scholarly journals Neural PD Controller for an Unmanned Aerial Vehicle Trained with Extended Kalman Filter

Algorithms ◽  
2020 ◽  
Vol 13 (2) ◽  
pp. 40 ◽  
Author(s):  
Javier Gomez-Avila ◽  
Carlos Villaseñor ◽  
Jesus Hernandez-Barragan ◽  
Nancy Arana-Daniel ◽  
Alma Y. Alanis ◽  
...  
Keyword(s):  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Mobile Robotics ◽  
Pid Controllers ◽  
Pd Controller ◽  
The Neural Network ◽  
Control Scheme ◽  
Highly Nonlinear ◽  
Aerial Vehicle ◽  
Linear Controllers

Flying robots have gained great interest because of their numerous applications. For this reason, the control of Unmanned Aerial Vehicles (UAVs) is one of the most important challenges in mobile robotics. These kinds of robots are commonly controlled with Proportional-Integral-Derivative (PID) controllers; however, traditional linear controllers have limitations when controlling highly nonlinear and uncertain systems such as UAVs. In this paper, a control scheme for the pose of a quadrotor is presented. The scheme presented has the behavior of a PD controller and it is based on a Multilayer Perceptron trained with an Extended Kalman Filter. The Neural Network is trained online in order to ensure adaptation to changes in the presence of dynamics and uncertainties. The control scheme is tested in real time experiments in order to show its effectiveness.

scholarly journals Ultra-wideband based cooperative relative localization algorithm and experiments for multiple unmanned aerial vehicles in GPS denied environments

2017 ◽  
Vol 9 (3) ◽  
pp. 169-186 ◽  
Author(s):  
Kexin Guo ◽  
Zhirong Qiu ◽  
Wei Meng ◽  
Lihua Xie ◽  
Rodney Teo
Keyword(s):  
Kalman Filter ◽  
Unmanned Aerial Vehicles ◽  
Unmanned Aerial Vehicle ◽  
Extended Kalman Filter ◽  
Ultra Wideband ◽  
Cooperative Localization ◽  
Relative Localization ◽  
Aerial Vehicles ◽  
Aerial Vehicle ◽  
Displacement Measurements

This article puts forward an indirect cooperative relative localization method to estimate the position of unmanned aerial vehicles (UAVs) relative to their neighbors based solely on distance and self-displacement measurements in GPS denied environments. Our method consists of two stages. Initially, assuming no knowledge about its own and neighbors’ states and limited by the environment or task constraints, each unmanned aerial vehicle (UAV) solves an active 2D relative localization problem to obtain an estimate of its initial position relative to a static hovering quadcopter (a.k.a. beacon), which is subsequently refined by the extended Kalman filter to account for the noise in distance and displacement measurements. Starting with the refined initial relative localization guess, the second stage generalizes the extended Kalman filter strategy to the case where all unmanned aerial vehicles (UAV) move simultaneously. In this stage, each unmanned aerial vehicle (UAV) carries out cooperative localization through the inter-unmanned aerial vehicle distance given by ultra-wideband and exchanging the self-displacements of neighboring unmanned aerial vehicles (UAV). Extensive simulations and flight experiments are presented to corroborate the effectiveness of our proposed relative localization initialization strategy and algorithm.

scholarly journals Nonlinear Autoregressive Neural Network and Extended Kalman Filters for Prediction of Financial Time Series

2020 ◽  
Vol 2020 ◽  
pp. 1-6 ◽  
Author(s):  
Ghassane Benrhmach ◽  
Khalil Namir ◽  
Abdelwahed Namir ◽  
Jamal Bouyaghroumni
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Financial Time Series ◽  
Broad Class ◽  
Financial Time ◽  
The Neural Network ◽  
Nonlinear Autoregressive ◽  
Autoregressive Neural Network

Time series analysis and prediction are major scientific challenges that find their applications in fields as diverse as finance, biology, economics, meteorology, and so on. Obtaining the method with the least prediction error is one of the difficult problems of financial market and investment analysts. State space modelling is an efficient and flexible method for statistical inference of a broad class of time series and other data. The neural network is an important tool for analyzing time series especially when it is nonlinear and nonstationary. Essential tools for the study of Box-Jenkins methodology, neural networks, and extended Kalman filter were put together. We examine the use of the nonlinear autoregressive neural network method as a prediction technique for financial time series and the application of the extended Kalman filter algorithm to improve the accuracy of the model. As application on a real example, we are analyzing the time series of the daily price of steel over a 790-day period for establishing the superiority of this method over other existing methods. The simulation results using MATLAB and R software show that the model is capable of producing a reasonable accuracy.

Vision-based terrain referenced navigation of aerial vehicles using an adaptive extended Kalman filter

2017 ◽  
Vol 232 (8) ◽  
pp. 1584-1597 ◽  
Author(s):  
Sung-Hoon Mok ◽  
Youngjoo Kim ◽  
Hyochoong Bang
Keyword(s):  
Kalman Filter ◽  
Extended Kalman Filter ◽  
Least Squares Method ◽  
New Approach ◽  
Terrain Referenced Navigation ◽  
Digital Terrain ◽  
Highly Nonlinear ◽  
Noise Covariance ◽  
Adaptive Extended Kalman Filter ◽  
Filter Divergence

This paper addresses a vision-based terrain referenced navigation of an aircraft. A digital terrain map, in the surroundings of the aircraft, is compared with the camera measurements to estimate the aircraft position. Generally, the measurement equation in the terrain referenced navigation is highly nonlinear due to the sharp changes of terrain. Thus, the conventional extended Kalman filter could lead to unstable navigation solutions. In this paper, a new approach using an adaptive extended Kalman filter is proposed to cope up with the nonlinearity problem. A least squares method is utilized to derive the linearized measurement equations. The Jacobian matrix and sensor noise covariance are modified as a means of smoothing the sharp changes of terrain. Monte Carlo simulations verify that the proposed filter gives the stable navigation solutions, even when there is a large initial error, which is the primary reason for the filter divergence. Moreover, the proposed adaptation barely requires additional computational burden, whereas the high-order filters such as particle filter generally needs higher computational power.

Weighted Multiple Model Adaptive PID Control with Crossover Frequency Shift Tuning for a Hydraulic Turbine Plant

2013 ◽  
Vol 278-280 ◽  
pp. 1644-1647
Author(s):  
Chalang Hamarasheed ◽  
Sallehuddin Mohamed Haris ◽  
Zulkifli Mohd Nopiah
Keyword(s):  
Hydraulic Turbine ◽  
Pid Controllers ◽  
Multiple Model ◽  
Turbine Plant ◽  
Control Scheme ◽  
Highly Nonlinear ◽  
Multiple Model Adaptive Control ◽  
Phase Shifting Method ◽  
Hydraulic Turbines ◽  
Adaptive Pid Control

Hydraulic turbines are known to have complex and highly nonlinear dynamics with some varying parameters, especially in the presence of large or abrupt disturbances. In this study, the weighted multiple model adaptive control scheme was used as a controller for a hydraulic turbine model, with the aim of providing desirable characteristics such as robustness and stability. The system of comprised four candidate plant models with four corresponding candidate PID controllers which were tuned according to the phase shifting method. The plant operation, subjected to both abruptly changing and smoothly changing load conditions, was simulated. From the results, it was found that the proposed controller showed very good performance for both types of disturbance changes.

scholarly journals Camera-Based Tracking of Floating Objects using Fixed-wing UAVs

2021 ◽  
Vol 102 (4) ◽  
Author(s):  
Håkon Hagen Helgesen ◽  
Torleiv H. Bryne ◽  
Erik F. Wilthil ◽  
Tor Arne Johansen
Keyword(s):  
Kalman Filter ◽  
Target Tracking ◽  
Covariance Matrix ◽  
Extended Kalman Filter ◽  
Tracking System ◽  
Thermal Camera ◽  
Thermal Images ◽  
Aerial Vehicle ◽  
Floating Objects

AbstractThis article concerns tracking of floating objects using fixed-wing UAVs with a monocular thermal camera. Target tracking from an agile aerial vehicle is challenging because uncertainty in the UAV pose negatively affects the accuracy of the measurements obtained through thermal images. Consequently, the accuracy of the tracking estimates is degraded if navigation uncertainty is neglected. This is especially relevant for the estimated target covariance since inconsistency is a likely consequence. A tracking system based on the Schmidt-Kalman filter is proposed to mitigate navigation uncertainty. Images gathered with an uncertain UAV pose are weighted less than images captured with a reliable pose. The UAV pose is estimated independently in a multiplicative extended Kalman filter where the estimated covariance matrix is a measure of the uncertainty. The method is compared experimentally with two traditional alternatives based on the extended Kalman filter. The results show that the proposed method performs better with respect to consistency and accuracy.

scholarly journals Anti-Disturbance Compensator Design for Unmanned Aerial Vehicle

2019 ◽  
Vol 26 (1) ◽  
pp. 86-103 ◽  
Author(s):  
Ibraheem Kasim Ibraheem
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Disturbance Rejection ◽  
Pid Controllers ◽  
Hurwitz Stability ◽  
Output Performance ◽  
Disturbance Rejection Control ◽  
Compensator Design ◽  
Control Scheme ◽  
Aerial Vehicle ◽  
Quadrotor System

In this paper, an Anti-Disturbance Compensator is suggested for the stabilization of a 6-DoF quadrotor Unmanned Aerial vehicle (UAV) system, namely, the Improved Active Disturbance Rejection Control (IADRC). The proposed Control Scheme rejects the disturbances subjected to this system and eliminates the effect of the uncertainties that the quadrotor system exhibits. The complete nonlinear mathematical model of the 6-DoF quadrotor UAV system has been used to design the four ADRCs units for the attitude and altitude stabilization. Stability analysis has been demonstrated for the Linear Extended State Observer (LESO) of each IADRC unit and the overall closed-loop system using Hurwitz stability criterion. A minimization to a proposed multi-objective Output Performance Index (OPI) is achieved in the MATLAB environment to tune the IADRCs parameters using Genetic Algorithm (GA). The IADRC has been tested for the 6-DOF quadrotor under different tracking scenarios, including disturbance rejection and uncertainties elimination and compared with nonlinear and linear PID controllers. The simulations showed the excellent performance of the proposed compensator against the controllers used in the comparison.

Sign in / Sign up

Export Citation Format

Share Document