2026-09-19T13:32:11Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1472472023-01-20T03:34:41Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Annaswamy, Anuradha
Guha, Anubhav
Massachusetts Institute of Technology. Department of Mechanical Engineering
2023-01-19T18:40:07Z
2023-01-19T18:40:07Z
2022-09
2022-10-05T13:45:57.716Z
https://hdl.handle.net/1721.1/147247
This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties. A combination of Adaptive Control (AC) in the inner loop and a Reinforcement Learning (RL) based policy in the outer loop is proposed such that in real-time the inner-loop model reference adaptive controller contracts the closed-loop dynamics towards a reference system, while the RL in the outerloop directs the overall system towards approximately optimal performance. This AC-RL approach is developed for a class of control affine nonlinear dynamical systems, and employs extensions to systems with multiple equilibrium points, systems with input magnitude constraints, and systems in which a high-order tuner is required for adequate performance. In addition to establishing a stability guarantee with realtime control, the AC-RL controller is also shown to lead to parameter learning with persistent excitation. Numerical validations of all algorithms are carried out using a quadrotor landing task on a moving platform. These results point out the clear advantage of the proposed integrative AC-RL approach.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
AC-RL: A Framework for Real-Time Control, Learning & Adaptation
Thesis
application/pdf
Master
Master of Science in Mechanical Engineering
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="7b266825-7703-4a9c-a6ce-354edd90ae94">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>AC-RL: A Framework for Real-Time Control, Learning & Adaptation</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-09</PublicationDate>
<Authors>
<Author>
<DisplayName>Guha, Anubhav</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>This paper considers the problem of real-time control and learning in dynamic systems subjected to parametric uncertainties. A combination of Adaptive Control (AC) in the inner loop and a Reinforcement Learning (RL) based policy in the outer loop is proposed such that in real-time the inner-loop model reference adaptive controller contracts the closed-loop dynamics towards a reference system, while the RL in the outerloop directs the overall system towards approximately optimal performance. This AC-RL approach is developed for a class of control affine nonlinear dynamical systems, and employs extensions to systems with multiple equilibrium points, systems with input magnitude constraints, and systems in which a high-order tuner is required for adequate performance. In addition to establishing a stability guarantee with realtime control, the AC-RL controller is also shown to lead to parameter learning with persistent excitation. Numerical validations of all algorithms are carried out using a quadrotor landing task on a moving platform. These results point out the clear advantage of the proposed integrative AC-RL approach.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>