MaLPi Project

Machine Learning on a Raspberry Pi (also a subtle reference to the Stargate shows)

A robotics project for playing around with hardware and learning to use Machine Learning techniques.

Task

This is my very tentative list of features to add to MaLPi. Although they are listed in numbered order, only the first one is 'real'. If/when I finish the first task I'll re-asses the list, possibly moving things around or dropping some or adding new ones.

  1. VAE based DonkeyCar pilot
  2. Pre-train VAE on images from all but one track
  3. Train separate policies on each track with the VAE as an image embedder
  4. Switch to RNN policy
  5. Train a single policy on multiple tracks/tasks
  6. Add a small DNC as a working memory
  7. Add an IMU and learn to detect crashes/bumps
  8. Add more tasks
    • Cone/Human/dog/etc detector (bounding box as output)
    • Drive to goal with goal given as an image
    • Sketches as inputs (goals) and/or outputs
    • NLP description of a scene or task trajectory as output
  9. Switch to more formal multi-task and/or meta-learning and/or lifelong learning
  10. Add some form of Aggregate memory that includes all previous experience

Model Predictive Control is a control method based on planning n-steps into the future to find the best path, as currently determined by the model. Take the first step. Then re-plan, take the new first step. Repeat until done.

Software

My GitHub repo
My DonkeyCar fork

Current Hardware

MaLPi

Estimated total hardware costs: $210-$230

Previous Hardware Versions

Bleyddyn

Bleyddyn

Professional Programmer, ML Student

links