Ubuntu on Beagleboard XM

Nearly after a year of hiatus, I started my work on robotics once again. I just finished the installation of Ubuntu 10.10 build on Beagleboard XM board. I will upload an image soon to make you believe that I really did it ;-)

I followed the instructions available at this wikipedia site and it worked for me without any hiccups. I collected few information before deciding to go for Ubuntu for Beagleboard. Even though it has a slow graphics compared to Angstrom or Android, Ubuntu is supported by a large repository of packages which makes life easier while installing softwares like opencv.  My next task is to install OpenCV on it.

When you first boot from the SD-Card image, you get a login prompt on the terminal. Use following login information:

login: ubuntu
password: temppwd

After you finish installing the desktop environment (xfce), it again presents you with a login prompt (GUI screen). This time click on the Demo User and type "temppwd" as the password.

One more thing: My ethernet lan port is detected as usb1 rather than eth0. In order to configure your network do the following:

$ sudo dhclient usb1

I think you need to execute this command every time you restart the system.

Testing Latex

\int_{0}^{1}\frac{x^{4}\left(1-x\right)^{4}}{1+x^{2}}dx
=\frac{22}{7}-\pi

My first SBC : RB-100 Vortex86DX

I recently got a single board computer (SBC) called RB-100 with a Vortex86DX from RobotShop. It can operated with a 6V - 24 V battery. I suggest you to get the RoBoard Starter Kit that includes a video card   (Mini PCI - VGA-Z9S) and cables necessary for connecting devices like mouse, keyboard and a monitor.  Video card is necessary for connecting a monitor to the board so that we can monitor the installation processes. Also download various manuals (hardware, software) from above links. The one tutorial which I found extremely useful and the one which worked for me is available here.  In case this link does not work, then try this. You also need to download the modified Debian kernel for Vortex86D processor from this link.  The adjacent image shows the picture of the RB-100 SBC board without a video card and without any peripherals.

The next figure shows the peripherals connected to this board. This includes an USB mouse, an USB keyboard, a terminal, a LAN terminal and a 6V battery. It also shows the graphics card connected to its MINI PCI slot. The complete set up in the last picture below. I hope these pictures give you a feel about how to get started with this SBC. Because, when I started I was confused about how to put things together. I suggest you to go through the hardware manual that is available at RobotShop's site.

James McLurkin

• His personal homepage.
• His profile on Nova.
• An interesting article on Intelligent Life based on his talk at Kentucky.
• Another Article on a blog about his work on Swarm Robotics.
• Finally, his page on Wikipedia.
  

My First robot with Arduino

This is my first robot with Arduino Mega boards. The body of the robot is made with the components of RobotDesigner kit (Japan Robotech Ltd.) This includes wheels (motors), IR sensors and the body. Here we use an array of 6 IR sensors to avoid obstacles on its path. Arduino MEGA provides 16 Analog input pins and 13 PWM outputs which can be used to drive motors. We use Toshiba TA7291AP full-bridge driver to drive the dc motors. It can give an output current of 1A and can provide forward and reverse rotations. We use two battery supply for this robot. One for powering the Arduino board and the other one for driving the motors.
The one thing I must mention here is that I could assemble and program the entire thing only because of the help that I received from my labmate Mr. Asuki Kohno, who is a final year under-graduate student in our lab. He is very good at these things.

I recently modified the design. The new one makes use of a caterpillar track that enables it to move over things like wires, cotton, threads and other soft  objects lying on the ground. Putting caterpillar track on to the robot took some time. Its because we are not using an off-the-shelf caterpillar module. That would have saved our time, but these are not readily available. I mean you need to order from abroad. We could get hold of "Tamiya Track kit" to build our own caterpillar system. It costs only $10 to get one such kit. But one has to align the wheels and mount them on his robot properly so that the track does not slip over the wheel etc. A better one with its own frame to house caterpillar track may cost little higher. For instance, RP5 track chassis costs around $50.

Swarm Robots and Data Mining

My current work is about extracting some "Higher Knowledge" using Data Mining on the log data collect from external sensors like a camera. Before going any further, let me tell you about the kind of robots I am using here.

1. The price of one robot is around 20K JPY or US$ 200. 
2. It runs on a 6V battery. It has two motors to control its motion.
3. It uses only 3 IR sensors to detect obstacles.
4. There is no way, we can store on-board signals (for instance, IR readings) and analyse it off-line using a computer. 
5. It does not have any communication capabilities (like wireless, radio or blue tooth) with which it can communicate with other agents or with a central computer.

Hence the controller design completely depends on the designer who 'observes' the robot behaviour during its motion (say using his eyes, or a camera) and then based on his understanding, he modifies the controller to improve its performance  while achieving certain goals.

Now, our purpose is to build a system, where behaviour of several robots are analysed using data mining methods and useful hints are derived which could be used by the designer to improve the controller. The story is like this ...

A designer (a person) writes an algorithm for the swarm robots to perform a task and then goes away at night for sleep. During his absence, robot behaviour is recorded through an external sensory system (say multiple camera system in a building).  An autonomous data mining system (ADMS) analyses these logs and finds out if any robot manifested any kind of anomalous behaviour. It also enumerates the possible causes for such a behaviour and suggests some improvements that could be incorporated to overcome this anomaly. So in the morning, the designer comes back and analyses the results. He either incorporates the suggestion made by the ADMS in improving the controller or rejects its suggestions. 

This sounds more like science fiction at this stage. However, we have just started working on it ... Following video shows the motion of 4 robots which have been programmed to avoid obstacles (walls or other agents) while navigating the workspace. In this task, the robots are to be designed to increase the patrol rate which is the rate at which robot explores the workspace.

Making your own Swarm Robot ... where to start.

Many labs in big universities make their own robots. For instance, S-bot (Swarm-bot) is being developed and maintained by LIS at EPFL. Here I would list  few commercial companies which provide you cheaper ready-to-use components to build your own robots :

1. Lego Mindstorm Nxt 2.0. The third party C interface could be obtained easily. Mindstorm Nxt 2.0 provides advanced capabilities like bluetooth or wireless communication, color detection.

2. Robot Designer by Japan Robotech Ltd. One of the good thing about this product is that they provide an integrated development environment for writting codes in C which can transferred on to robot by serial port. So, complicated algorithms can be implemented on it.However, it can not support more than 5 sensor inputs.


With Arduino boards, the capabilities of your robot could be increased to a great extent.For instance, it can support nearly 50 sensors ( I need to check this one, though!)

With time, I would try to update this information ....