Carlos Celemin, Ph.D.
Post-doctoral Researcher, Delft University of Technology
I am a postdoc in the Cognitive Robotics Department (CoR) at TU Delft with Jens Kober. My research is focused on the intersection of Robotics and Machine Learning methods for sequential Decision-Making systems, specifically Reinforcement Learning, Imitation Learning, and combinations of both. I am interested in Interactive Imitation Learning methods that allow non-expert users to transfer their partial knowledge to the robots, and allow them to obtain decision-making systems with high-level performances. I aim to develop data-efficient methods that make feasible the learning of complex motor skills directly with real robots.
We have talked about our work "Uncertainties Based Queries for Interactive Policy Learning with Evaluations and Corrections" in the workshop Empowering Interactive Robots by Learning Through Multimodal Feedback Channel in the 23rd ACM International Conference on Multimodal Interaction.
I am serving as Associate Editor for IROS 2021.
I am serving as Workshop co-chair of the IEEE/ASME International Conference on Advanced Intelligent Mechatronics, AIM 2021.
I have given the lectures on Reinforcement Learning within the course of Knowledge-based Control Systems in 2021.
I have given an invited lecture on "Robot Learning from Human-Robot Interaction" within the course of Human-Robot Interaction in the Robotics Master in 2020.
New conference paper: Snehal Jauhri, Carlos Celemin, and Jens Kober. Interactive Imitation Learning in State-Space. In Conference on Robot Learning (CoRL), 2020.
New conference paper: Giovanni Franzese, Carlos Celemin, and Jens Kober. Learning Interactively to Resolve Ambiguity in Reference Frame Selection. In Conference on Robot Learning (CoRL), 2020.
New journal paper: Rodrigo Pérez-Dattari, Carlos Celemin, Giovanni Franzese, Javier Ruiz-del-Solar, and Jens Kober. Interactive Learning of Temporal Features for Control. IEEE Robotics and Automation Magazine (Special Issue on “Deep Learning and Machine Learning in Robotics”), 2020.
I am serving as Associate Editor for IROS 2020.
I was selected as a Pioneer for participating in the Workshop: RSS Pioneers 2020.
I have been invited to give a talk at the workshop on "Closing the Academia to Real-World Gap in Service Robotics" during "RSS 2020" (July 13) in Oregon State University at Corvallis, Oregon, USA.
I am invited to give a talk at the workshop on “Human-Robot Collaboration & AI for industrial applications” during the European Robotics Forum 2020 in Malaga, Spain (March 03-05).
Our "Workshop on Interactive Robot Learning" proposal got accepted in ICRA 2020 (May 31).
New journal paper: Carlos Celemin, Guilherme Maeda, Javier Ruiz-del-Solar, Jan Peters, and Jens Kober. Reinforcement Learning of Motor Skills using Policy Search and Human Corrective Advice. International Journal of Robotics Research, OnlineFirst, 2019.
New conference paper: Jan Scholten, Daan Wout, Carlos Celemin, and Jens Kober. Deep Reinforcement Learning with Feedback-based Exploration. In IEEE Conference on Decision and Control (CDC), 2019.
New conference paper: Carlos Celemin and Jens Kober. Simultaneous Learning of Objective Function and Policy from Interactive Teaching with Corrective Feedback. In IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), 2019.
I am invited to give a talk at the IROS workshop "Open-Ended Learning for Object Perception and Grasping: Current Successes and Future Challenges" to be held the last day of IROS 2019 (November 8) in Macau, China.
New preprint: Daan Wout, Jan Scholten, Carlos Celemin, and Jens Kober. Learning Gaussian Policies from Corrective Human Feedback. arXiv:1903.05216 [cs.LG], 2019.
New conference paper: Rodrigo Pérez Dattari, Carlos Celemin, Javier Ruiz Del Solar, and Jens Kober. Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach. In IEEE International Conference on Robotics and Automation (ICRA), pp. 7611–7617, 2019.
I will give the lectures on Reinforcement Learning in the course "Knowledge-based Control Systems"
New journal paper: Carlos Celemin, Javier Ruiz del Solar, and Jens Kober. A fast hybrid reinforcement learning framework with human corrective feedback. In Autonomous Robots, 2019.
I am giving a talk about my work in the Belgium Netherlands Workshop on Reinforcement Learning 2018, in Novermber 19.
I joined the Cognitive Robotics (CoR) department at TU Delft, since January of 2018, where I will be working as a postdoctoral researcher with Jens Kober in the Learning and Autonomous Control (LAC) group.
New conference paper: Rodrigo Pérez Dattari, Carlos Celemin, Javier Ruiz Del Solar, and Jens Kober. Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks. In International Symposium on Experimental Robotics (ISER), 2018.
I talked about my work at the International Symposium of Robotics Research (ISRR 2017), during a workshop on December 15, 2017.
New workshop paper: Carlos Celemin, Guilherme Maeda, Jens Kober, and Javier Ruiz-del-Solar. Human Corrective Advice in the Policy Search Loop. In Workshop Human-in-the-loop Robotic Manipulation: On the Influence of the Human Role, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017.
I attended the RoboCup 2017 with our UChile robotics Team, participating in the standard Platform League, in Nagoya, Japan.
I gave a talk about my work at the Intelligent Autonomous Systems (IAS) group at TU Darmstadt, Germany, July of 2017.
New conference paper: Carlos Celemin, Rodrigo Perez, Javier Ruiz-del-Solar, and Manuela Veloso. Interactive Machine Learning Applied to Dribble a Ball in Soccer with Biped Robots. In RoboCup 2017 Symposium, 2017.
I am visiting the Intelligent Autonomous Systems (IAS) group at TU Darmstadt, Germany, between June and September of 2017.
I am giving a talk in a colloquium at the Delft Center for Systems and Control (DCSC) at TU Delft, the Netherlands, in 18th of April, 2017.
I am visiting the Delft Center for Systems and Control (DCSC), at TU Delft, the Netherlands, between January and May of 2017.
I am visiting the CORAL research group, at Carnegie Mellon University, USA, between September and December of 2016.
I got a grant from the RoboCup Federation, for collaborations with other RoboCup labs.
I attended the RoboCup 2016 with our UChile robotics Team, participating in the standard Platform League (we reached semifinals for the third consecutive year), in Leipzig, Germany.
I was visiting the National Institute for Astrophysics and Opto-Electronics (INAOE) in Puebla, Mexico, between April and May of 2016.