UAV Modular Control Architecture

Asmaa, Idalene; Boukhdir, Khalid; Medromi, Hicham

doi:10.1007/978-981-15-6048-4_28

Cited by 2 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In decentralized architectures, we can further distinguish hierarchical organizations from fully distributed ones. Next, we will describe this taxonomy of architectures [7][8][9], which are schematically depicted in Figure 2. In centralized control structures (depicted in Figure 2a), a single platform directly manages the whole swarm, meaning that it performs any calculations needed to execute control tasks.…”

Section: Swarm Management Organizationmentioning

confidence: 99%

Application of Deep Reinforcement Learning to UAV Swarming for Ground Surveillance

Arranz,

Carramiñana,

Miguel

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper summarizes in depth the state of the art of aerial swarms, covering both classical and new reinforcement-learning-based approaches for their management. Then, it proposes a hybrid AI system, integrating deep reinforcement learning in a multi-agent centralized swarm architecture. The proposed system is tailored to perform surveillance of a specific area, searching and tracking ground targets, for security and law enforcement applications. The swarm is governed by a central swarm controller responsible for distributing different search and tracking tasks among the cooperating UAVs. Each UAV agent is then controlled by a collection of cooperative sub-agents, whose behaviors have been trained using different deep reinforcement learning models, tailored for the different task types proposed by the swarm controller. More specifically, proximal policy optimization (PPO) algorithms were used to train the agents’ behavior. In addition, several metrics to assess the performance of the swarm in this application were defined. The results obtained through simulation show that our system searches the operation area effectively, acquires the targets in a reasonable time, and is capable of tracking them continuously and consistently.

show abstract

Section: Swarm Management Organizationmentioning

confidence: 99%

Application of Deep Reinforcement Learning to UAV Swarming for Ground Surveillance

Arranz,

Carramiñana,

Miguel

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, there has been a surge in research efforts in the field of UAVs, with various areas of study being explored. Antennas [2,3], aircraft detection [4,5], control [6], and trajectories [7] have emerged as the most prominent research directions [8]. Moreover, research on human-UAV interaction [9], swarm behavior [10], environmental sensing [11], safety and reliability [12], and application-specific development [13] has also garnered significant attention [14].…”

Section: Introductionmentioning

confidence: 99%

Design and Optimization of UAV Aerial Recovery System Based on Cable-Driven Parallel Robot

Wu,

Sun,

Yue

et al. 2024

Biomimetics

View full text Add to dashboard Cite

Aerial recovery and redeployment can effectively increase the operating radius and the endurance of unmanned aerial vehicles (UAVs). However, the challenge lies in the effect of the aerodynamic force on the recovery system, and the existing road-based and sea-based UAV recovery methods are no longer applicable. Inspired by the predatory behavior of net-casting spiders, this study introduces a cable-driven parallel robot (CDPR) for UAV aerial recovery, which utilizes an end-effector camera to detect the UAV’s flight trajectory, and the CDPR dynamically adjusts its spatial position to intercept and recover the UAV. This paper establishes a comprehensive cable model, simultaneously considering the elasticity, mass, and aerodynamic force, and the static equilibrium equation for the CDPR is derived. The effects of the aerodynamic force and cable tension on the spatial configuration of the cable are analyzed. Numerical computations yield the CDPR’s end-effector position error and cable-driven power consumption at discrete spatial points, and the results show that the position error decreases but the power consumption increases with the increase in the cable tension lower limit (CTLL). To improve the comprehensive performance of the recovery system, a multi-objective optimization method is proposed, considering the error distribution, power consumption distribution, and safety distance. The optimized CTLL and interception space position coordinates are determined through simulation, and comparative analysis with the initial condition indicates an 83% reduction in error, a 62.3% decrease in power consumption, and a 1.2 m increase in safety distance. This paper proposes a new design for a UAV aerial recovery system, and the analysis lays the groundwork for future research.

show abstract

UAV Modular Control Architecture

Cited by 2 publications

References 14 publications

Application of Deep Reinforcement Learning to UAV Swarming for Ground Surveillance

Application of Deep Reinforcement Learning to UAV Swarming for Ground Surveillance

Design and Optimization of UAV Aerial Recovery System Based on Cable-Driven Parallel Robot

Contact Info

Product

Resources

About