My name is Fuda van Diggelen, and I am a second year PhD student in the Computational Intelligence group at the Vrije Universiteit Amsterdam. My project is in collaboration with Technology Innovation Institute (TII), and supervised by Guszti Eiben and Eliseo Ferrante.

The topic of my PhD is the development of learning algorithms for evolvable legged robots –where we evolve both body and brain– in dynamic environments. The Evolutionary Robotucs (ER) context of my PhD provides several interesting challenges regarding embodied intelligence, model agnostic learning, and adaptive control. I mainly work in Python and C++ as part of a team that develops a software package called Revolve which is a wrapper for robot evolution experiments around different simulators (MuJoCo, Gazebo, Isaac Gym). Within this framework, I develop controllers for robots that learn motor skills from scratch using Differential Neural Networks.

Background

I graduated in 2020 with two master degrees: Human Movement Science (with predicate cum laude Vrije Universiteit Amserdam) and Mechanical Engineering (Technische Universiteit Delft). Both masters were obtained in nominally in parallel. For my study Human Movement Science (in which I also obtained my B.Sc. degree) I specialised in human motor control and neuromechanics. At TU Delft I specialised on the topic of bio-robotics and control theory.

Research Interest

In general, I like to combine ideas from different fields and nature to solve hard probems in robotics. Topics of interests include: self-modelling, embodied intelligence, complex adaptive systems, and control theory. I believe that current machine learning applications in robotics could benefit a lot when using control theoretic principles. For example, leveraging physics informed domains, geometric priors, and equivariant properties provide additional frameworks for current models. Currently, I am mostly interested in the use of ML for data-driven modelling of complex systems in robotic control.

Interested in collaboration? Feel free to contact me: fuda.van.diggelen@vu.nl