Skip to content
forked from ob-f/OpenBot

OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones supports advanced robotics workloads such as person following and real-time autonomous navigation.

Notifications You must be signed in to change notification settings

Lilousarg/OpenBot

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Exploring Reinforcement Learning for Autonomous Control: A Case Study with the OpenBot Platform

This repository concerns my Masters thesis, a work on implementing Reinforcement Learning to real hardware entirely on a smartphone, using the OpenBot educational platform.

It is composed of my written report, and the folder OpenBot is forked from https://github.com/isl-org/OpenBot with modifications in the app using Android Studio, modifications of the python's script for machine learning training to include Reinforcement learning. There are also the codes provided for the work done on Cartpole and Pong.

The code modifications on the OpenBot app was mostly done in the logger folder where the policy gradient feature and MyModel can be found. The code for the preliminary attempt can be seen in the python scripts and the LoggerFragmentRL class.

For any remarks or questions, do not hesitate to ask me at [email protected]

About

OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones supports advanced robotics workloads such as person following and real-time autonomous navigation.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 49.8%
  • Java 24.5%
  • Jupyter Notebook 18.2%
  • C 2.8%
  • CMake 1.9%
  • Python 1.4%
  • Other 1.4%