IIT People Search

Research center
Interests
About

Daniel Felipe Ordoñez Apraez is a Ph.D. student of the European Laboratory for Learning and Intelligent Systems (ELLIS) doctoral program under the supervision of Dr. Claudio Semini (DLS), Dr. Massimiliano Pontil (UCL-CSML), and Dr. Carlos Mastalli (RoMi). He received a Masters's degree in Artificial Intelligence from the Universitat Politècnica de Catalunya (UPC-Barcelona Tech) and a Bachelors's degree in Mechatronics Engineering from the Universidad Nacional De Colombia (UNAL).

He previously worked as a research student (and later scientist) at the Institut de Robòtica i Informàtica Industrial (CSIC-IRI-UPC) under the supervision of Dr. Francesc Moreno-Noguer, Dr. Mario Martin, and Dr. Antonio Agudo in the intersection of computer graphics, robotics, and control for the synthesis of realistic high-speed legged locomotion using Reinforcement Learning techniques, and the study of Discrete Morphological Symmetries of robotic systems. 

His doctoral project focuses on the intersection of Optimal Control and applied Machine Learning applied to legged robot control, system identification, and disturbance identification. 


Education

Title: B.Sc. in Mechatronics Engineering
Institute: Universidad Nacional de Colombia
Location: Bogotá D.C.
Country: Colombia
From: 2013 To: 2019

Title: M.Sc. in Artificial Intelligence
Institute: Universitat Politècnica de Catalunya · Barcelona Tech - UPC
Location: Barcelona
Country: Spain
From: 2019 To: 2021

Top Publications
2023
Ordonez-Apraez D., Martin M., Agudo A., Moreno-Noguer F.
On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis
Robotics Science and Systems, pp. 8
2022
Ordonez-Apraez D., Agudo A., Moreno-Noguer F., Martin M.
An Adaptable Approach to Learn Realistic Legged Locomotion without Examples
International Conference on Robotics and Automation
All Publications
2023
Ordonez-Apraez D., Martin M., Agudo A., Moreno-Noguer F.
On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis
Robotics Science and Systems, pp. 8
2022
Ordonez-Apraez D., Agudo A., Moreno-Noguer F., Martin M.
An Adaptable Approach to Learn Realistic Legged Locomotion without Examples
International Conference on Robotics and Automation