Sökning: onr:"swepub:oai:DiVA.org:kth-346076" >
DANSE :
DANSE : Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Bayesian Setup
-
- Ghosh, Anubhab (författare)
- KTH,Teknisk informationsvetenskap
-
- Honore, Antoine (författare)
- KTH,Teknisk informationsvetenskap
-
- Chatterjee, Saikat (författare)
- KTH,Teknisk informationsvetenskap
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2023
- 2023
- Engelska.
-
Ingår i: Proceedings 31st European Signal Processing Conference, EUSIPCO 2023. - : Institute of Electrical and Electronics Engineers (IEEE). ; , s. 870-874
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.2...
-
visa färre...
Abstract
Ämnesord
Stäng
- We propose DANSE - a data-driven non-linear state estimation method. DANSE provides a closed-form posterior of the state of a model-free process, given linear measurements of the state in a Bayesian setup, like the celebrated Kalman filter (KF). Non-linear dynamics of the state are captured by data-driven recurrent neural networks (RNNs). The training of DANSE combines maximum-likelihood and gradient-descent in an unsupervised framework, i.e. only measurement data and no process data are required. Using simulated linear and non-linear process models, we demonstrate that DANSE - without knowledge of the process model - provides competitive performance against model-based approaches such as KF, unscented KF (UKF), extended KF (EKF), and a hybrid approach such as KalmanNet.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Nyckelord
- deep learning
- neural networks
- recurrent neural networks
- state estimation
- Bayesian networks
- Deep neural networks
- Gradient methods
- Maximum likelihood estimation
- Bayesian
- Closed form
- Data driven
- Linear state estimation
- Model free
- Neural-networks
- Nonlinear state
- Process-models
- State estimation methods
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)