Neuro-Optimal Control of Helicopter UAVs

Nodland, David and Ghosh, Arpita and Zargarzadeh, H and Jagannathan, S (2011) Neuro-Optimal Control of Helicopter UAVs. In: SPIE Defense, Security and Sensing, 25-29 April, 2011, Orlando, Florida, USA.

PDF - Published Version


Helicopter UAVs can be extensively used for military missions as well as in civil operations, ranging from multi- role combat support and search and rescue, to border surveillance and forest fire monitoring. Helicopter UAVs are underactuated nonlinear mechanical systems with correspondingly challenging controller designs. This paper presents an optimal controller design for the regulation and vertical tracking of an underactuated helicopter using an adaptive critic neural network framework. The online approximator-based controller learns the infinite- horizoncontinuous-time Hamilton-Jacobi-Bellman(HJB) equation and then calculates the corresponding optimal control input that minimizes the HJB equation forward-in-time. In the proposed technique, optimal regulation and vertical tracking is accomplished by a single neural network (NN) with a second NN necessary for the virtual controller. Both of the NNs are tuned online using novel weight update laws. Simulation results are included to demonstrate the effectiveness of the proposed control design in hovering applications. (Unmanned Systems Technology XIII, edited by Douglas W. Gage, Charles M. Shoemaker, Robert E. Karlsen, Grant R. Gerhart)

Item Type:Conference or Workshop Item (Paper)
Official URL/DOI:doi: 10.1117/12.883518
Uncontrolled Keywords:Nonlinear optimal control, helicopter UAV, neural network (NN), online approximator (OLA), HJB equation, hovering
Divisions:Material Science and Technology
ID Code:3595
Deposited On:23 Jul 2011 10:33
Last Modified:02 Jan 2012 14:08
Related URLs:

Repository Staff Only: item control page