Neural Network Based Model Reference Control
In the chapter, as an extension of Chap. 8, we further develop Neural Network (NN) based direct model reference control for the angular motion subsystem. The closed-loop angular motion subsystem is guaranteed to match the reference model in a prescribed finite time. As it is noted that the forward velocity can be indirectly affected by the reference of tilt angle, in this chapter we develop an NN based reference trajectory planner for tilt angle, which is called Adaptive Generator of Implicit Control Trajectory (AGICT), such that the forward velocity can be “controlled” to follow the desired velocity asymptotically.
KeywordsTilt Angle Radial Basis Function Neural Network Forward Velocity Neural Network Weight Finite Time Horizon
- 84.Lewis, F.L., Jagannathan, S., Yesildirek, A.: Neural Network Control of Robot Manipulators and Nonlinear Systems. Taylor & Francis, London (1999) Google Scholar
- 132.Yang, C., Ge, S.S., Xiang, C., Chai, T.Y., Lee, T.H.: Output feedback NN control for two classes of discrete-time systems with unknown control directions in a unified approach. IEEE Trans. Neural Netw. 19(11), 873–1886 (2008) Google Scholar