Book Image

ROS Robotics Projects

Book Image

ROS Robotics Projects

Overview of this book

Robot Operating System is one of the most widely used software frameworks for robotic research and for companies to model, simulate, and prototype robots. Applying your knowledge of ROS to actual robotics is much more difficult than people realize, but this title will give you what you need to create your own robotics in no time! This book is packed with over 14 ROS robotics projects that can be prototyped without requiring a lot of hardware. The book starts with an introduction of ROS and its installation procedure. After discussing the basics, you’ll be taken 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 ROS robotics applications for beginner, intermediate, and expert levels inside! This book will be the perfect companion for a robotics enthusiast who really wants to do something big in the field.
Table of Contents (20 chapters)
ROS Robotics Projects
Credits
About the Author
Acknowledgements
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface

Image recognition using ROS and TensorFlow


After discussing the basics of TensorFlow, let's start discussing how to interface ROS and TensorFlow to do some serious work. In this section, we are going to deal with image recognition using these two.

There is a simple package to perform image recognition using TensorFlow and ROS. Here is the ROS package to do this:

https://github.com/qboticslabs/rostensorflow

This package was forked from https://github.com/OTL/rostensorflow. The package basically contains a ROS Python node that subscribes to images from the ROS webcam driver and performs image recognition using TensorFlow APIs. The node will print the detected object and its probability.

Note

This code was developed using TensorFlow tutorials from the following link: https://www.tensorflow.org/versions/r0.11/tutorials/image_recognition/index.html.

The image recognition is mainly done using a model called deep convolution network. It can achieve high accuracy in the field of image recognition. An...