Braitenberg Vehicles
This example demonstrates a Braitenberg vehicle discussed in chapter 6 of the book. The example presented here is a version of the vehicle 2c presented in the book. The simulation below recreates the performance of the actual robot using the same control architecture.
The control architecture
The control architecture of the agent is similar to vehicles 2c, except that it has two types of sensors. There are two proximity sensors (shaded boxes in the figure below) and two light sensors (white boxes). The sensors are directly connected the to the motors, as the figure shows.
The proximity sensor on the left side is connected via excitatory (positive) link to the left motor and an inhibitory (negative) link to the right motor. The opposite is the case for the sensor on the right side. Due to this connection arrangement, the left motor will rotate faster when the robot approaches an obstacle on its left side and as a result it will finally avoid it.
The light sensors are connected in a similar way but this time the polarity of the connections is reversed. As a result the agent will approach light sources rather than avoid them.
Go ahead,
In the JAVA based simulator the performance of the real Khepera robot is simulated. The Khepera robot used 8 eight IR sensors for detecting obstacles. The simulated robot also has eight such sensors which can be seen indicated as rays extending from the robots center. To stay thought close to the original vehicle 2c only two sensors (one on each side of the simulated robot are used). The length of these rays indicate the sensor range. The green polygons are objects which can be detected by these sensors.
To gain a further understanding of the control architecture you can view
Implementation issues
The source code has been implemented and tested on the Khepera robot without any particular problems.
- Copyright 1999 Dimitrios Lambrinos..
- Do you have any comments about this site? Please drop us a line at lambri@ifi.unizh.ch
