Research on Route Tracking Controller of Quadrotor UAV Based on Fuzzy Logic and RBF Neural Network

Jia, Kejin; Lin, Siqi; Du, Yun; Zou, Chao; Lu, Mengyanglin

doi:10.1109/access.2023.3322944

Cited by 3 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A common characteristic of online learning techniques is that all methods are modelfree, except for the proposed approach in [93].…”

Section: Discussionmentioning

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

“…A common characteristic of online learning techniques is that all methods are modelfree, except for the proposed approach in [93].…”

Section: Discussionmentioning

confidence: 99%

“…Jia et al [93] provided a solution to the trajectory tracking problem by combining a fuzzy logic method, a radial basis function (RBF) NN, and a classical PID controller. The PID output and the current UAV position information are provided to the RBF NN as input values, and the network learns to adjust controller parameters.…”

Section: Online 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

“…These epochs relate to the number of times the data are processed through the algorithm to adjust the weight parameters and improve the performance and convergence to a network solution. On the other hand are the algorithms that perform their training and identification online while the system to be studied is evolving [15,16]. Therefore, the weight parameter estimation is adjusted online due to training processes, such as the filtered error algorithm [17] and the Extended Kalman Filter (EKF) [18].…”

Section: Introductionmentioning

confidence: 99%

A Recurrent Neural Network for Identifying Multiple Chaotic Systems

Echenausía-Monroy,

Pena Ramirez,

Álvarez

et al. 2024

Mathematics

View full text Add to dashboard Cite

This paper presents a First-Order Recurrent Neural Network activated by a wavelet function, in particular a Morlet wavelet, with a fixed set of parameters and capable of identifying multiple chaotic systems. By maintaining a fixed structure for the neural network and using the same activation function, the network can successfully identify the three state variables of several different chaotic systems, including the Chua, PWL-Rössler, Anishchenko–Astakhov, Álvarez-Curiel, Aizawa, and Rucklidge models. The performance of this approach was validated by numerical simulations in which the accuracy of the state estimation was evaluated using the Mean Square Error (MSE) and the coefficient of determination (r2), which indicates how well the neural network identifies the behavior of the individual oscillators. In contrast to the methods found in the literature, where a neural network is optimized to identify a single system and its application to another model requires recalibration of the neural algorithm parameters, the proposed model uses a fixed set of parameters to efficiently identify seven chaotic systems. These results build on previously published work by the authors and advance the development of robust and generic neural network structures for the identification of multiple chaotic oscillators.

show abstract

Nonlinear model predictive control of vehicle trajectory tracking using tilting technology

Yao,

Bai,

Jia

2024

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

To enhance the performance of trajectory tracking in high-speed autonomous vehicles, this paper adopts a new technology for controlling the vehicle body to tilt toward the inside of a curve, known as “tilting technology.” It achieves this tilt through an active suspension system that inclines the vehicle body toward the inside of the curve, thereby reducing or offsetting the torque generated by gravity with the torque produced by centrifugal force. This significantly improves the vehicle’s handling stability and anti-rollover capability. Integrating this technology with active steering control, a nonlinear model predictive trajectory tracking controller has been designed. For this integrated controller, the Fiala lateral tire force model is used to establish a nonlinear vehicle model with steering-rolling dynamics, while a double-lane-change and single-lane-change tests are designed as the reference paths. To avoid the tilting angle of the vehicle body being too large to exceed the effective stroke of the suspension, a clipped ideal tilt angle is adopted as the desired tilting angle. Simulation verification is carried out to confirm the validity of the integrated trajectory tracking control. The proposed controller is compared with two other trajectory tracking controllers, the controller that takes zero rolling angle as the control target and the controller without rolling control. The results show that, compared with the latter two, the proposed trajectory tracking controller can ensure well tracking ability, meanwhile effectively improving the handling stability, anti-rollover capability, and occupant lateral ride comfort during trajectory tracking for high-speed unmanned vehicles.

show abstract

Research on Route Tracking Controller of Quadrotor UAV Based on Fuzzy Logic and RBF Neural Network

Cited by 3 publications

References 32 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

A Recurrent Neural Network for Identifying Multiple Chaotic Systems

Nonlinear model predictive control of vehicle trajectory tracking using tilting technology

Contact Info

Product

Resources

About