Book Image

Hands-On ROS for Robotics Programming

By : Bernardo Ronquillo Japón
Book Image

Hands-On ROS for Robotics Programming

By: Bernardo Ronquillo Japón

Overview of this book

Connecting a physical robot to a robot simulation using the Robot Operating System (ROS) infrastructure is one of the most common challenges faced by ROS engineers. With this book, you'll learn how to simulate a robot in a virtual environment and achieve desired behavior in equivalent real-world scenarios. This book starts with an introduction to GoPiGo3 and the sensors and actuators with which it is equipped. You'll then work with GoPiGo3's digital twin by creating a 3D model from scratch and running a simulation in ROS using Gazebo. Next, the book will show you how to use GoPiGo3 to build and run an autonomous mobile robot that is aware of its surroundings. Finally, you'll find out how a robot can learn tasks that have not been programmed in the code but are acquired by observing its environment. You'll even cover topics such as deep learning and reinforcement learning. By the end of this robot programming book, you'll be well-versed with the basics of building specific-purpose applications in robotics and developing highly intelligent autonomous robots from scratch.
Table of Contents (19 chapters)
1
Section 1: Physical Robot Assembly and Testing
5
Section 2: Robot Simulation with Gazebo
8
Section 3: Autonomous Navigation Using SLAM
13
Section 4: Adaptive Robot Behavior Using Machine Learning

ML comes to robotics

ML has its roots in statistical science. Remember when you have a cloud of points on an x-y frame and try to find the straight line that best fits all of them at the same time? This is what we call a linear regression and can be solved with a simple analytical formula. Regression is the first algorithm that you typically study when getting started with ML.

To acquire perspective, be aware that, before 1980, artificial intelligence and ML were part of the same corpora of knowledge. Then, artificial intelligence researchers focused their efforts on using logical, knowledge-based approaches, and ML kept the algorithmic approach, regression being the most basic and having neural network-based algorithms as its main bundle. Hence, this fact favored that ML evolved as a separated discipline.

Following path of the traditional research in neural networks in the &apos...