Artificial Vision and Language Processing for Robotics

图书信息

作者	Álvaro Morena Alberola
出版社	Packt Publishing
ISBN	9781838557669
出版时间	2019-04-30
字数	484.5万
分类	进口书,外文原版书,电脑,网络

读书简介

Create end-to-end systems that can power robots with artificial vision and deep learning techniques Key Features * Study ROS, the main development framework for robotics, in detail * Learn all about convolutional neural networks, recurrent neural networks, and robotics * Create a chatbot to interact with the robot Book Description Artificial Vision and Language Processing for Robotics begins by discussing the theory behind robots. You'll compare different methods used to work with robots and explore computer vision, its algorithms, and limits. You'll then learn how to control the robot with natural language processing commands. You'll study Word2Vec and GloVe embedding techniques, non-numeric data, recurrent neural network (RNNs), and their advanced models. You'll create a simple Word2Vec model with Keras, as well as build a convolutional neural network (CNN) and improve it with data augmentation and transfer learning. You'll study the ROS and build a conversational agent to manage your robot. You'll also integrate your agent with the ROS and convert an image to text and text to speech. You'll learn to build an object recognition system using a video. By the end of this book, you'll have the skills you need to build a functional application that can integrate with a ROS to extract useful information about your environment. What you will learn * Explore the ROS and build a basic robotic system * Understand the architecture of neural networks * Identify conversation intents with NLP techniques * Learn and use the embedding with Word2Vec and GloVe * Build a basic CNN and improve it using generative models * Use deep learning to implement artificial intelligence(AI)and object recognition * Develop a simple object recognition system using CNNs * Integrate AI with ROS to enable your robot to recognize objects Who this book is for Artificial Vision and Language Processing for Robotics is for robotics engineers who want to learn how to integrate computer vision and deep learning techniques to create complete robotic systems. It will prove beneficial to you if you have working knowledge of Python and a background in deep learning. Knowledge of the ROS is a plus.

目录

Preface

About the Book

About the Authors

Objectives

Audience

Approach

Minimum Hardware Requirements

Software Requirements

Conventions

Installation and Setup

Additional Resources

Chapter 1

Fundamentals of Robotics

Introduction

History of Robotics

Artificial Intelligence

Natural Language Processing

Computer Vision

Types of Robots

Industrial Robots

Service Robots

Hardware and Software of Robots

Robot Positioning

Exercise 1: Computing a Robot’s Position

How to Work with Robots

Exercise 2: Computing the Distance Traveled by a Wheel with Python

Exercise 3: Computing Final Position with Python

Activity 1: Robot Positioning Using Odometry with Python

Summary

Chapter 2

Introduction to Computer Vision

Introduction

Basic Algorithms in Computer Vision

Image Terminology

OpenCV

Basic Image Processing Algorithms

Thresholding

Exercise 4: Applying Various Thresholds to an Image

Morphological Transformations

Exercise 5: Applying the Various Morphological Transformations to an Image

Blurring (Smoothing)

Exercise 6: Applying the Various Blurring Methods to an Image

Exercise 7: Loading an Image and Applying the Learned Methods

Introduction to Machine Learning

Decision Trees and Boosting Algorithms

Bagging:

Boosting

Exercise 8: Predicting Numbers Using the Decision Tree, Random Forest, and AdaBoost Algorithms

Artificial Neural Networks (ANNs)

Exercise 9: Building Your First Neural Network

Activity 2: Classify 10 Types of Clothes from the Fashion-MNIST Database

Summary

Chapter 3

Fundamentals of Natural Language Processing

Introduction

Natural Language Processing

Parts of NLP

Levels of NLP

NLP in Python

Natural Language Toolkit (NLTK)

Exercise 10: Introduction to NLTK

spaCy

Exercise 11: Introduction to spaCy

Topic Modeling

Term Frequency – Inverse Document Frequency (TF-IDF)

Latent Semantic Analysis (LSA)

Exercise 12: Topic Modeling in Python

Activity 3: Process a Corpus

Language Modeling

Introduction to Language Models

The Bigram Model

N-gram Model

Calculating Probabilities

Exercise 13: Create a Bigram Model

Summary

Chapter 4

Neural Networks with NLP

Introduction

Recurrent Neural Networks

Introduction to Recurrent Neural Networks (RNN)

Inside Recurrent Neural Networks

RNN architectures

Long-Dependency Problem

Exercise 14: Predict House Prices with an RNN

Long Short-Term Memory

Exercise 15: Predict the Next Solution of a Mathematical Function

Neural Language Models

Introduction to Neural Language Models

RNN Language Model

Exercise 16: Encoding a Small Corpus

The Input Dimensions of RNNs

Activity 4: Predict the Next Character in a Sequence

Summary

Chapter 5

Convolutional Neural Networks for Computer Vision

Introduction

Fundamentals of CNNs

Building Your First CNN

Exercise 17: Building a CNN

Improving Your Model - Data Augmentation

Exercise 18: Improving Models Using Data Augmentation

Activity 5: Making Use of Data Augmentation to Classify correctly Images of Flowers

State-of-the-Art Models - Transfer Learning

Exercise 19: Classifying €5 and €20 Bills Using Transfer Learning with Very Little Data

Summary

Chapter 6

Robot Operating System (ROS)

Introduction

ROS Concepts

ROS Commands

Installation and Configuration

Catkin Workspaces and Packages

Publishers and Subscribers

Exercise 20: Publishing and Subscribing

Exercise 21: Publishers and Subscribers

Simulators

Exercise 22: The Turtlebot configuration

Exercise 23: Simulators and Sensors

Activity 6: Simulators and Sensors

Summary

Chapter 7

Build a Text-Based Dialogue System (Chatbot)

Introduction

Word Representation in Vector Space

Word Embeddings

Cosine Similarity

Word2Vec

Problems with Word2Vec

Gensim

Exercise 24: Creation of a Word Embedding

Global Vectors (GloVe)

Exercise 25: Using a Pretrained GloVe to See the Distribution of Words in a Plane

Dialogue Systems

Tools for Developing Chatbots

Types of Conversational Agents

Classification by Input-Output Data Type

Classification by System Knowledge

Creation of a Text-Based Dialogue System

Exercise 26: Create Your First Conversational Agent

Activity 7: Create a Conversational Agent to Control a Robot

Summary

Chapter 8

Object Recognition to Guide a Robot Using CNNs

Introduction

Multiple Object Recognition and Detection

Exercise 24: Building Your First Multiple Object Detection and Recognition Algorithm

ImageAI

Multiple Object Recognition and Detection in Video

Activity 8: Multiple Object Detection and Recognition in Video

Summary

Chapter 9

Computer Vision for Robotics

Introduction

Darknet

Basic Installation of Darknet

YOLO

First Steps in Image Classification with YOLO

YOLO on a Webcam

Exercise 28: Programming with YOLO

ROS Integration

Exercise 29: ROS and YOLO Integration

Activity 9: A Robotic Security Guard

Summary

Appendix

Chapter 1: Fundamentals of Robotics

Activity 1: Robot Positioning Using Odometry with Python

Chapter 2: Introduction to Computer Vision

Activity 2: Classify 10 Types of Clothes from the Fashion-MNIST Data

Chapter 3: Fundamentals of Natural Language Processing

Activity 3: Process a Corpus

Chapter 4: Neural Networks with NLP

Activity 4: Predict the Next Character in a Sequence

Chapter 5: Convolutional Neural Networks for Computer Vision

Activity 5: Making Use of Data Augmentation to Classify correctly Images of Flowers

Chapter 6: Robot Operating System (ROS)

Activity 6: Simulators and Sensor

Chapter 7: Build a Text-Based Dialogue System (Chatbot)

Activity 7: Create a Conversational Agent to Control a Robot

Chapter 8: Object Recognition to Guide a Robot Using CNNs

Activity 8: Multiple Object Detection and Recognition in Video

Chapter 9: Computer Vision for Robotics

Activity 9: A Robotic Security Guard