Distributed Theory in Applications of Autonomous Vehicles

Deadline for manuscript submissions: 15 January 2024.

Guest Editor (1)

Zongyu  Zuo
Prof. Zongyu Zuo 
The Seventh Research Division, Beihang University, Beijing 100191, China
Interests: Control of UAVs; Cooperative Control of Multiagent Systems; Nonlinear Control Theory and Applications; Finite-/Fixed-time Stability/Stabilization

Co-Guest Editors (2)

Zhongguo  Li
Dr. Zhongguo Li 
Department of Computer Science, University College London, London, UK
Interests: Distributed Control; Robotic Path Planning; Multi-Agent Systems; Distributed Learning; Autonomous Systems
Yao  Zou
Prof. Yao Zou 
University of Intelligence Science and Technology, Beijing 100084, China
Interests: Multi-agent Systems; Distributed Control; Aircraft Control

Special Issue Information

In recent years, multi-vehicle systems have been extensively investigated and applied.  Distributed theory plays a principal role in coordinating large-scale multi-vehicle systems, which has been featured in cooperative sensing, control, planning, guidance, and other swarm mechanisms. How to coordinate numerous autonomous vehicles to exhibit certain complicated swarm behaviors depends on exquisite distributed theory in sensing, control, planning, and guidance. Besides, distributed techniques require information interaction of neighboring vehicle via network communications. This means that outstanding swarm behaviors depend on perfect interactive protocols. Moreover, a majority of autonomous vehicles, such as UAVs, USVs, and UGVs, are characterized by nonlinear, non-holonomic, and under-actuated attributes. This imposes additional difficulty in their coordination subject to the complexity of internal models. Moreover, autonomous vehicles frequently operate in strange unstructured circumstances. Confronted with environmental disturbances, it becomes difficult to maintain benign cooperative performance. This motivates the introduction of feasible anti-disturbance mechanisms into distributed techniques. 

In this Topic Collection, we invite you to contribute original research articles, brief reports, systematic reviews, systemic and shorter perspectives, opinions, and expert perspectives on all aspects related to the theme of “distributed theory and applications to autonomous vehicles”. Relevant topics include but are not limited to:
  • Distributed control of autonomous vehicles
  • Distributed path/trajectory planning of autonomous vehicles
  • Distributed guidance of autonomous vehicles
  • Formation control of UAVs/UGVs/USVs
  • Methodologies for distributed theory 
  • Distributed sensing
  • Resilient distributed control
  • Robust/Adaptive distributed control 
  • Distributed filter
  • Distributed optimization
  • Collective intelligence
  • Self-organization
  • Multi-vehicle systems
  • Multi-vehicle applications


 

Published Papers (2 Papers)

Open Access

Communication

26 June 2025

Production and Calibration of a Lambertian Surface Based on Barium Sulfate (BaSO4) for the Calibration of Multispectral Cameras

Drones, or unmanned aerial vehicles (UAVs), are increasingly utilized across diverse fields such as agriculture, environmental analysis, and engineering due to their ability to capture high-quality multispectral imagery. To ensure the accuracy of these images, radiometric calibration of onboard multispectral cameras is essential. This study aimed to develop and calibrate a low-cost Lambertian surface using barium sulfate (BaSO4) for radiometric calibration of UAV-mounted multispectral cameras. A stainless steel mold was designed to compact BaSO4, and the resulting surface was calibrated using an ASD FieldSpec HandHeld UV/NIR spectroradiometer and a Spectralon plate as the reference standard. Results showed a strong correlation (Pearson’s r = 0.9988) between the BaSO4 surface and the Spectralon plate, confirming that the BaSO4-based surface is a cost-effective alternative for producing diffuse Lambertian surfaces with performance comparable to the standard.

Daniel  CarvalhoGranemann
Adão Robson Elias*
Henrique dos SantosFelipetto
Fernanda SayuriYoshino Watanabe
Edson LuisPiroli
Drones Veh. Auton.
2025,
2
(3), 10012; 
Open Access

Article

30 October 2025

Smart Drone Neutralization: AI Driven RF Jamming and Modulation Detection with Software Defined Radio

The increasing use of wireless technologies in many aspects of people’s lives has led to a congested electromagnetic spectrum, making it critical to manage the limited available spectrum as efficiently as possible. This is particularly important for military activities such as electronic warfare, where jamming is used to disrupt enemy communication, self-attacking drones, and surveillance drones. However, current detection methods used by armed personnel, such as optical sensors and Radio Detection and Ranging (RADAR), do not include Radio Frequency (RF) analysis, which is crucial for identifying the signals used to operate drones. To combat security vulnerabilities posed by the rogue or unidentified transmitters, RF transmitters should be detected not only by the available data content of broadcasts but also by the physical properties of the transmitters. This requires faster fingerprinting and identifying procedures that extend beyond the traditional hand-engineered methods. In this paper, RF data from the drones’ remote controller is identified and collected using Software Defined Radio (SDR), a radio that employs software to perform signal-processing tasks that were previously accomplished by hardware. A deep learning model is then provided to train and detect modulation strategies utilized in drone communication and a suitable jamming strategy. This paper overviews Unmanned Aerial Vehicles (UAV) neutralization, communication signals, and Deep Learning (DL) applications. It introduces an intelligent system for modulation detection and drone jamming using Software Defined Radio (SDR). DL approaches in these areas, alongside advancements in UAV neutralization techniques, present promising research opportunities. The primary objective is to integrate recent research themes in UAV neutralization, communication signals, and Machine Learning (ML) and DL applications, delivering a more efficient and effective solution for identifying and neutralizing drones. The proposed intelligent system for modulation detection and jamming of drones based on SDR, along with deep learning approaches, holds great potential for future research in this field.

Savindu Nanayakkara*
Sagara  Sumathipala
Nalan  Karunanayake
Mihiraj  Karunanayake
Thilina  Kumara
Drones Veh. Auton.
2025,
2
(4), 10019; 
TOP