2026-09-19T08:59:18Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/108017 2023-07-11 col_2142_5131 col_2142_14787 com_2142_5130 com_2142_9630 com_2142_234

Safety Critical Systems Disturbance rejection Flight evaluation of deep model reference adaptive control text Thesis Chowdhary, Girish Virdi, Jasvir 2020-08-26T21:57:58Z 2020-08-26T21:57:58Z 2020-05-12 2020-05 This thesis presents flight test results for a new neuroadaptive architecture: Deep Neural Network based Model Reference Adaptive Control (DMRAC). This architecture utilizes the power of deep neural network representations for modeling significant nonlinearities while marrying it with the boundedness guarantees that characterize MRAC based controllers. Through experiments on a real quadcopter platform, it is shown that DMRAC can outperform state of the art controllers in different flight regimes while having long-term learning abilities. This makes DMRAC a highly powerful architecture for high-performance control of nonlinear systems. Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms The student, Jasvir Virdi, accepted the attached license on 2020-05-08 at 12:41. The student, Jasvir Virdi, submitted this Thesis for approval on 2020-05-08 at 12:48. This Thesis was approved for publication on 2020-05-12 at 11:55. DSpace SAF Submission Ingestion Package generated from Vireo submission #15292 on 2020-08-25 at 17:13:28 Made available in DSpace on 2020-08-26T21:57:58Z (GMT). No. of bitstreams: 2 VIRDI-THESIS-2020.pdf: 4898928 bytes, checksum: 38d3ee747039b2a0e7b71c749e592b0c (MD5) LICENSE.txt: 4209 bytes, checksum: 9a3ca6ab0f0e2d77c1d8b502ac3283bd (MD5) Previous issue date: 2020-05-12 application/pdf http://hdl.handle.net/2142/108017 en Copyright 2020 Jasvir Virdi Adaptive Control Machine Learning Mechanical Sci & Engineering Mechanical Engineering University of Illinois at Urbana-Champaign Thesis M.S.