Book Image

ROS Programming: Building Powerful Robots

By : Anil Mahtani, Aaron Martinez, Enrique Fernandez Perdomo, Luis Sánchez, Lentin Joseph
Book Image

ROS Programming: Building Powerful Robots

By: Anil Mahtani, Aaron Martinez, Enrique Fernandez Perdomo, Luis Sánchez, Lentin Joseph

Overview of this book

This learning path is designed to help you program and build your robots using open source ROS libraries and tools. We start with the installation and basic concepts, then continue with the more complex modules available in ROS, such as sensor and actuator integration (drivers), navigation and mapping (so you can create an autonomous mobile robot), manipulation, computer vision, perception in 3D with PCL, and more. We then discuss advanced concepts in robotics and how to program using ROS. You'll get a deep overview of the ROS framework, which will give you a clear idea of how ROS really works. During the course of the book, you will learn how to build models of complex robots, and simulate and interface the robot using the ROS MoveIt motion planning library and ROS navigation stacks. We'll go through great projects such as building a self-driving car, an autonomous mobile robot, and image recognition using deep learning and ROS. You can find beginner, intermediate, and expert ROS robotics applications inside! It includes content from the following Packt products: ? Effective Robotics Programming with ROS - Third Edition ? Mastering ROS for Robotics Programming ? ROS Robotics Projects
Table of Contents (37 chapters)
Title page
Copyright and Credits
Packt Upsell
Preface
Bibliography
Index

Introduction to deep learning and its applications


So what actually is deep learning? It is a buzzword in neural network technology. What is a neural network then? An artificial neural network is a computer software model that replicates the behaviour of neurons in the human brain. A neural network is one way to classify data. For example, if we want to classify an image by whether it contains an object or not, we can use this method. There are several other computer software models for classification like logistic regression, Support Vector Machine (SVM); a neural network is one among them.

So why we are not calling it neural network instead of deep learning? The reason is that in deep learning, we use a large number of artificial neural networks. So you may ask, "So why it was not possible before?" The answer: to create a large number of neural networks (multilayer perceptron), we may need a high amount of computational power. So how has it become possible now? It's because of the availability...