To sum up, here are the main objectives of this project:
* Learn the robot operating system ROS2 environment and use Python3 to create nodes and call
topics and services
* Control a Gazebo simulated Turtlebot in a simulated map
* Understand the basic notion of Simultaneous Localization and Mapping (SLAM) and use it to
generate a map using data from the simulated robot
* (Ongoing) Implement reinforcement learning for obstacle avoidance and path planning in a way to has the optimal policy to plan the robot’s trajectory to explore an unknown room
* (future_plan) Test the trained algorithm on a real Turtlebot after validating the simulations