Evaluación de la inteligencia artificial generativa en el contexto de la automática: un análisis crítico
Loading...
Publication date
Advisors
Research group
Center
Abstract
La reciente proliferación de las inteligencias artificiales (IA), en particular las IA generativas, está impulsando una necesidad
de transformación en la educación universitaria. La habilidad de las IA para generar contenido, redactar informes, resúmenes y
solucionar problemas de diversa complejidad, debería inducir una revisión de muchos de los métodos de evaluación tradicionales;
o al menos, un reconocimiento de la capacidad del estudiantado para emplear estas herramientas en la ejecución de sus tareas.
Este artículo tiene como objetivo evaluar las competencias de las principales IA disponibles en la actualidad para llevar a cabo
tareas asociadas con la ingeniería de control, tanto teóricas como prácticas. Los resultados indican que las IA actuales todavía
no pueden resolver problemas de control de manera efectiva, y tienden a recurrir a soluciones estándar que no siempre son
apropiadas; no obstante, muestran un rendimiento satisfactorio respecto de conocimientos teóricos generales.
The recent proliferation of artificial intelligences (AIs), particularly generative AIs, is driving a need for transformation in university education. The ability of AIs to generate content, write reports, summaries and solve problems of varying complexity should prompt a review of many traditional assessment methods, or at least a recognition of students’ ability to employ these tools in the execution of their tasks. This paper aims to assess the competencies of the main AIs currently available for carrying out tasks associated with control engineering, both theoretical and practical. The results indicate that current AIs are not yet able to solve control problems effectively, and tend to resort to standard solutions that are not always appropriate; however, they show satisfactory performance with respect to general theoretical knowledge.
The recent proliferation of artificial intelligences (AIs), particularly generative AIs, is driving a need for transformation in university education. The ability of AIs to generate content, write reports, summaries and solve problems of varying complexity should prompt a review of many traditional assessment methods, or at least a recognition of students’ ability to employ these tools in the execution of their tasks. This paper aims to assess the competencies of the main AIs currently available for carrying out tasks associated with control engineering, both theoretical and practical. The results indicate that current AIs are not yet able to solve control problems effectively, and tend to resort to standard solutions that are not always appropriate; however, they show satisfactory performance with respect to general theoretical knowledge.
Unesco Subjects
Bibliographic citation
Barragán, A. J., Aquino, A., Enrique, J. M., Segura, F., Martínez, M. Á., & Andújar, J. M. (2024). Evaluación la inteligencia artificial generativa en el contexto de la automática. In Jornadas de Automática (Issue 45). Universidade da Coruña. https://doi.org/10.17979/ja-cea.2024.45.10733














