Learning & Control

This pillar focuses on learning and control methods that allow robots to act robustly in the real world, especially when simulations, training conditions, and deployment environments do not perfectly match. I work on machine learning approaches that help robots adapt their behavior over time, transfer policies safely from simulation to reality, and maintain performance under changing conditions. The long-term objective is to support increasingly autonomous systems that can make reliable decisions in industrial and assistive contexts while remaining aligned with safety and operational constraints.

Key open problems include how to reduce the brittleness of learning-based control, how to maintain performance under continual change, and how to combine adaptation with safety guarantees. Current directions include continual domain adaptation, sim2real transfer, interaction-aware reinforcement learning, and methods that improve robustness without requiring excessive hyperparameter tuning or hand-crafted task-specific engineering. I am particularly interested in learning frameworks that are not only effective but also transparent enough to support engineering trust, iteration, and deployment in real collaborative systems.

Related Projects

Project Thumbnail
ROMEO
Robot-MEdiated Object manipulation with haptic feedback

01 Apr 2024 » 31 Mar 2027

Read more
Project Thumbnail
M-RoCK
Human-Machine Interaction Modeling for Continuous Improvement of Robot Behavior

01 Aug 2021 » 31 Jul 2024

Read more
Project Thumbnail
RobotDoC
Robotics for Development of Cognition

01 Sep 2009 » 01 Sep 2014

Read more
Project Thumbnail
IRMA
Autonomous Mobile Robot Research

01 Jul 2005 » 01 Dec 2009

Read more

Featured Publications:

  1. Safe Continual Domain Adaptation After Sim2Real Transfer of Reinforcement Learning Policies in Robotics
     Pre-print. Mar 2025.
    Josifovski, Josip; Gu, Shangding; Malmir, Mohammadhossein; Huang, Haoliang; Auddy, Sayantan; Navarro-Guerrero, Nicolás; Spanos, Costas; Knoll, Alois
    DOI, PDF, URL, bib file. bibkey: Josifovski2025Safe Supplementary material ©2025 The Authors.
  2. Continual Domain Randomization
     IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 4965-4972. Abu Dhabi, United Arab Emirates. Oct 2024.
    Josifovski, Josip; Auddy, Sayantan; Malmir, Mohammadhossein; Piater, Justus; Knoll, Alois; Navarro-Guerrero, Nicolás
    DOI, PDF, URL, bib file. bibkey: Josifovski2024Continual Supplementary material ©2024 IEEE The Authors.
  3. Quantifying the Effect of Feedback Frequency in Interactive Reinforcement Learning for Robotic Tasks
     Neural Computing and Applications. Special Issue on Human-aligned Reinforcement Learning for Autonomous Agents and Robots. vol. 35, no. 23, pp. 16931–16943. Aug 2023.
    Harnack, Daniel; Pivin-Bachler, Julie; Navarro-Guerrero, Nicolás
    DOI, PDF, URL, bib file. bibkey: Harnack2023Quantifying ©2023 Springer The Authors.
  4. Editorial: Cognitive Inspired Aspects of Robot Learning
     Frontiers in Neurorobotics. vol. 17, pp. 1256788. Aug 2023.
    Cruz, Francisco; Solis, Miguel A.; Navarro-Guerrero, Nicolás
    DOI, PDF, URL, bib file. bibkey: Cruz2023Editorial ©2023 Frontiers Media S.A. The Authors.
  5. Survey on Reinforcement Learning for Language Processing
     Artificial Intelligence Review. vol. 56, no. 2, pp. 1543–1575. Feb 2023.
    Uc-Cetina, Víctor; Navarro-Guerrero, Nicolás; Martin-Gonzalez, Anabel; Weber, Cornelius; Wermter, Stefan
    DOI, PDF, URL, bib file. bibkey: Uc-Cetina2023Survey ©2023 Springer US The Authors.
  6. Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks
     IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 10193-10200. Kyoto, Japan. Oct 2022.
    Josifovski, Josip; Malmir, Mohammadhossein; Klarmann, Noah; Zagar, Bare Luka; Navarro-Guerrero, Nicolás; Knoll, Alois
    DOI, PDF, URL, bib file. bibkey: Josifovski2022Analysis Supplementary material ©2022 IEEE The Authors.
  7. Guest Editorial Special Issue on Emerging Topics on Development and Learning
     IEEE Transactions on Cognitive and Developmental Systems. vol. 14, no. 2, pp. 255–257. Jun 2022.
    Escobar, María-José; Navarro-Guerrero, Nicolás; Ruiz-del-Solar, Javier; Sandini, Giulio
    DOI, PDF, URL, bib file. bibkey: Escobar2022Guest ©2022 IEEE The Authors.
  8. Guest Editorial Special Issue on Continual Unsupervised Sensorimotor Learning
     IEEE Transactions on Cognitive and Developmental Systems. vol. 13, no. 2, pp. 234–238. Jun 2021.
    Navarro-Guerrero, Nicolás; Nguyen, Sao Mai; Öztop, Erhan; Zhong, Junpei
    DOI, PDF, URL, bib file. bibkey: Navarro-Guerrero2021Guest ©2021 IEEE
  9. Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks
     International Journal of Computational Intelligence and Applications. vol. 17, no. 2, pp. 1850008. Jun 2018.
    Hinz, Tobias; Navarro-Guerrero, Nicolás; Magg, Sven; Wermter, Stefan
    DOI, PDF, URL, bib file. bibkey: Hinz2018Speeding Supplementary material ©2018 World Scientific Publishing Europe Ltd. The Authors.
  10. Improving Robot Motor Learning with Negatively Valenced Reinforcement Signals
     Frontiers in Neurorobotics. vol. 11, no. 10, Apr 2017.
    Navarro-Guerrero, Nicolás; Lowe, Robert; Wermter, Stefan
    DOI, PDF, URL, bib file. bibkey: Navarro-Guerrero2017Improving Supplementary material ©2017 Copyright Navarro-Guerrero et al.
  11. Neurocomputational Mechanisms for Adaptive Self-Preservative Robot Behaviour
     Universität Hamburg. Hamburg, Germany. May 2016.
    Navarro-Guerrero, Nicolás
    PDF, URL, bib file. bibkey: Navarro-Guerrero2016Neurocomputational Supplementary material ©2016 Copyright Nicolás Navarro-Guerrero
  12. Interaction in Reinforcement Learning Reduces the Need for Finely Tuned Hyperparameters in Complex Tasks
     Kognitive Systeme. vol. 3, no. 2, Dec 2015.
    Stahlhut, Chris; Navarro-Guerrero, Nicolás; Weber, Cornelius; Wermter, Stefan
    DOI, PDF, URL, bib file. bibkey: Stahlhut2015Interaction ©2015 Copyright Stahlhut et al.
  13. Interaction is More Beneficial in Complex Reinforcement Learning Problems than in Simple Ones
     Interdisziplinärer Workshop Kognitive Systeme: Mensch, Teams, Systeme und Automaten. pp. 142-150. Bielefeld, Germany. Mar 2015.
    Stahlhut, Chris; Navarro-Guerrero, Nicolás; Weber, Cornelius; Wermter, Stefan
    PDF, URL, bib file. bibkey: Stahlhut2015Interaction slides ©2015 Copyright tahlhut et al.
  14. Special Session: Training in Robotics for Development of Cognition (RobotDoC)
     Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL). Osaka, Japan. Aug 2013.
    Vollmer, Anna-Lisa; Ruciński, Marek; Alessandro, Cristiano; Wilkinson, Nicholas; Navarro-Guerrero, Nicolás; Handl, Andrea
    PDF, URL, bib file. bibkey: Vollmer2013Special ©2013 Copyright Vollmer et al.
  15. Fuzzy Motivations in a Multiple Agent Behaviour-Based Architecture
     International Journal of Advanced Robotic Systems. vol. 10, no. 313, pp. 1-13. Aug 2013.
    Arredondo, Tomás; Freund, Wolfgang; Navarro-Guerrero, Nicolás; Castillo, Patricio
    DOI, PDF, URL, bib file. bibkey: Arredondo2013Fuzzy ©2013 CC BY 3.0 Copyright Arredondo et al.
  16. Real-World Reinforcement Learning for Autonomous Humanoid Robot Docking
     Robotics and Autonomous Systems. vol. 60, no. 11, pp. 1400-1407. Nov 2012.
    Navarro-Guerrero, Nicolás; Weber, Cornelius; Schroeter, Pascal; Wermter, Stefan
    DOI, PDF, URL, bib file. bibkey: Navarro-Guerrero2012Real ©2012 Elsevier B.V. All rights reserved.
  17. A Neurocomputational Amygdala Model of Auditory Fear Conditioning: A Hybrid System Approach
     International Joint Conference on Neural Networks (IJCNN). pp. 214-221. Brisbane, QLD, Australia. Jun 2012.
    Navarro-Guerrero, Nicolás; Lowe, Robert; Wermter, Stefan
    DOI, PDF, URL, bib file. bibkey: Navarro-Guerrero2012Neurocomputational slides ©2012 IEEE
  18. Many-Routes Hypothesis of Fear Conditioning: A Dynamical Reservoir Based Approach
     Marie-Curie Researchers Symposium Poster. Warsaw, Poland. Sep 2011.
    Navarro, Nicolás; Lowe, Robert; Weber, Cornelius; Wermter, Stefan
    PDF, URL, bib file. bibkey: Navarro2011Many ©2011 Copyright Nicolás Navarro-Guerrero
  19. Real-World Reinforcement Learning for Autonomous Humanoid Robot Charging in a Home Environment
     Annual Conference Towards Autonomous Robotic Systems (TAROS). vol. 6856 of LNCS, pp. 231-240. Sheffield, UK. Aug 2011.
    Navarro, Nicolás; Weber, Cornelius; Wermter, Stefan
    DOI, PDF, URL, bib file. bibkey: Navarro2011Real slides ©2011 Springer-Verlag Berlin Heidelberg
  20. Desarrollo e implementación de algoritmo evolutivo multi-objectivo para generar rutas online en un robot móvil autónomo
     Universidad Técnica Federico Santa María. Valparaíso, Chile. Dec 2009. Language: Spanish
    Navarro-Guerrero, Nicolás
    URL, bib file. bibkey: Navarro-Guerrero2010Desarrollo ©2009 Copyright Navarro-Guerrero
  21. Cooperative Adaptive Behavior Acquisition in Mobile Robot Swarms Using Neural Networks and Genetic Algorithms
     Electronics, Robotics and Automotive Mechanics Conference (CERMA). pp. 417-421. Morelos, Mexico. Sep 2008.
    Muñoz, César; Navarro, Nicolás; Arredondo, Tomás; Freund, Wolfgang
    DOI, URL, bib file. bibkey: Munoz2008Cooperative ©2008 IEEE
  22. Real-Time Adaptive Fuzzy Motivations for Evolutionary Behavior Learning by a Mobile Robot
     Mexican International Conference on Artificial Intelligence (MICAI) - Advances in Artificial Intelligence. vol. 4293 of LNCS, pp. 101-111. Apizaco, Mexico. Nov 2006.
    Freund, Wolfgang; Arredondo Vidal, Tomás; Muñoz, César; Navarro, Nicolás; Quirós, Fernando
    DOI, PDF, URL, bib file. bibkey: Freund2006Real ©2006 Springer-Verlag Berlin Heidelberg
  23. Acquiring Adaptive Behaviors of Mobile Robots Using Genetic Algorithms and Artificial Neural Networks
     Electronics, Robotics and Automotive Mechanics Conference (CERMA). vol. 1, pp. 87-91. Cuernavaca, Mexico. Sep 2006.
    Navarro, Nicolás; Muñoz, César; Freund, Wolfgang; Arredondo, Tomás
    DOI, PDF, URL, bib file. bibkey: Navarro2006Acquiring ©2006 IEEE
  24. Fuzzy Motivations for Evolutionary Behavior Learning by a Mobile Robot
     International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE). vol. 4031 of LNCS, pp. 462-471. Annecy, France. Jun 2006.
    Arredondo, Tomás; Freund, Wolfgang; Muñoz, César; Navarro, Nicolás; Quirós, Fernando
    DOI, PDF, URL, bib file. bibkey: Arredondo2006Fuzzy ©2006 Springer-Verlag Berlin Heidelberg