2007
DOI: 10.1109/ijcnn.2007.4370992
|View full text |Cite
|
Sign up to set email alerts
|

Comparison of Real-time Online and Offline Neural Network Models for a UAV

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2007
2007
2022
2022

Publication Types

Select...
6
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 19 publications
(5 citation statements)
references
References 6 publications
0
5
0
Order By: Relevance
“…The system matrices A t , B t , Cand G t in model (13) are calculated by (14)(15)(16)(17)(18) for which knowledge of the working-point state predictionˆ( )( , , , ) w t jt j N + = − | 1 2 1 is required. It is possible to obtain knowledge about some processes being controlled.…”
Section: Multistep-ahead Predictive Model For Mpcmentioning
confidence: 99%
See 1 more Smart Citation
“…The system matrices A t , B t , Cand G t in model (13) are calculated by (14)(15)(16)(17)(18) for which knowledge of the working-point state predictionˆ( )( , , , ) w t jt j N + = − | 1 2 1 is required. It is possible to obtain knowledge about some processes being controlled.…”
Section: Multistep-ahead Predictive Model For Mpcmentioning
confidence: 99%
“…To overcome the disadvantages and restrictions of the physical modeling, some intelligent and advanced methods have been explored for modeling and controlling quad‐rotor vehicles. Puttige and Anavatti presented a comparison of real‐time online and offline NN models for a quad‐rotor UAV, the approximation property of NN is applied to learn the dynamics of the quad‐rotor UAV. In , the nonlinear dynamics of the quad‐rotor are described by a multiple input multiple output (MIMO) radial basis function (RBF)–autoregressive with exogenous variables (ARX) model, and a state feedback control law with a linear quadratic regulator (LQR) approach is proposed.…”
Section: Introductionmentioning
confidence: 99%
“…Hence, it may not perform as expected in different flight conditions. Due to the constraints on the training (particularly in terms of the available training time) in the online model it may not provide the desired accuracy under all flight conditions [21]. As a solution to this issue the offline and the online models are combined in the form of a multi-network architecture and individual outputs are compared with respect to a particular criterion and dynamically selected.…”
Section: Multi-network Architecturementioning
confidence: 99%
“…Hence, it may not perform as expected in different flight conditions. Due to the constraints on the training (particularly in terms of the available training time) in the online model it may not provide the desired accuracy under all flight conditions [16]. As a solution to this issue the offline and the online models are compared with respect to a particular criterion and dynamically selected.…”
Section: Multi-network Architecturementioning
confidence: 99%