ROS Robotics Projects Second Edition

Build and control robots powered by the Robot Operating System, machine learning, and virtual reality

Ramkumar Gandhinathan , Lentin Joseph 지음

Packt(GCO Science) 2019년 12월 18일 출간

작품소개

책소개

▶Book Description
Nowadays, heavy industrial robots placed in workcells are being replaced by new age robots called cobots, which don't need workcells. They are used in manufacturing, retail, banks, energy, and healthcare, among other domains. One of the major reasons for this rapid growth in the robotics market is the introduction of an open source robotics framework called the Robot Operating System (ROS).

This book covers projects in the latest ROS distribution, ROS Melodic Morenia with Ubuntu Bionic (18.04). Starting with the fundamentals, this updated edition of ROS Robotics Projects introduces you to ROS-2 and helps you understand how it is different from ROS-1. You'll be able to model and build an industrial mobile manipulator in ROS and simulate it in Gazebo 9. You'll then gain insights into handling complex robot applications using state machines and working with multiple robots at a time. This ROS book also introduces you to new and popular hardware such as Nvidia's Jetson Nano, Asus Tinker Board, and Beaglebone Black, and allows you to explore interfacing with ROS. You'll learn as you build interesting ROS projects such as self-driving cars, making use of deep learning, reinforcement learning, and other key AI concepts.

By the end of the book, you'll have gained the confidence to build interesting and intricate projects with ROS.

▶What You Will Learn
- Grasp the basics of ROS and understand ROS applications
- Uncover how ROS-2 is different from ROS-1
- Handle complex robot tasks using state machines
- Communicate with multiple robots and collaborate to build apps with them
- Explore ROS capabilities with the latest embedded boards such as Tinker Board S and Jetson Nano
- Discover how machine learning and deep learning techniques are used with ROS
- Build a self-driving car powered by ROS
- Teleoperate your robot using Leap Motion and a VR headset

▶Key Features
- Create and program cool robotic projects using powerful ROS libraries
- Build industrial robots like mobile manipulators to handle complex tasks
- Learn how reinforcement learning and deep learning are used with ROS

▶Who This Book Is For
If you're a student, hobbyist, professional, or anyone with a passion for learning robotics and interested in learning about algorithms, motion control, and perception capabilities from scratch, this book is for you. This book is also ideal for anyone who wants to build a new product and for researchers to make the most of what's already available to create something new and innovative in the field of robotics.

목차

▶TABLE of CONTENTS
1. Getting Started with ROS
2. Introduction to ROS-2 and Its Capabilities
3. Building an Industrial Mobile Manipulator
4. Handling Complex Robot Tasks Using State Machines
5. Building an Industrial Application
6. Multi-Robot Collaboration
7. ROS on Embedded Platforms and Their Control
8. Reinforcement Learning and Robotics
9. Deep Learning Using ROS and TensorFlow
10. Creating a Self-Driving Car Using ROS
11. Teleoperating Robots Using a VR Headset and Leap Motion
12. Face Detection and Tracking Using ROS, OpenCV, and Dynamixel Servos

책 속으로

▶What this book covers
- Chapter 1, Getting Started with ROS, is a basic introductory chapter on ROS for beginners. This chapter will help you get an idea of the ROS software framework and its concepts.

- Chapter 2, Introduction to ROS-2 and Its Capabilities, introduces you to ROS-2, the newest upgraded framework that helps us use ROS in real-time applications. This chapter is organized in a similar manner to Chapter 1, Getting Started with ROS, such that users are able to differentiate between both ROS versions and understand their capabilities and limitations.

- Chapter 3, Building an Industrial Mobile Manipulator, is where you will learn how to build a mobile robot and a robot arm and combine them both to be used in a virtual environment and control them through ROS.

- Chapter 4, Handling Complex Robot Tasks Using State Machines, introduces you to techniques in ROS that could be adapted while using robots for continuous and complicated task management.

- Chapter 5, Building an Industrial Application, is where you will combine the skills acquired in Chapters 3, Building an Industrial Mobile Manipulator and Chapter 4, Handling Complex Robot Tasks Using State Machines, effectively, to create a user application. Here, we will demonstrate how to use the mobile manipulator to deliver products to houses in a neighborhood.

- Chapter 6, Multi-Robot Collaboration, teaches you how to communicate between multiple robots of the same or different category and control them separately and together in groups.

- Chapter 7, ROS on Embedded Platforms and Their Control, helps you understand the latest embedded controller and processor boards, such as STM32-based controllers, Tinker Board, Jetson Nano, and many more. We will also look at how to control their GPIOs via ROS and control them via voice-based commands through Alexa.

- Chapter 8, Reinforcement Learning and Robotics, introduces you to one of the most commonly used learning techniques in robotics called reinforcement learning. In this chapter, you will understand what reinforcement learning is and the math behind it using examples. Additionally, we will discover how to incorporate this learning technique with ROS by means of simple projects.

- Chapter 9, Deep Learning Using ROS and TensorFlow, is a project made using a trending technology in robotics. Using the TensorFlow library and ROS, we can implement interesting deep learning applications. You can implement image recognition using deep learning, and an application using SVM can be found in this chapter.

- Chapter 10, Creating a Self-Driving Car Using ROS, is one of the more interesting projects in this book. In this chapter, we will build a simulation of a self-driving car using ROS and Gazebo.

- Chapter 11, Teleoperating Robots Using a VR Headset and Leap Motion, shows you how to control a robot's actions using a VR headset and Leap Motion sensor. You can play around with VR, which is a trending technology these days.

- Chapter 12, Face Detection and Tracking Using ROS, OpenCV, and Dynamixel Servos, takes you through a cool project that you can make with ROS and the OpenCV library. This project basically creates a face tracker application in which your face will be tracked in such a way that the camera will always point to your face. We will use intelligent servos such as Dynamixel to rotate the robot on its axis.

출판사 서평

▶ Preface
Robot Operating System (ROS) is one of the most popular robotics middleware and is used by universities and industries for robot-specific applications. Ever since its introduction, many robots have been introduced to the market and users have been able to use them with ease within their applications. One of its main draws is its open source nature. ROS does not need a user to reinvent the wheel; instead, standardizing robot operations and applications is simple.

This book is an upgrade to the previous edition and introduces you to newer ROS packages, interesting projects, and some added features. This book targets projects in the latest (at the time of writing) ROS distribution―ROS Melodic Morenia with Ubuntu Bionic version 18.04.

Here, you will understand how robots are used in industries and will learn the step-by-step procedure of building heterogeneous robot solutions. Unlike the service call and action features in ROS, you will be introduced to cooler techniques that let robots handle intricate tasks in a smart way. This knowledge should pave the way to far more intelligent and selfperforming autonomous robots. Additionally, we will also introduce ROS-2, so you can learn the differences between this version and the previous ROS version and find help in choosing a specific middleware for your application.

Industries and research institutes are focusing primarily on the fields of computer vision and natural language processing. While the previous edition of this book introduced you to some simple vision applications such as object detection and face tracking, this edition will introduce you to one of the most widely used smart speaker platforms on the market, Amazon's Alexa, and how to control robots using it. In parallel, we will introduce new hardware, such as Nvidia Jetson, Asus Tinker Board, and BeagleBone Black and explore their capabilities with ROS.

While people may know how to control robots individually, one of the most common problems faced by users in the ROS community is the use of multiple robots working in synchronization, whether they are of the same type or not. This becomes complicated, as robots may follow similar topic names and may possibly lead to confusion in a sequence of operations. This book helps in highlighting the possible conflicts and suggests solutions.

This book also touches on reinforcement learning, including how it can be used with robotics and ROS. Furthermore, you will find the most interesting projects for building a self-driving car, deep learning with ROS, and building teleoperation solutions using VR headsets and Leap Motion, as they're currently trending and are being researched continuously.

작가정보

저자(글) Ramkumar Gandhinathan

Ramkumar is a roboticist and a researcher by profession. He started building robots since his sixth grade and has been into the robotics field for over 15 years through personal and professional connect. He has built, in person, over 80+ robots of different types. With an overall professional experience of 7 years (4 years full time and 3 years part-time/internship) in the robotics industry, he has ROS experience of 5 years. As a part of his professional career, he has built over 15+ industrial robot solutions using ROS. He also fascinates building drones and is a drone pilot by practice. His research interests and passion are towards the field of SLAM, motion planning, sensor fusion, multi-robot communication, and systems integration.

저자(글) Lentin Joseph

Lentin Joseph is an author, roboticist and robotics entrepreneur from India. He runs a robotics software company called Qbotics Labs in Kochi/Kerala. He has 8 years of experience in the robotics domain primarily in Robot Operating System, OpenCV, and PCL.He has authored several books in ROS, namely, Learning Robotics using Python first and second edition, Mastering ROS for Robotics Programming first and second edition, ROS Robotics Projects, and Robot Operating System for Absolute Beginners.He has pursued his Masters in Robotics and Automation from India and also worked at Robotics Institute, CMU, USA. He is also a TEDx speaker.