I put together a new robot using Dynamixel AX-12+ servos and
I wanted to test an algorithm for tracking a moving object.
The camera being used is a DLink 920 wireless operating
over 802.11g and the visual tracking is done using
RoboRealm. All processing is done on my desktop PC. The
full writeup can be found here:
This video demonstrates learning by example in an
artificial neural network that controls the motion of a
mobile robot. The robot uses four sonar sensors and three IR
sensors to detect the ranges to nearby objects. A wireless
controller is used to initially remote control the robot
past some test objects while the robot records the sensor
readings and motor control signals. This data is then used
to train a 2x7 artificial neural network (2 motors and 7
sensors). Once the network is trained, it is used to control
the robot without intervention from the operator.
This is a followup to my earlier post describing the use of
a simple neural network to control a light following robot.
In the original demonstration, the connections between input
and output neurons were hard coded with values that were
known to steer the robot in the right way. In the current
demonstration, the neural network is initialized with random
connections and the correct behavior has to be learned.
In the video below, the robot begins with a random 2x2
neural network for controlling the motors based on the
values of the two light sensors mounted on the front. A
supervised learning algorithm employing the Delta Rule is
used to train the network by utilizing a known solution to
provide the teaching signals five times per second. At the
beginning of the video, you can see that the robot turns
away from the light and even goes backward. However, within
10-15 seconds, the network is already sufficiently trained
to follow the light beam.
I just finished up a little demo regarding the use of a
simple artificial neural network (ANN) to control a mobile
robot. The demonstration is only meant to introduce the
concepts and terminology of neural nets rather than being
something particularly useful. Also, this blog entry does
not deal with *learning* in ANN's which is what they are
most famous for. That will be the topic of a forthcoming
blog entry and demo.
Here is the link to the report. If you get bored
math at the beginning, you can scroll down toward the end
where there is a Youtube video demonstrating the robot in
I have been working recently on an omnidirectional vision
system for a mobile robot. My latest results involve using
the system for obstacle avoidance and navigation. You can
find an explanation and a few short videos at: