Pregled bibliografske jedinice broj: 121242
An Optimal Control Synthesis of Nonlinear Systems by Neural Network Backpropagation-Through-Time Algorithm
An Optimal Control Synthesis of Nonlinear Systems by Neural Network Backpropagation-Through-Time Algorithm // DAAAM International Scientific Book 2003 / Katalinić, Branko (ur.).
Beč: DAAAM International Vienna, 2003. str. 305-318
CROSBI ID: 121242 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
An Optimal Control Synthesis of Nonlinear Systems by Neural Network Backpropagation-Through-Time Algorithm
Autori
Kasać, Josip ; Novaković, Branko ; Majetić, Dubravko ; Brezak, Danko
Vrsta, podvrsta i kategorija rada
Poglavlja u knjigama, znanstveni
Knjiga
DAAAM International Scientific Book 2003
Urednik/ci
Katalinić, Branko
Izdavač
DAAAM International Vienna
Grad
Beč
Godina
2003
Raspon stranica
305-318
ISBN
3-901509-30-5
Ključne riječi
Optimal Control, Nonlinear Systems, Robot Control, Gradient Algorithm, Backpropagation-Through-Time Algorithm
Sažetak
This work presents a new numerical algorithm for the time optimal control of nonlinear multivariable systems with control and state vectors constraints. The algorithm is based on the backpropagation-through-time algorithm (BPTT), which is used as a learning algorithm for recurrent neural networks. Also, a heuristic algorithm for the time optimal control is presented. This algorithm is based on the characteristics of penalty functions for control and state vectors constraints. The proposed algorithms are especially suitable for treating complicate state vector constraints. Also, the proposed algorithms provide better convergence properties then numerical algorithms based on conversion of optimal control problem into a nonlinear programming one. The algorithms are applied on the problem of the time optimal robot control with the state vector constraints in the form of obstacle avoidance.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
