Posts Tagged ‘autonomous obstacle avoidance’

Kinect Car

 

 

De’Ranged Bot from Kazi Murtaza.

My FYP, just started

hello hi, as this is my final semester in my university Szabist doing Bs-Computing, and my final year project is Autonomous Obstacle Detection And Avoidance on Scaled Car Model, yes its a mouth full,
my objective is;

  • Navigating System, which controls the car for autonomous obstacle avoidance
  • System, Flexible enough to be implementing on other robots, or future projects.

Using state of art Technology Like; Kinect for computer vision, micro controllers  like; Raspberry Pi, Netduino and Arduino this could never be easier, achieving this goal is challenging but possible, this will be an interesting project at least. My basic draft concept at this point is;  a robot using four-wheeled, deferentially steered, The base of the robot is almost rectangular, The robot is equipped with two batteries, each 30 Ah 12 V, supplying the robot and the Kinect sensor with power. Besides the Kinect sensor, the robot is also equipped with range sensors. Four analogous SHARP IR sensors, GP2Y0A21YK, two placed in the robot’s direction of heading and the other two pointing in the opposite direction. In addition, the robot is equipped with two digital ultrasonic Maxsonar EZ1 from MaxBotix pointing forward. The IR and ultrasonic sensors are used for emergency situations only, bypassing the navigation system by braking the motors in case the risk of collision is imminent. The robot is equipped with four microcontrollers. Two of the microcontrollers read wheel encoder values and control the rotational speed of the two motors. The third microcontroller controls the power supply and monitors the charging of the batteries. The fourth microcontroller handles communication between the other controllers as well as processing of sensor input from the IR and ultrasonic sensors. It also handles the communication between the robot and the laptop running the navigation system. The robot and the Kinect sensor are connected via USB to the laptop placed on top of the robot.

So far what I have achieved is installed Kinect on my Machine for testing the steps I followed were listed at this site here; but I guess the steps were not updated and there is difference at some points, which I will list down below.

Step 0

Uninstall any previews drivers, such as CLNUI. Look at the end of this post if you want to see how you can have multiple drivers installed.

Step 1

  • Download Kinect Drivers and unzip.
  • Open the unzipped folder and navigate to Platform/Win32/Driver.
  • Run dpinst-x86.exe (if you have a 32-bit processor) or dpinst-amd64.exe (if you have a 64-bit processor).

Step 2

Download and install the latest stable or unstable OpenNI Binaries from OpenNI website.

the link in step is a 404 and you should go and install OPENNI SDK v1.5.4.0 from here

Step 3

Download and install the latest stable or unstable OpenNI Compliant Middleware Binaries (NITE) from OpenNI website.

again the is 404 and you should go and install NiTE v1.5.2.2.1 from here (scroll to bottom of the page you will see), guide also stated that it will require a PrimeSense key: 0KOIk2JeIBYClPWVnMoRKn5cdY4= , which it did not.

Step 4

Download and install the latest stable or unstable OpenNI Compliant Hardware Binaries from OpenNI website.
Both stable and unstable releases have worked for me. If you have trouble installing the unstable releases, just try the stable ones.

again 404, go here and install OpenNI-Compliant Sensor Driver v5.1.2.1

Step 5

  • Plug in your Kinect device and connect its USB port with your PC.
  • Wait until the driver software is found and applied.
  • Navigate to the Device Manager (Control Panel). You should see something like the following:

Kinect in the Device Manager window
You are nearly done.below steps were accurate;

Step 6

  • Download the KinectXMLs file and unzip. The extracted folders contain totally four XML files which are going to replace the ones OpenNI installed (the XMLs I provide simply contain the license key and the correct Kinect camera resolution).
  • Navigate to KinectXMLs\OpenNI folder and copy the SampleConfig.xml file. Navigate to C:\Program Files\OpenNI\Data (if you have a 32-bit processor) or C:\Program Files (x86)\OpenNI\Data (if you have a 64-bit processor) and replace SampleConfig.xml with the one you copied.
  • Navigate to KinectXMLs\NITE folder and copy the Sample-Scene.xml, Sample-Tracking.xml and Sample-User.xml files. Navigate to C:\Program Files\Prime Sense\NITE\Data (if you have a 32-bit processor) or C:\Program Files (x86)\Prime Sense\NITE\Data (if you have a 64-bit processor) and replace Sample-Scene.xml, Sample-Tracking.xml and Sample-User.xml with the ones you copied.

Step 7

Navigate to C:\Program Files\OpenNI\Samples\Bin\Release (or C:\Program Files (x86)\OpenNI\Samples\Bin\Release) and try out the existing demo applications. Try the demos found in C:\Program Files\Prime Sense\NITE\Samples\Bin\Release (or C:\Program Files (x86)\Prime Sense\NITE\Samples\Bin\Release), too. If they work properly, then you are done! Congratulations!

If they do not work, make sure that you have replaced the XML files I mentioned in step 5 with the ones I provided you. If the demos still do not work, try installing the stable version of OpenNI, middleware and hardware binaries. Personally, I have successfully installed OpenNI and NITE (both stable and unstable releases) in a 32-bit desktop and a 64-bit laptop following the methodology I described.

Step 8

You have successfully installed Kinect in your Windows PC! Read the documentation and familiarize yourself with the OpenNI and NITE API. You’ll find the proper assemblies in:

  • C:\Program Files\OpenNI\Bin (or C:\Program Files (x86)\OpenNI\Bin) and
  • C:\Program Files\Prime Sense\NITE\Bin (or C:\Program Files (x86)\Prime Sense\NITE\Bin)

OpenNI is the primary assembly you’ll need when developing Natural User Interfaces applications.

C# tutorials on using the managed OpenNI.net libraries coming soon! Stay tuned in this blog.

 
Original credit goes to, Software Developer Vangos Pterneas, a student of the Athens University of Economics and Business, Department of Informatics. This guide and any associated source codes and files is licensed under The Code Project website and also under the Code Project Open License. I wish to share this article to educate the Kinect community on how to install the Kinect to their Personal Computers. By doing so, we would like to advocate and promote the development of programs by developers worldwide.