Zobrazeno 1 - 10
of 153
pro vyhledávání: '"Mircea-Bogdan Radac"'
Autor:
Mircea-Bogdan Radac, Timotei Lala
Publikováno v:
IEEE Access, Vol 8, Pp 214153-214165 (2020)
An optimal robust control solution for general nonlinear systems with unknown but observable dynamics is advanced here. The underlying Hamilton-Jacobi-Isaacs (HJI) equation of the corresponding zero-sum two-player game (ZS-TP-G) is learned using a Q-
Externí odkaz:
https://doaj.org/article/617dd7df8c9c4b3e92b4adfc4c90394a
Autor:
Mircea-Bogdan Radac
Publikováno v:
Entropy, Vol 24, Iss 7, p 889 (2022)
A hierarchical learning control framework (HLF) has been validated on two affordable control laboratories: an active temperature control system (ATCS) and an electrical rheostatic braking system (EBS). The proposed HLF is data-driven and model-free,
Externí odkaz:
https://doaj.org/article/b90015879745499d9f3d4ae756e37c71
Publikováno v:
Energies, Vol 15, Iss 1, p 267 (2021)
This paper focuses on validating a model-free Value Iteration Reinforcement Learning (MFVI-RL) control solution on a visual servo tracking system in a comprehensive manner starting from theoretical convergence analysis to detailed hardware and softwa
Externí odkaz:
https://doaj.org/article/9b988b41acbd4a3b979fdb0ef0efbbd4
Autor:
Mircea-Bogdan Radac, Timotei Lala
Publikováno v:
Mathematics, Vol 9, Iss 21, p 2752 (2021)
A general control system tracking learning framework is proposed, by which an optimal learned tracking behavior called ‘primitive’ is extrapolated to new unseen trajectories without requiring relearning. This is considered intelligent behavior an
Externí odkaz:
https://doaj.org/article/27eae8132fa040ff8b0ebeacc15e0503
Autor:
Radu-Emil Precup, Stefan Preitl, Claudia-Adina Bojan-Dragos, Mircea-Bogdan Radac, Alexandra-Iulia Szedlak-Stinean, Elena-Lorena Hedrea, Raul-Cristian Roman
Publikováno v:
Facta Universitatis. Series: Mechanical Engineering, Vol 15, Iss 2, Pp 231-244 (2017)
This paper presents theoretical and application results concerning the development of evolving Takagi-Sugeno-Kang fuzzy models for two dynamic systems, which will be viewed as controlled processes, in the field of automotive applications. The two dyn
Externí odkaz:
https://doaj.org/article/fc8fa057d1a946cd87e0a6060f92b9a5
Publikováno v:
Energies, Vol 14, Iss 4, p 1006 (2021)
In this paper, a novel Virtual State-feedback Reference Feedback Tuning (VSFRT) and Approximate Iterative Value Iteration Reinforcement Learning (AI-VIRL) are applied for learning linear reference model output (LRMO) tracking control of observable sy
Externí odkaz:
https://doaj.org/article/ee8b3a11f0b8430ba552855bc3fed662
Publikováno v:
Algorithms, Vol 14, Iss 1, p 2 (2020)
This paper presents the performance of two sliding mode control algorithms, based on the Lyapunov-based sliding mode controller (LSMC) and reaching-law-based sliding mode controller (RSMC), with their novel variants designed and applied to the anti-l
Externí odkaz:
https://doaj.org/article/8fd30f82eb1f4af6907b85ca1088e020
Autor:
Mircea-Bogdan Radac, Timotei Lala
Publikováno v:
Algorithms, Vol 12, Iss 10, p 212 (2019)
The authors would like to mention that their paper is an extended version of the IEEE conference paper [...]
Externí odkaz:
https://doaj.org/article/ee01bbbedb7443cdbe57126cf3e0d373
Autor:
Mircea-Bogdan Radac, Timotei Lala
Publikováno v:
Algorithms, Vol 12, Iss 6, p 121 (2019)
Linearly and nonlinearly parameterized approximate dynamic programming approaches used for output reference model (ORM) tracking control are proposed. The ORM tracking problem is of significant interest in practice since, with a linear ORM, the close
Externí odkaz:
https://doaj.org/article/6f0e362de51241db911a2fe5c36f4bf7
Data-Driven Model-Free Tracking Reinforcement Learning Control with VRFT-based Adaptive Actor-Critic
Autor:
Mircea-Bogdan Radac, Radu-Emil Precup
Publikováno v:
Applied Sciences, Vol 9, Iss 9, p 1807 (2019)
This paper proposes a neural network (NN)-based control scheme in an Adaptive Actor-Critic (AAC) learning framework designed for output reference model tracking, as a representative deep-learning application. The control learning scheme is model-free
Externí odkaz:
https://doaj.org/article/f197138e8c184d399d1d0e4a0b4c3b97