Data-driven design of a reference governor using deep reinforcement learning

Reference tracking systems involve a plant that is stabilized by a local controller and a command center that indicates the reference set-point the plant should follow. Typically, these systems are subjected to limitations such as poorly designed controllers that do not allow them to achieve the desired performance. In situations where it is not possible to redesign the closed-loop system, it is usual to incorporate a reference governor that instructs the system to follow a modified reference path such that the resultant path is close to the ideal one. Current strategies to design the reference governor need to know a model of the system, which can be an unfeasible task. In this letter, we propose a framework based on deep reinforcement learning that can learn a policy to generate a modified reference that improves the system's performance in a non-invasive and model-free fashion. To illustrate the effectiveness of our approach, we present two challenging cases: a flight control with a pilot model that includes human reaction delays, and a mean-field control problem for a massive number of space-heating device. The proposed strategy successfully designs the reference governor that works even in situations that were not seen during the learning process.

• Autores: Arroyo Bernal, María Angélica
• Fecha de publicación: 2019
• Institución: Universidad de los Andes
• Repositorio: Séneca: repositorio Uniandes
• Idioma: eng
• OAI Identifier: oai:repositorio.uniandes.edu.co:1992/43959
• Acceso en línea: http://hdl.handle.net/1992/43959
• Palabra clave: Controladores programables - Investigaciones; Aprendizaje automático (Inteligencia artificial) - Investigaciones; Ingeniería
• Rights: openAccess
• License: https://repositorio.uniandes.edu.co/static/pdf/aceptacion_uso_es.pdf