Here's a collection of various resources that I've found really helpful over the years:

Technical docs and tutorials

Lie Algebra:

  1. A micro Lie theory for state estimation in robotics (Joan Solà et al): Lecture video, Paper

  2. Tom Drummond's notes

  3. Ethan Eade's documents

Random ML Tidbits:

  1. Feedback in Machine Learning systems:

    1. Short video [Drew Bagnell]

    2. Longer ICML2020 talk [A Venkatraman, S Chaudhary]

    3. Article

Courses

AI/ML/Robotics:

  1. Intro to AI (UC Berkeley CS188) - The Pac-Man projects are the best set of assignments I've ever done.

  2. Statistical Techniques in Robotics (CMU Robotics 16-831) - A great overview of probabilistic and learning techniques in robotics.

  3. Advanced Robotics (UC Berkeley CS 287) - Tour de force of Robotics. The lecture slides are fantastic reference material.

Reinforcement Learning:

  1. Introduction to Reinforcement Learning (David Silver)

  2. Deep RL bootcamp (Pieter Abbeel et al)

Applying to US PhD programs

This document by Prof Harchol at CMU