We use cookies to improve your website experience. To learn about our use of cookies and how you can manage your cookie settings, please see our Cookie Policy. By closing this message, you are consenting to our use of cookies.

Add your Insight

Manuscript deadline
20 January 2022

Cover image - Journal of Control and Decision

Journal of Control and Decision

Special Issue Editor(s)

Dr. BalaAnand Muthu, Adhiyamaan College of Engineering, India
[email protected]

Dr. Imran Shafique Ansari, University of Glasgow
[email protected]

Dr. Xuan Liu (yusuf), Yangzhou University, China
[email protected]

Visit JournalArticles

Deep Learning for Unmanned Vehicle Systems

Unmanned Vehicle Systems (UVS) is an important research area in modern computational intelligence techniques and forms the basis for future generation automated systems. In recent decades, the unmanned vehicle systems have witnessed adverse growth expanding its application towards numerous safety-critical applications.  In UVS, the vehicles are controlled and managed in an automated manner without any direct human interventions across the board. The vehicles can either autonomously operates on its own through its sensing and directing competencies or otherwise controlled using remote control techniques. Some of the important applications of the UVS include Unmanned Ground Vehicles (UGV), Unmanned Underwater Vehicles (UUV), Unmanned Aerial Vehicles (UAV), Unmanned Surface Vehicles (USV) and unscrewed spacecraft’s. At present, most of the research works on UVS deals with the automation of critical applications where it is more vulnerable and problematic for a human operator to be diligent. This includes optimum communication between human-machine interfaces with persistent reliability under tough environmental circumstances. Further, automation and control of sensors, data processing, and telemetry units wanting human interventions with improved performance and reliability remain to be an open challenge for the researchers across various fields of computational intelligence.

Deep learning (DL) is a rapid technique with successful application across numerous research domains. The combination of DL and UVS can act as a state-of-the-art technique that would bring significant development in both public and life-critical applications. The advanced learning capabilities of DL algorithms assist in the effective management of complex real-time UVS datasets. This makes its application more appropriate for the development of autonomous robotic systems. As a result, over the past few decades, there is an increasing trend for deep learning-based robotic models for UVS; DL in the context of UVS helps in instance segmentation, semantic segmentation, object tracking, object detection, and recognition of safety-critical applications. Further, it also helps with planning and motion control activities. However, the present-day capability limitations of DL to deal with UVS are huge and require significant improvements. Some of the considerable drawbacks of DL in UVS include the requirement of greater computational resources, bandwidth, reliability, scalability, power consumption, availability, cost, coverage, data quality impacts on spatial and temporal alignments between different sensors and improved robustness for various data models. Further, most of the UVS applications work based on cloud systems which may lead to numerous cyber-attacks and network vulnerabilities. With the use of the two cutting-edge technologies DL and UVS, there exists emerging attention in utilizing DL to improve significant drawbacks of UVS.

This special issue entitled “Deep Learning for Unmanned Vehicle Systems” aims to bring together researchers from industries and academics to submit their novel ideas and concepts on DL based UVS. The topics of the special issue include but not limited to the following:

  • Object detection and computer vision for UVS
  • Trust, privacy and security in DL based UVS applications
  • Approaches using DL based UVS for future generation computational intelligence system
  • Deep neural networks (DNN) for robot automation in UVS
  • DL based UVS for agriculture, health, military, underwater explorations and several other critical applications
  • Planning and decision making in UVS using DL
  • Path tracking, control and navigation in UVS using DL algorithms
  • Novel design and architectures for UVS using DL
  • DL based UVS and its application in real-world
  • DL based algorithms and intelligent solutions for UVS
  • Integration of DL-UVS for smart cities and its advantages
  • Network and communication protocols for DL based UVS in smart cities

Looking to Publish your Research?

We aim to make publishing with Taylor & Francis a rewarding experience for all our authors. Please visit our Author Services website for more information and guidance, and do contact us if there is anything we can help with!

Submission Instructions

SPECIAL ISSUE ON “DEEP LEARNING FOR UNMANNED VEHICLE SYSTEMS”

We will send invitation to authors to attract high quality articles in our SI

Publication will be done according to journal policy

Instructions for AuthorsSubmit an Article