Hybrid Model-Based and Data-Driven Wind Velocity Estimator for the Navigation System of a Robotic Airship

07/14/2019
by   Apolo Silva Marton, et al.
0

In the context of autonomous airships, several works in control and guidance use wind velocity to design a control law. However, in general, this information is not directly measured in robotic airships. This paper presents three alternative versions for estimation of wind velocity. Firstly, an Extended Kalman Filter is designed as a model-based approach. Then a Neural Network is designed as a data-driven approach. Finally, a hybrid estimator is proposed by performing a fusion between the previous designed estimators: model-based and data-driven. All approaches consider only GPS, IMU and Pitot tube as available sensors. Simulations in a realistic nonlinear model of the airship suggest that the cooperation between these two techniques increases the estimation performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/06/2022

Data-Driven Meets Navigation: Concepts, Models, and Experimental Validation

The purpose of navigation is to determine the position, velocity, and or...
research
05/03/2019

A New Hybrid Control Architecture to Attenuate Large Horizontal Wind Disturbance for a Small-Scale Unmanned Helicopter

This paper presents a novel method to attenuate large horizontal wind di...
research
09/13/2023

Stepwise Model Reconstruction of Robotic Manipulator Based on Data-Driven Method

Research on dynamics of robotic manipulators provides promising support ...
research
03/04/2020

Touch the Wind: Simultaneous Airflow, Drag and Interaction Sensing on a Multirotor

Disturbance estimation for Micro Aerial Vehicles (MAVs) is crucial for r...
research
11/29/2018

Design and Control of A Hybrid Sailboat for Enhanced Tacking Maneuver

Sailing robots provide a low-cost solution to conduct the ocean missions...
research
05/30/2022

Development of a hybrid model-based data-driven collision avoidance algorithm for vehicles in low adhesion conditions

Winter conditions, characterized by the presence of ice and snow on the ...
research
10/18/2021

Unsupervised Learned Kalman Filtering

In this paper we adapt KalmanNet, which is a recently pro-posed deep neu...

Please sign up or login with your details

Forgot password? Click here to reset