I'm Rodrigo Pérez-Dattari, a roboticist interested in every aspect of robotic decision-making.
I'm currently completing my doctoral studies at the Delft University of Technology in The Netherlands. Here, my work has primarily focused on developing methodologies to enhance the learning of motion policies, aiming for greater flexibility, efficiency, and reliability.
News
-
[August 2024] Ph.D. Thesis “Generalizable Robotic Imitation Learning: Interactive Learning and Inductive Bias” by Rodrigo Pérez-Dattari, publicly available at TU Delft repository.
-
[August 2024] Journal paper “Deep Metric Imitation Learning for Stable Motion Primitives” by Rodrigo Pérez-Dattari, Cosimo Della Santina and Jens Kober, accepted as regular paper to Advanced Intelligent Systems.
-
[October 2023] Awarded DAAD AInet Fellowship.
-
[May 2023] Journal paper “Stable Motion Primitives via Imitation and Contrastive Learning” by Rodrigo Pérez-Dattari and Jens Kober, accepted as regular paper to the IEEE Transactions on Robotics (T-RO).
-
[May 2023] Conference paper “Robotic Packaging Optimization with Reinforcement Learning” by Eveline Drijver, Rodrigo Pérez-Dattari, Jens Kober, Cosimo Della Santina and Zlatan Ajanovic, accepted to the IEEE International Conference on Automation Science and Engineering (CASE).
-
[August 2022] Journal paper “Interactive Imitation Learning in Robotics: a Survey” by Carlos Celemin, Rodrigo Pérez-Dattari, Eugenio Chisari, Giovanni Franzese, Leandro de Souza Rosa, Ravi Prakash, Zlatan Ajanović, Marta Ferraz, Abhinav Valada, and Jens Kober, accepted to the Foundations and Trends® in Robotics Journal.
-
[July 2022] Journal paper “Visually-Guided Motion Planning for Autonomous Driving from Interactive Demonstrations” by Rodrigo Pérez-Dattari, Bruno Brito, Oscar de Groot, Jens Kober and Javier Alonso-Mora accepted to the International Scientific Journal Engineering Applications of Artificial Intelligence.
-
[February 2021] Conference paper “Imitation Learning with Inconsistent Demonstrations through Uncertainty-based Data Manipulation” by Peter Valletta, Rodrigo Pérez-Dattari and Jens Kober, accepted to the IEEE International Conference on Robotics and Automation (ICRA).
-
[March 2020] Journal paper “Interactive Learning of Temporal Features for Control”, by Rodrigo Pérez-Dattari, Carlos Celemin, Giovanni Franzese, Javier Ruiz-del-Solar and Jens Kober, accepted as regular paper to the IEEE Robotics and Automation Magazine (RAM).
-
[April 2019] Accepted as a participant to the ETH Robotics Summer School.