packtpublishing/artificial-intelligence-for-robotics

Artificial Intelligence for Robotics, published by Packt

Artificial Intelligence for Robotics

This is the code repository for Artificial Intelligence for Robotics, published by Packt.

Build intelligent robots that perform human tasks using AI techniques

What is this book about?

Artificial Intelligence for Robotics starts with an introduction to Robot Operating Systems (ROS), Python, robotic fundamentals, and the software and tools that are required to start out with robotics. You will learn robotics concepts that will be useful for making decisions, along with basic navigation skills.

This book covers the following exciting features:

• Get started with robotics and artificial intelligence
• Apply simulation techniques to give your robot an artificial personality
• Understand object recognition using neural networks and supervised learning techniques
• Pick up objects using genetic algorithms for manipulation
• Teach your robot to listen using NLP via an expert system

If you feel this book is for you, get your copy today!

Instructions and Navigations

All of the code is organized into folders. For example, Chapter02.

The code will look like the following:

Sudo apt-get install python-pip python-dev build-essential
Sudo pip install –upgrade pip

Following is what you need for this book:

If you have basic knowledge about robotics and want to build or enhance your existing robot’s intelligence, then Artificial Intelligence for Robotics is for you. This book is also for enthusiasts who want to gain knowledge of AI and robotics.

I've added wiring diagrams and some pictures of the electronics placement on the robot for fans of the book who are trying to duplicate TinMan the Robot. There is also arduino code in Chapter 1

With the following software and hardware list you can run all code files present in the book (Chapter 1-15).

Software and Hardware List

Chapter	Software required	OS required
1-2	ROS Kinetic Kame, VirtualBox 5.2.12, Python 2.2.7, Python 3.3.5	Windows, Ubuntu
4	Tensorflow 1.9.0, Keras,	Windows Python 3.3.5
6	Mycroft Picroft version, Google Voice Kit	Ubuntu
9	Eliza-Python	Windows, Ubuntu

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it.

Code in Action

Click on the following link to see the Code in Action: (http://bit.ly/2ohcbLg)

Related products

• Artificial Intelligence with Python [Packt] [Amazon]

• Mastering ROS for Robotics Programming - Second Edition [Packt] [Amazon]

Get to Know the Author

Francis X. Govers is an autonomous vehicle designer at Bell Helicopter Textron. He is the designer of 28 unmanned vehicles or robots for land, sea, air, and space, including RAMSEE, the autonomous security guard robot. Francis helped design the International Space Station, the F-35 JSF Fighter, the US Army Future Combat Systems, and systems for NASCAR and IndyCar. He is an engineer, pilot, author, musician, artist, and maker. He received five outstanding achievement awards from NASA and recognition from Scientific American for World Changing Ideas.

Suggestions and Feedback

Click here if you have any feedback or suggestions.

Download a free PDF

If you have already purchased a print or Kindle version of this book, you can get a DRM-free PDF version at no cost.
Simply click on the link to claim your free PDF.

https://packt.link/free-ebook/9781789950649

artificial-intelligence-for-robotics's Issues

The Chapter 4, what should I do when I get the CSV file?

I labeled the image and get the xml file,convert it into csv file ,after this i don't know what to do next, in
your code, i don't know where the csv file are mentioned, could you plz help me and solve my problem

request of robot-specfic ROS setting files. e.g. URDF

I have ordered the exact hardware and tried to following your path to create the same environment.
Could you share the ROS source/driver files? (e.g. ROS workspace)

AttributeError: 'module' object has no attribute '_TensorLike'

I was trying to compile chapter 4 code, I got the following error.

compiling CNN network...
Traceback (most recent call last):
File "trainTheCNN.py", line 127, in
cnNetwork = LeNet.build(width=128, height=128, depth=3, classes=2)
File "trainTheCNN.py", line 39, in build
input_shape=inputShape))
File "/usr/local/lib/python2.7/dist-packages/keras/engine/sequential.py", line 164, in add
layer(x)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/base_layer.py", line 414, in call
self.assert_input_compatibility(inputs)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/base_layer.py", line 279, in assert_input_compatibility
K.is_keras_tensor(x)
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 470, in is_keras_tensor
if not is_tensor(x):
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 478, in is_tensor
return isinstance(x, tf_ops._TensorLike) or tf_ops.is_dense_tensor_like(x)
AttributeError: 'module' object has no attribute '_TensorLike'

But After I upgraded tensorflow, I got the following issue:

Using TensorFlow backend.
Illegal instruction

can you please help me?
Thank you

could not find Book web page

Hi, I couldn't find the book web page mentioned in section 2:
http://github.com/fgovers/ai_and_robots ...
thx

Google AIY Voice Kit

Dear Sir,

Can I use Google AIY Voice Kit on UP board instead of Raspberry pi 3?

Best regards,
Thank you

Not Documented

Dear Sir,

I just followed all the hardware and software requirements , putting the robot all together as i buy was great but other components : how to connect Arduino Mega 2560 microcontroller and Pololu Micro Maestro Servo Controller x6? How to start the tests if everything is good. I have offline trained CNN for object detection so how we get the result back in to the robot .

Thanks ,

Qlearn Script not working as expected

Correct me if I'm wrong but it seems there is a typo in line 156 of the "armTrainingQlearn.py" and line 149 of the "armTrainingQlearn2.py" which causes the script to seem like it is learning but I do not think it is because fixing this "typo", thus
-changing: maxStat = thisStateQ
-to: maxState = thisStateQ

Causes the training to oscillate between just 2 and/ or sometimes 3 states out of the 27 states present in the Qmatrix.

Please help with a fix or at least share some more clarification as to why I am obtaining these results.
Thank you.

raspberry pi

can I use any board running ubuntu with ros ,without ubiquity, connected to an arduino board instead of using raspberry pi?

thank you,

best regards,
joe

Arduino codes

Dear Sir,

Can you please share the arduino files for a better follow up in your book?

thank you,

best regards,
Joe

Indexed Qlearning Script [armTrainingQlearnIndexed.py] contains foreign variables

Hello, I find it quite confusing and would like some clarification if any, as to why we are accessing the Qmatrix using an undefined index in line 178 of the script (armTrainingQlearnIndexed.py).
Are we doing this to deliberately to throw the exception? Or could someone tell me what is happening here?
Because changing "statQ" (which isn't defined anywhere) to "stat" (which maybe the intended variable) causes the training to output very different results.

This really is giving me a head spin.

How to deploy the reinforcement learning pickle file onto the robot?

I rewrote the reinforcement code to make it work and then save it as a pickle file as instructed. However, there is no further instruction how I should deploy the pickle file on the robot on the book. Can you please show me some hints or reference links for doing so?

Thanks
Tao