Back to search

Georgia Institute of Technology

Secure, Intermittent, and Model-Free Learning Framework for Autonomous Cyber Physical Systems

Abstract

dc:description.abstract

Cyber-physical systems (CPS) integrate humans and computational systems to control physical plants using sensing signals and feedback loops. The interconnection, modularity, and exposure to human environments, reveal CPS to attacks from adversaries. In an adversarial, information-constrained, and model-agnostic environment, reinforcement learning (RL) methods design optimal control policies using reward signals that possess decentralized learning and deployment protocols. Increased continuous data-sharing between sensors, actuators, and the cloud adds complexities to the network leading to degradation of communication effectiveness and increased the possibility of reinforcement signal dropouts, leaving the learning framework with access to a sparse set of rewards or even state measurements. This work presents a Moving Target Defense (MTD) framework, to switch between allowable actuator combinations. MTD allows the input-generation framework to maintain controllability, enhance performance, and safeguard the CPS from. A data-driven controllability algorithm identifies allowable actuator combinations to guarantee controllability. During sensing breakdown, lack of complete state measurements dictates an intermittent framework to approximate value functions and tune embedded neural networks. When continuous communication between the reinforcement channel and the controller is challenged, the proposed framework will develop an self learning algorithm that will provide conditions wherein the internal reinforcement signal is rich enough to allow learning of the optimal control policy and when a trade-off between internal and external reinforcements is utilized. Finally, bionic, human brain-centric learning for CPS is formalised using B.F. Skinner's operant conditioning re-contextualised for learning in CPS, as well as sparse evolutionary training of neuronal configurations informed with physics of the system to approximate solutions to the non-linear Hamilton-Jacobi-Bellman (HJB) is presented.

Degree

thesis:*
Level thesis:degree_level
Doctoral
Department dc:contributor.department
Mechanical Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2023

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Connelly, Prachi P.
Advisors dc:contributor.advisor
  • Vamvoudakis, Kyriakos G.
  • Costello, Mark
Committee members dc:contributor.committeemember
  • Mazumdar, Anirban
  • Erturk, Alper
  • Wan, Yan

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/75178

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Connelly, Prachi P.. Secure, Intermittent, and Model-Free Learning Framework for Autonomous Cyber Physical Systems. Doctoral thesis, Georgia Institute of Technology, 2023. https://hdl.handle.net/1853/75178