Joshi, G and Padhi, R (2017) Robust control of quadrotors using neuro-adaptive control augmented with state estimation. In: AIAA Guidance, Navigation, and Control Conference, 9 - 13 January 2017, Grapevine, Texas.
![]() |
PDF
AIAA_GUI_NAV_CON_CON_18P_2017.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy |
Abstract
A new Sobolev norm based neuro-adaptive control approach is presented in this paper which leads to fast learning of the disturbance function in the system dynamics with lesser transients. The new weight update rule improves the learning characteristics of the neural network under noisy environment by augmenting with state estimation to make learning process operational under noisy condition. The proposed approach is successfully applied to the challenging problem of controlling quadrotors with significant uncertainty in system model involving system inertia, blade apping phenomenon and actuator misalignment. The trajectory tracking performance and attitude hold of quadrotor in presence of un- modeled uncertainty and measurement sensor noise is found to be superior compared to baseline controller.
Item Type: | Conference Paper |
---|---|
Publication: | AIAA Guidance, Navigation, and Control Conference, 2017 |
Publisher: | American Institute of Aeronautics and Astronautics Inc, AIAA |
Additional Information: | cited By 3; Conference of AIAA Guidance, Navigation, and Control Conference, 2017 ; Conference Date: 9 January 2017 Through 13 January 2017; Conference Code:190189 |
Keywords: | Learning systems; Reusable rockets; Robust control; State estimation; Uncertainty analysis, Disturbance functions; Learning process; Measurement sensor; Neuro-adaptive control; Noisy conditions; Noisy environment; System modeling; Trajectory tracking, Adaptive control systems |
Department/Centre: | Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering) |
Date Deposited: | 25 Sep 2020 07:26 |
Last Modified: | 25 Sep 2020 07:26 |
URI: | http://eprints.iisc.ac.in/id/eprint/65684 |
Actions (login required)
![]() |
View Item |