Hands-On ROS for Robotics Programming

Training scenarios

This section is devoted to explaining how the reinforcement learning package – the content of the code sample provided with the book repository – is organized.

First, let's take into account that we are going to train the robot for two scenarios:

• Scenario 1: Travel to a target location. This scene is shown in the following image and consists of a square limited by four walls. There are no obstacles in the environment. The target location can be any point within the limits of the walls:

• Scenario 2: Travel to a target location avoiding obstacles. This scene consists of the same square plus four static cylindrical obstacles. ...