Intelligent Position Controller for Unmanned Aerial Vehicles (UAV) Based on Supervised Deep Learning

Cárdenas, Javier Alexis; Carrero, Uriel E.; Poveda, Edgar Camilo Camacho; Calderón, J.

doi:10.3390/machines11060606

Cited by 3 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cardenas et al [30] developed a DNN-based flight position controller using a supervised DL technique. A dataset that includes position, velocity, acceleration, and motor output signals for different trajectories was created by using a PID flight controller.…”

Section: Deep Learningmentioning

confidence: 99%

A Survey of Offline- and Online-Learning-Based Algorithms for Multirotor Uavs

Sönmez,

Rutherford,

Valavanis

2024

Drones

View full text Add to dashboard Cite

Multirotor UAVs are used for a wide spectrum of civilian and public domain applications. Their navigation controllers include onboard sensor suites that facilitate safe, autonomous or semi-autonomous multirotor flight, operation, and functionality under nominal and detrimental conditions and external disturbances, even when flying in uncertain and dynamically changing environments. During the last decade, given the available computational power, different learning-based algorithms have been derived, implemented, and tested to navigate and control, among other systems, multirotor UAVs. Learning algorithms have been and are used to derive data-driven based models, to identify parameters, to track objects, to develop navigation controllers, and to learn the environments in which multirotors operate. Learning algorithms combined with model-based control techniques have proven beneficial when applied to multirotors. This survey summarizes the research published since 2015, dividing algorithms, techniques, and methodologies into offline and online learning categories and then further classifying them into machine learning, deep learning, and reinforcement learning sub-categories. An integral part and focus of this survey is on online learning algorithms as applied to multirotors, with the aim to register the type of learning techniques that are either hard or almost hard real-time implementable, as well as to understand what information is learned, why, how, and how fast. The outcome of the survey offers a clear understanding of the recent state of the art and of the type and kind of learning-based algorithms that may be implemented, tested, and executed in real time.

show abstract

Section: Deep Learningmentioning

confidence: 99%

A Survey of Offline- and Online-Learning-Based Algorithms for Multirotor Uavs

Sönmez,

Rutherford,

Valavanis

2024

Drones

View full text Add to dashboard Cite

show abstract

“…As stated in our previous work [8], smart agriculture (precision agriculture) is an approach to farming that uses technology to improve efficiency and productivity. It involves the use of sensors, drones, and other devices to collect data on soil conditions, crop health, and weather patterns.…”

Section: Literature Reviewmentioning

confidence: 99%

Modeling of Unmanned Aerial Vehicles for Smart Agriculture Systems Using Hybrid Fuzzy PID Controllers

Amertet,

Gebresenbet,

Alwan

2024

Applied Sciences

View full text Add to dashboard Cite

Unmanned aerial vehicles have a wide range of uses in the military field, non-combat situations, and civil works. Due to their ease of operation, unmanned aerial vehicles (UAVs) are highly sought after by farmers and are considered the best agricultural technologies, since different types of controller algorithms are being integrated into drone systems, making drones the most affordable option for smart agriculture sectors. PID controllers are among the controllers frequently incorporated into drone systems. Although PID controllers are frequently used in drones, they have some limitations, such as sensitivity to noise and measurement errors, which can lead to instability or oscillations in the system. On the other hand, PID controllers provide improved accuracy in drone system responses. When using PID controllers to achieve the best performance in a drone system, it is better to share the advantages of PID controllers with other intelligence controllers. One promising option is the fuzzy PID controller. The aim of this study was to control quadcopter states (rolling, altitude, and airspeed) by leveraging quadcopter technology and adding hybrid fuzzy PID controls into the system. The quadcopter system and its controllers were mathematically modeled using the Simulink/MATLAB platform, and the system was controlled by fuzzy PID controllers. For validation purposes, the fuzzy PID controller was compared with a classically tuned PID controller. For roll, height, and airspeed, the fuzzy PID controller provided an improvement of 41.5%, 11%, and 44%, respectively, over the classically tuned PID controller. Therefore, the fuzzy PID controller best suits the needs of farmers and is compatible with smart agriculture systems.

show abstract

Implementation of partially tuned PD controllers of a multirotor UAV using deep deterministic policy gradient

Mosweu,

Seokolo,

Akano

et al. 2024

Journal of Electrical Systems and Inf Technol

View full text Add to dashboard Cite

The present methodology employed in classical control systems is characterized by high costs, significant processing requirements, and inflexibility. In conventional practice, when the controller exhibits instability after being implemented on the hardware, it is often adjusted to achieve stability. However, this approach is not suitable for mass-produced systems like drones, which possess diverse manufacturing tolerances and delicate stability thresholds. The aim of this study is to design and evaluate a controller for a multirotor unmanned aerial vehicle (UAV) system that is capable of adapting its gains in accordance with changes in the system dynamics. The controller utilized in this research employs a Simulink-constructed model that has been taught by reinforcement learning techniques, specifically employing a deep deterministic policy gradient (DDPG) network. The Simulink model of the UAV establishes the framework within which the agent engages in learning through interaction with its surroundings. The DDPG algorithm is an off-policy reinforcement learning technique that operates in continuous action spaces and does not require a model. The efficacy of the cascaded PD controllers and neural network tuner is evaluated. The results revealed that the controller exhibited stability during several flight phases, including take-off, hovering, path tracking, and landing manoeuvres.

show abstract

Intelligent Position Controller for Unmanned Aerial Vehicles (UAV) Based on Supervised Deep Learning

Cited by 3 publications

References 52 publications

A Survey of Offline- and Online-Learning-Based Algorithms for Multirotor Uavs

A Survey of Offline- and Online-Learning-Based Algorithms for Multirotor Uavs

Modeling of Unmanned Aerial Vehicles for Smart Agriculture Systems Using Hybrid Fuzzy PID Controllers

Implementation of partially tuned PD controllers of a multirotor UAV using deep deterministic policy gradient

Contact Info

Product

Resources

About