Detection and Recognition of Vehicle’s Headlights Types for Surveillance Using Deep Neural Networks. Sikandar Zaheer, Muhammad Javed Iqbal, Iftikhar Ahmad, Suleman Khan, and Rizwan Khan
Recent Advances of Deep Learning in Biology. Muhammad Shahid Iqbal, Iftikhar Ahmad, Tamoor Khan, Suleman Khan, Muneer Ahmad, and Lulu Wang