Deep Learning Based Neural Network Controller for Quad Copter: Application to Hovering Mode

Edhah, Saleh O.; Mohamed, Somayya; Rehan, Ahmed; Al-Dhaheri, M.; Alkhaja, Adham; Zweiri, Yahya

doi:10.1109/icecta48151.2019.8959776

Cited by 3 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the agent is never updated after training is completed. Bartak and Vykovsky [14] and Edhah et al [15] present representative examples of offline machine learning (ML) and deep learning (DL) algorithms, respectively. The studies of Xu et al [16], Rodriguez et al [17], and Yoo et al [18] are representative examples of offline RL algorithms.…”

Section: Definitionsmentioning

confidence: 99%

See 1 more Smart Citation

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: Definitionsmentioning

confidence: 99%

“…In Edhah et al [15], a DNN was used to control UAV altitude and hover. The standard feedforward, greedy layer-wise, and Long Short-Term Memory (LSTM) methods were evaluated and compared.…”

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

“…In this case, the control parameters are optimized using the PSO algorithm (PSO-APIDDFN). For clarity, Table 4 shows the new 33 (29)…”

Section: Quadrotor Control By the Pso-based Adaptive Pid Deep Feedfor...mentioning

confidence: 99%

“…Significantly, the DNN has enabled significant progress in sound and image processing applications, including feature detection, facial recognition, object identifications, computer vision, and text classification [26]- [28]. Besides, potential applications of DNN are numerous in control system engineering [29]. NN and similar approaches such as DNN and DFN can provide better results when used to online tune the PID controller parameters [13], [23]- [25] for controlling the quadrotor system.…”

Section: Introductionmentioning

confidence: 99%

Adaptive proportional integral derivative deep feedforward network for quadrotor trajectory-tracking flight control

Chater

Housny

Fadil

2022

IJECE

View full text Add to dashboard Cite

<span>When the controlled system is subject to parameter variations and external disturbances, a fixed-parameter proportional integral derivative (PID) controller cannot ensure its stabilization. In this case, its control requires online parameter adjustment. Specifically, as the quadrotor is a multi-input multi-output, nonlinear, and underactuated system, robust control is necessary to ensure efficient trajectory tracking flights. In this paper, an adaptive proportional integral derivative (APID) controller is proposed to control the quadrotor systems. This APID-based control strategy uses a two hidden layer deep feedforward network (DFN), where the one-step secant algorithm is chosen for initializing the DFN parameters. All the design steps of the proposed adaptive controller are described. The multidimensional particle swarm optimization (PSO) algorithm is used for tuning the DFN parameters. Then, using two simulation efficiency tests, a comparison between the proposed PSO-based APID-DFN, the (non-optimized) APID-DFN, the feedforward network APID, and the fixed-parameter PID controllers proves much efficiency of the proposed adaptive controller. The results illustrate that the proposed PSO-based APID-DFN controller can ensure good quadrotor system stabilization and achieve minimum overshoot and faster convergence speed for all quadrotor motions. Thus, the proposed control strategy could be considered an additional intelligent method-based adaptive control for unmanned aerial vehicles.</span>

show abstract

“…S. Bansal, et al used Neural Network in learning quadrotor dynamics for flight control [13]. S. Edhah et al used a new greedy Layer-wise approach in which they separated hidden layers to train separately [14]. After training, they merged all hidden layers as a single network.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Robot Control using Recurrent Neural Networks (LSTM; GRU) and Adaptive Sliding Mode Control

Patel¹,

Ƶeinali²,

Passi³

2021

International Conference of Control, Dynamic Systems, and Robotics

View full text Add to dashboard Cite

A phenomenal increase in computational power made deep learning possible for real-time applications in recent years. Nonlinearity, external disturbances, and robustness are significant challenges in robotics. To overcome these challenges, robust adaptive control is needed, which requires manipulator inverse dynamics. Deep Learning can be used to construct the inverse dynamic of a manipulator. In this paper, robust adaptive motion control is developed by effectively combining existing adaptive sliding mode controller (ASMC) with Recurrent Neural Network such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). A supervised learning approach is applied to train the LSTM and GRU model, which replaced the inverse dynamic model of a manipulator in model-based control design. The LSTM-based inverse dynamic model constructed using input-output data obtained from a simulation of a dynamic model of the two-links robot. The deep-learning-based controller applied for trajectory tracking control, and the results of the proposed Deep Learning-based controller are compared in three different scenarios: ASMC only, LSTM or GRU only, and LSTM or GRU with ASMC (with and without disturbance) scenario. The primary strategy of designing a controller with LSTM or GRU is to get better generalization, accuracy enhancement, compensate for fast time-varying parameters and disturbances. The experimental results depict that without tuning parameters proposed controller performs satisfactorily on unknown trajectories and disturbances.

show abstract

Deep Learning Based Neural Network Controller for Quad Copter: Application to Hovering Mode

Cited by 3 publications

References 8 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

Adaptive proportional integral derivative deep feedforward network for quadrotor trajectory-tracking flight control

Deep Learning-based Robot Control using Recurrent Neural Networks (LSTM; GRU) and Adaptive Sliding Mode Control

Contact Info

Product

Resources

About