Daniel Angelov

PhD Student Robotics and AI

University of Edinburgh

About me

Making actual robots smarter.

Researching how just a few expert demonstrations, alongside a causal view of the world, can be used to learn difficult, yet robust and safe, long-horizon behaviours for agents. Using hierarchical learning as a tool for the robot to understand the underlying problem structure. Pushing towards interpretable, explainable, cause-effect based machine learning for robotics.

PhD student at the Robust Autonomy and Decisions group, part of the Insitute for Perception, Action and Behaviour at the University of Edinburgh. I am supervised by Dr. Subramanian Ramamoorthy and Dr. Kartic Subr.

Building robots and liquid rocket engines.


  • Artificial Intelligence
  • Causality
  • Robotics
  • Computer Vision


  • PhD in Robotics and Autonomous Systems, 2020

    University of Edinburgh

  • MEng in Robotics, 2015

    University of Reading



Interactions and Analytics Intern


Jun 2017 – Nov 2017 Palo Alto, California
Working on the DARPA XAI project on Explainability in Artificial Intelligence Systems. Interview.

Research Assistant

The University of Edinburgh

Sep 2016 – Present Edinburgh

Worked as Teaching Support for various courses: Probabilistic Modellign and Reasoning, Reinforcement Learning, System Design Projects.

Currently RA with the Alan Turing Institute and the CRUK project MAMMOBOT.


OpenCV Developer

Google Summer of Code

Jun 2013 – Aug 2014 Remote
Spend two summer at GSOC with OpenCV to work on Line Segment Detector in imgproc and custom pattern calibration.

Software Engineer R&D

Robotic, Inc

Jul 2012 – Oct 2013 Bulgaria
Developed a stereo vision based system for long range (>250m) positioning and tracking of flying objects. Currently installed in several airports and factories.

Recent Posts

Interactive Plots with Bokeh/Holoviews (and Hugo) - Part 0

Bokeh and Holoviews are an amazing set of libraries to help us visualize data in an intuitive and interactive way. Here you’ll …

'wget' Files From Google Drive (+ online tool)

Working with different datasets across machines, in Google Colab, Kaggle Kernels or your own notebooks we sometimes need to transfer …

How to Remember Your Bash Spells with 'make'

Very often we find ourselves changing parameters of scripts or googling what was the right combination of bash commands. What’s …

Best paper runner-up award at the Conference on Robot Learning 2019

We received a best paper runner-up award at the Conference on Robot Learning 2019 for the paper of Disentangled Relational …

Interview during my PARC Internship


  • Bayes Centre, Edinburgh, Scotland EH89AB
  • DM Me