Thesis

Learning The-Self: Leveraging Proprioception to Guide the Autonomous Discovery of the Robot Body Schema

Biography

At the Technical University of Munich, my dedication over the past years has been to the intersection of robotics and machine intelligence, with a focus on applying machine learning and model-based approaches to robot self learning.

In the Robot Learning Group, our research efforts strive for innovative solutions that address real-world challenges in robotics, fostering a seamless integration of machine learning with traditional engineering techniques.

Research Interests

• Control of mechanical systems
• Embodied systems
• Learning algorithms for robots

Contact

• LinkedIn
• Google Scholar
• ORCID

Selected Publications

• Fernando Diaz Ledezma, Sami Haddadin, Machine learning-driven self-discovery of the robot body morphology, 2023. [Project Page]
• Fernando Diaz Ledezma, Sami Haddadin, RIL: Riemannian Incremental Learning of the Inertial Properties of the Robot Body Schema, 2021. [Project Page]
• Sami Haddadin, Lars Johannsmeier, Fernando Diaz Ledezma, Tactile Robots as a Central Embodiment of the Tactile Internet, 2019. [Project Page]
• Fernando Diaz Ledezma, Sami Haddadin, FOP Networks for Learning Humanoid Body Schema and Dynamics, 2018. [Project Page]
• Fernando Diaz Ledezma, Sami Haddadin, First-order-principles-based constructive network topologies: An application to robot inverse dynamics, 2017. [Project Page]