M. Amin Safavi

  • Engineer

M. Amin Safavi

I started my bachelor’s studies in Mechanical Engineering; however, after a three-month research internship at MEMOCS in Italy, I discovered my passion for robotic systems and control. I worked on a swarm algorithm enhanced with obstacle avoidance at that time. With that passion realized, I chose to study Dynamics and Control for my Master’s. My thesis was focused on distributed optimal control of multiple quadrotors cooperatively carrying a cylindrical payload. During my Master’s studies, I collaborated with CAV-lab, University of Surrey, to develop novel Deep Learning approaches for sensor fault detection and AV predictive maintenance. Later, I collaborated with the CVSSP to create a dataset and a baseline for sound-based drone detection and localization. Ultimately, I joined DeepX after finishing my Master’s studies in 2021.


Automation is more than making the means of production to scale and reducing human labor.

I regard Automation as Humanism, which aims to transcend the human condition. This idea is perfectly articulated in the essay, “In Praise of Idleness” by Bertrand Russell, written in 1932:

“In a world where no one is compelled to work more than four hours a day every person possessed of scientific curiosity will be able to indulge it, and every painter will be able to paint without starving, however excellent his pictures may be … Good nature is the result of ease and security, not of a life of arduous struggle. Modern methods of production have given us the possibility of ease and security for all; we have chosen instead to have overwork for some and starvation for others.”

Let’s automate and liberate, so we can live more fully and have more equality of opportunities.



  • Safe Learning for Control
  • Model Predicitve Control
  • Constrained Nonlinear Optimization
  • Scientific Machine Learning
  • Differentiable Programming


  • Mountain therapy!

    I always find mountains to be majestic and humbling. The raw sensations of scale and nature are both unsettling and calming, which makes them more magical. The experience of the climb is not only happening on the surface of the earth but also in mind. Through the route's ups and downs, I get to traverse my landscape of thoughts and emotions and become more self-aware.

  • Investigations on Human Condition

    Why are we who we are and the way we are?

    Our action and state space are not only entirely under our control but also dictate our life choices and experiences. We feel that we are in control and base the social constructs that we are free agents, but we are not entirely free. Everything from genomes, synapses, and neuro-modulators to evolutionary socio-economic dynamics and geopolitics and beyond to the unknown can overwrite our paths and put us under constraints. I think of the Human condition as an underactuated system that, at some states, loses controllability and observability for some tasks and hence falls into determinism. But this intuition falls short on systems of partially free agents. I actively look for better theories from different fields to better grasp my understanding of the world and how to navigate it conceptually and pragmatically. I call this grand quest human condition modeling and control, modeling different modes of collapse into determinism and control to reach the desired mode willfully.

We use cookies on this site to enhance your user experience. If you continue to browse, you accept the use of cookies policy on our site.