Decision Making
In 2005 we started to work on the application of Reinforcement Learning to real robots. About a decade later we extended that research to the decision making process in general (not necessarily involving learning). All in all, we have studied RL in diverse contexts within robotics: robot task planning, onboard computer efficiency, robot reflex learning, robot control architectures, networked telerobots and engineering education, among others.
We have the following publications on this matter:
Contents
Journals (9)
2026
A. Bañuls-Arias, C. Galindo, A. Cruz-Martín, M. Castellano Quero, J.M. Gandarias-Palacios, J.A. Fernández-Madrigal, V. Arevalo-Espejo
Modeling Time-Aware Mobile Robot Navigation by Learning Subjective Time Maps (STM)
Computer Modeling in Engineering & Sciences, vol. 148, no. 1, pp. 33, 2026. Q1 · T1
@article{banulsarias2026,
title = {Modeling Time-Aware Mobile Robot Navigation by Learning Subjective Time Maps (STM)},
author = {Bañuls-Arias, Adrián and Galindo, Cipriano and Cruz-Martín, Ana and Castellano Quero, Manuel and Gandarias-Palacios, Juan-Manuel and Fernández-Madrigal, Juan-Antonio and Arevalo-Espejo, Vicente},
url = {https://doi.org/10.32604/cmes.2026.085976},
doi = {10.32604/cmes.2026.085976},
year = {2026},
date = {2026-07-01},
journal = {Computer Modeling in Engineering & Sciences},
volume = {148},
number = {1},
pages = {33},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2022
D.A. Constantinescu, Á. González-Navarro, R. Asenjo-Plaza, J.A. Fernández-Madrigal, A. Cruz-Martín
Enabling Easier Programming of Machine Learning Algorithms on Robots with oneAPI Toolkits
IEEE FeedForward Magazine, vol. 1, no. 1, pp. 2-7, 2022.
@article{constantinescu2022,
title = {Enabling Easier Programming of Machine Learning Algorithms on Robots with oneAPI Toolkits},
author = {Constantinescu, Denisa-Andreaa and González-Navarro, Ángeles and Asenjo-Plaza, Rafael and Fernández-Madrigal, Juan-Antonio and Cruz-Martín, Ana},
url = {https://r6.ieee.org/scv-cs/wp-content/uploads/sites/81/2022/03/1-CS-Mag-Feedforward-Denisa-MyFinal.pdf},
year = {2022},
date = {2022-04-01},
journal = {IEEE FeedForward Magazine},
volume = {1},
number = {1},
pages = {2-7},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2021
J.L. Matez-Bandera, J. Monroy, J. Gonzalez-Jimenez
Efficient semantic place categorization by a robot through active line-of-sight selection
Knowledge-Based Systems, vol. 240, 2021, ISSN: 0950-7051. Q1 · T1
@article{matez2021,
title = {Efficient semantic place categorization by a robot through active line-of-sight selection},
author = {Matez-Bandera, J. L and Monroy, Javier and Gonzalez-Jimenez, Javier},
url = {https://mapir.isa.uma.es/papersrepo/2021/2021_matez_KBS_semantic_place_categorization.pdf},
doi = {10.1016/j.knosys.2021.108022},
issn = {0950-7051},
year = {2021},
date = {2021-12-01},
journal = {Knowledge-Based Systems},
volume = {240},
abstract = {In this paper, we present an attention mechanism for mobile robots to face the problem of place categorization. Our approach, which is based on active perception, aims to capture images with characteristic or distinctive details of the environment that can be exploited to improve the efficiency (quickness and accuracy) of the place categorization. To do so, at each time moment, our proposal selects the most informative view by controlling the line-of-sight of the robot’s camera through a pan-only unit. We root our proposal on an information maximization scheme, formalized as a next-best-view problem through a Markov Decision Process (MDP) model. The latter exploits the short-time estimated navigation path of the robot to anticipate the next robot’s movements and make consistent decisions. We demonstrate over two datasets, with simulated and real data, that our proposal generalizes well for the two main paradigms of place categorization (object-based and image-based), outperforming typical camera-configurations (fixed and continuously-rotating) and a pure-exploratory approach, both in quickness and accuracy.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
D.A. Constantinescu, Á. González-Navarro, F. Corbera, J.A. Fernández-Madrigal, R. Asenjo-Plaza
Efficiency and Productivity for Decision Making on Low-Power Heterogeneous CPU+GPU SoCs
Journal of Supercomputing, vol. 77, pp. 44-65, 2021. Q2 · T2
@article{constantinescu2021,
title = {Efficiency and Productivity for Decision Making on Low-Power Heterogeneous CPU+GPU SoCs},
author = {Constantinescu, Denisa-Andreaa and González-Navarro, Ángeles and Corbera, Francisco and Fernández-Madrigal, Juan-Antonio and Asenjo-Plaza, Rafael},
url = {https://link.springer.com/article/10.1007/s11227-020-03257-3},
doi = {10.1007/s11227-020-03257-3},
year = {2021},
date = {2021-01-01},
journal = {Journal of Supercomputing},
volume = {77},
pages = {44-65},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2020
D.A. Constantinescu, Á. González-Navarro, J.A. Fernández-Madrigal, R. Asenjo-Plaza
Performance Evaluation of Decision Making under Uncertainty for Low Power Heterogeneous Platforms
Journal of Parallel and Distributed Computing, vol. 137, pp. 119-133, 2020. Q1 · T1
@article{constantinescu2020,
title = {Performance Evaluation of Decision Making under Uncertainty for Low Power Heterogeneous Platforms},
author = {Constantinescu, Denisa-Andreaa and González-Navarro, Ángeles and Fernández-Madrigal, Juan-Antonio and Asenjo-Plaza, Rafael},
doi = {10.1016/j.jpdc.2019.11.009},
year = {2020},
date = {2020-03-01},
journal = {Journal of Parallel and Distributed Computing},
volume = {137},
pages = {119-133},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2019
Á. Martínez-Tenor, A. Cruz-Martín, J.A. Fernández-Madrigal
Interactive Learning Environments, vol. 37, no. 3, pp. 293-306, 2019. Q2 · T2
@article{martineztenor2019,
title = {Teaching Machine Learning In Robotics Interactively: The Case Of Reinforcement Learning With Lego® Mindstorms},
author = {Martínez-Tenor, Ángel and Cruz-Martín, Ana and Fernández-Madrigal, Juan-Antonio},
doi = {10.1080/10494820.2018.1525411},
year = {2019},
date = {2019-01-01},
journal = {Interactive Learning Environments},
volume = {37},
number = {3},
pages = {293-306},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2018
Á. Martínez-Tenor, J.A. Fernández-Madrigal, A. Cruz-Martín, J. Gonzalez-Jimenez
Towards a Common Implementation of Reinforcement Learning for Multiple Robotic Tasks
Expert Systems With Applications, vol. 100, pp. 246-259, 2018. Q1 · T1
@article{martineztenor2018,
title = {Towards a Common Implementation of Reinforcement Learning for Multiple Robotic Tasks},
author = {Martínez-Tenor, Ángel and Fernández-Madrigal, Juan-Antonio and Cruz-Martín, Ana and Gonzalez-Jimenez, Javier},
doi = {10.1016/j.eswa.2017.11.011},
year = {2018},
date = {2018-06-01},
journal = {Expert Systems With Applications},
volume = {100},
pages = {246-259},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2017
Á. Martínez-Tenor, J.A. Fernández-Madrigal, A. Cruz-Martín, J. Gonzalez-Jimenez
Towards a Common Implementation of Reinforcement Learning for Multiple Robotic Tasks
arXiv.org, 2017, (preliminary version).
@article{martineztenor2017,
title = {Towards a Common Implementation of Reinforcement Learning for Multiple Robotic Tasks},
author = {Martínez-Tenor, Ángel and Fernández-Madrigal, Juan-Antonio and Cruz-Martín, Ana and Gonzalez-Jimenez, Javier},
url = {https://arxiv.org/abs/1702.06329},
year = {2017},
date = {2017-02-01},
journal = {arXiv.org},
note = {preliminary version},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
2006
C. Galindo, A. Cruz-Martín, J.L. Blanco, J.A. Fernández-Madrigal, J. Gonzalez-Jimenez
A Multi-Agent Control Architecture for a Robotic Wheelchair
Applied Bionics & Biomecanics, vol. 3, no. 3, pp. 179–189, 2006, ISSN: 0921-8890. Q4 · T3
@article{galindo2006b,
title = {A Multi-Agent Control Architecture for a Robotic Wheelchair},
author = {Galindo, Cipriano and Cruz-Martín, Ana and Blanco, José-Luis and Fernández-Madrigal, Juan-Antonio and Gonzalez-Jimenez, Javier},
url = {https://mapir.isa.uma.es/wp-content/uploads/publicaciones/legacy/cgalindo/papers/draft_MARCA.pdf},
doi = {10.1533/abbi.2006.0027},
issn = {0921-8890},
year = {2006},
date = {2006-01-01},
journal = {Applied Bionics & Biomecanics},
volume = {3},
number = {3},
pages = {179--189},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Conferences (5)
2019
D.A. Constantinescu, Á. González-Navarro, F. Corbera, J.A. Fernández-Madrigal, R. Asenjo-Plaza
Solving Large-Scale Markov Decision Processes on Low-Power Heterogeneous Platforms
19th International Conference on Computational and Mathematical Methods in Science and Engineering, Universidad de Cádiz Costa Ballena, Cádiz (España), 2019.
@inproceedings{constantinescu2019,
title = {Solving Large-Scale Markov Decision Processes on Low-Power Heterogeneous Platforms},
author = {Constantinescu, Denisa-Andreaa and González-Navarro, Ángeles and Corbera, Francisco and Fernández-Madrigal, Juan-Antonio and Asenjo-Plaza, Rafael},
year = {2019},
date = {2019-07-01},
booktitle = {19th International Conference on Computational and Mathematical Methods in Science and Engineering},
address = {Costa Ballena, Cádiz (España)},
organization = {Universidad de Cádiz},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2014
Á. Martínez-Tenor, J.A. Fernández-Madrigal, A. Cruz-Martín
Lego Mindstorms NXT and Q-learning: a teaching approach for robotics and engineering
7th International Conference of Education, Research and Innovation (ICERI, 2014), Seville (Spain), 2014.
@inproceedings{martineztenor2014b,
title = {Lego Mindstorms NXT and Q-learning: a teaching approach for robotics and engineering},
author = {Martínez-Tenor, Ángel and Fernández-Madrigal, Juan-Antonio and Cruz-Martín, Ana},
url = {http://library.iated.org/view/MARTINEZTENOR2014LEG},
year = {2014},
date = {2014-11-01},
booktitle = {7th International Conference of Education, Research and Innovation (ICERI, 2014)},
address = {Seville (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2007
J.A. Fernández-Madrigal, C. Galindo, E. Cruz-Martín, A. Cruz-Martín, J. Gonzalez-Jimenez
Automatic Regulation of the Information Flow in the Control Loops of a Web Teleoperated Robot
IEEE International Conference on Robotics and Automation (ICRA'07), Rome (Italy), 2007.
@inproceedings{fernandezmadrigal2007c,
title = {Automatic Regulation of the Information Flow in the Control Loops of a Web Teleoperated Robot},
author = {Fernández-Madrigal, Juan-Antonio and Galindo, Cipriano and Cruz-Martín, Elena and Cruz-Martín, Ana and Gonzalez-Jimenez, Javier},
url = {http://babel.isa.uma.es/_utils/downloads/logdownloads.php?u=jafma&t=pdf&f=downloads%2Fjafma%2Fpapers%2Fwebforicra07_final.pdf},
year = {2007},
date = {2007-04-01},
booktitle = {IEEE International Conference on Robotics and Automation (ICRA'07)},
address = {Rome (Italy)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
C. Galindo, J.A. Fernández-Madrigal, J. Gonzalez-Jimenez
Towards the Automatic Learning of Reflex Modulation for Mobile Robot Navigation
pp. 347–356, Springer-Verlag, 2007, ISBN: 978-3-540-73055-2.
@inproceedings{galindo2007b,
title = {Towards the Automatic Learning of Reflex Modulation for Mobile Robot Navigation},
author = {Galindo, Cipriano and Fernández-Madrigal, Juan-Antonio and Gonzalez-Jimenez, Javier},
url = {http://babel.isa.uma.es/_utils/downloads/logdownloads.php?u=jafma&t=pdf&f=downloads%2Fjafma%2Fpapers%2FMurcia-Reflexes_enviado.pdf},
doi = {10.1007/978-3-540-73055-2_37},
isbn = {978-3-540-73055-2},
year = {2007},
date = {2007-01-01},
volume = {4527},
pages = {347--356},
publisher = {Springer-Verlag},
series = {Lecture Notes in Computer Science (International Work-conference on the Interplay between Natural and Artificial Computation)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2005
C. Galindo, J. Gonzalez-Jimenez, J.A. Fernández-Madrigal
An Architecture for Close Human-Robot Interaction. Application to Rehabilitation Robotics
IEEE International Conference on Mechatronics and Automation (ICMA'2005), Ontario (Canada), 2005.
@inproceedings{galindo2005,
title = {An Architecture for Close Human-Robot Interaction. Application to Rehabilitation Robotics},
author = {Galindo, Cipriano and Gonzalez-Jimenez, Javier and Fernández-Madrigal, Juan-Antonio},
url = {http://babel.isa.uma.es/_utils/downloads/logdownloads.php?u=jafma&t=pdf&f=downloads%2Fjafma%2Fpapers%2FachrinforICMA2005.pdf},
year = {2005},
date = {2005-07-01},
booktitle = {IEEE International Conference on Mechatronics and Automation (ICMA'2005)},
address = {Ontario (Canada)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
National conferences (2)
2021
D.A. Constantinescu, Á. González-Navarro, R. Asenjo-Plaza, J.A. Fernández-Madrigal, A. Cruz-Martín
Enhancing On-Line Planning Under Uncertainty via Bloom Filter Based Memory
Actas de las jornadas SARTECO 2021, Málaga (Spain), 2021.
@inproceedings{constantinescu2021b,
title = {Enhancing On-Line Planning Under Uncertainty via Bloom Filter Based Memory},
author = {Constantinescu, Denisa-Andreaa and González-Navarro, Ángeles and Asenjo-Plaza, Rafael and Fernández-Madrigal, Juan-Antonio and Cruz-Martín, Ana},
year = {2021},
date = {2021-09-01},
booktitle = {Actas de las jornadas SARTECO 2021},
address = {Málaga (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
2017
D.A. Constantinescu, Á. González-Navarro, J.A. Fernández-Madrigal, R. Asenjo-Plaza
Optimization of a decision-making algorithm for heterogeneous platforms
XXVIII Jornadas de Paralelismo (JP2017), Málaga (Spain), 2017.
@inproceedings{constantinescu2017,
title = {Optimization of a decision-making algorithm for heterogeneous platforms},
author = {Constantinescu, Denisa-Andreaa and González-Navarro, Ángeles and Fernández-Madrigal, Juan-Antonio and Asenjo-Plaza, Rafael},
year = {2017},
date = {2017-09-01},
booktitle = {XXVIII Jornadas de Paralelismo (JP2017)},
address = {Málaga (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
PhD Theses (1)
2022
D.A. Constantinescu
Towards Energy Efficiency and Productivity for Decision Making in Mobile Robot Navigation
E.T.S.I. Industriales, 2022.
@phdthesis{constantinescu2022b,
title = {Towards Energy Efficiency and Productivity for Decision Making in Mobile Robot Navigation},
author = {Constantinescu, Denisa-Andreaa},
year = {2022},
date = {2022-07-01},
school = {E.T.S.I. Industriales},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
Master Theses (4)
2022
A.J. Pérez Bazuelo
Aprendizaje por refuerzo en remoto para la navegación de robots móviles
E.T.S.I. Industriales (Univ. de Málaga, Spain), 2022.
@mastersthesis{perezbazuelo2022,
title = {Aprendizaje por refuerzo en remoto para la navegación de robots móviles},
author = {Pérez Bazuelo, Antonio Jesús},
year = {2022},
date = {2022-09-01},
school = {E.T.S.I. Industriales (Univ. de Málaga, Spain)},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
P. Pardo López
Aprendizaje por refuerzo para posicionamiento de objetos mediante un brazo manipulador
E.T.S.I. Industriales (Univ. de Málaga, Spain), 2022.
@mastersthesis{pardolopez2022,
title = {Aprendizaje por refuerzo para posicionamiento de objetos mediante un brazo manipulador},
author = {Pardo López, Pablo},
year = {2022},
date = {2022-09-01},
school = {E.T.S.I. Industriales (Univ. de Málaga, Spain)},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
2021
R. de Santiago Fernández
Implementación en ROS del aprendizaje automático de la navegación reactiva de un robot móvil con retrasos en el proceso
E.T.S.I. Industriales, 2021.
@mastersthesis{santiagofernandez2021,
title = {Implementación en ROS del aprendizaje automático de la navegación reactiva de un robot móvil con retrasos en el proceso},
author = {de Santiago Fernández, Rafael},
year = {2021},
date = {2021-07-01},
school = {E.T.S.I. Industriales},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
2020
F.J. Naranjo Campos
Mejoras del aprendizaje por refuerzo tabular en el contexto de la navegación de robots móviles
E.T.S.I. Industriales, 2020.
@mastersthesis{naranjocampos2020,
title = {Mejoras del aprendizaje por refuerzo tabular en el contexto de la navegación de robots móviles},
author = {Naranjo Campos, Francisco José},
year = {2020},
date = {2020-09-01},
school = {E.T.S.I. Industriales},
keywords = {},
pubstate = {published},
tppubtype = {mastersthesis}
}
Technical Reports (2)
2021
J.A. Fernández-Madrigal
Tabular True On-Line SARSA(lambda)
University of Malaga 2021.
@techreport{fernandezmadrigal2021b,
title = {Tabular True On-Line SARSA(lambda)},
author = {Fernández-Madrigal, Juan-Antonio},
url = {https://babel.isa.uma.es/_utils/downloads/logdownloads.php?u=jafma&t=pdf&f=downloads%2Fjafma%2Fpapers%2Ftabulartosl.pdf},
year = {2021},
date = {2021-06-01},
institution = {University of Malaga},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
2013
J.A. Fernández-Madrigal, A. Cruz-Martín
Some experiments on the integration of symbolic and sub-symbolic learning based on imagery and abstraction
Centre for Robotic and Neural and Systems, CRNS, University of Plymouth (UK) Systems // Engineering and Automation Dpt., University of Málaga (Spain) 2013.
@techreport{fernandezmadrigal2013b,
title = {Some experiments on the integration of symbolic and sub-symbolic learning based on imagery and abstraction},
author = {Fernández-Madrigal, Juan-Antonio and Cruz-Martín, Ana},
year = {2013},
date = {2013-08-01},
institution = {Centre for Robotic and Neural and Systems, CRNS, University of Plymouth (UK) Systems // Engineering and Automation Dpt., University of Málaga (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
