| Autor: |
Hong Quang Nguyen, Anh Duc Hoang, Phuong Nam Dao, Tien Hoang Nguyen |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Research in Intelligent and Computing in Engineering ISBN: 9789811575266 |
| DOI: |
10.1007/978-981-15-7527-3_51 |
| Popis: |
This paper presents output feedback based online adaptive reinforcement learning control for a wheeled inverted pendulum (WIP) system based on the linearized system model, which belongs to a class of continuous time systems under the influence of external disturbance and/or dynamic uncertainties. Both the Policy Iteration (PI) and Value Iteration (VI) techniques are considered in the proposed algorithm based on the equivalent discrete time system and application of Kronecker product for the data collections. Finally, it is shown that the theoretical analysis and simulation results demonstrate the effectiveness of the proposed control structure. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
