Escaping the Maze

Ezzat Leïla & Orthlieb Camille

June 2010

Signals, Instruments and Systems

Steps of the project

e-puck randomly placed in the environment

Reach a wall

Follow the wall reading the

frequency using the IR sensors

Link the found frequency and the

localization

Find the absolute localization

Move around the world to find the

final point

Description of the environment

• Simplification of the world

• E-puck turns always left

• E-puck follows the wall at equal distance

• Use of front and side sensors (0,2 and 5)

• Use of compass and GPS datas

• E-puck starts updating its position after a corner

Detection of changes of colors

• Response value sent after each time step

• Number of time steps stocked before each change of color

• Detection and storage of change of color

Link frequencies and location

Detect frequency

Update believed positions from

the corner

Deduce the wall

Know from which corner he starts

Find the good believed position

Like in maze…

• From a known position, find the final point – the maze’s escape

Effect of noise on the IR sensor• Front Sensor : to move and turn• 1% of noise doesn’t change

anything• 10% the robot can’t follow the wall

• Right sensor : to detect frequency• 30% of noise doesn’t affect the

measures• 50% doesn’t detect any change

of color

The movie

Conclusion

• Main objectives reached

• Our findings have to be improved in order to escape a real maze • Make a code enought flexible to reproduce

many times the lecture of frequencies and update positions

• Revise the stability of the detect values

• Face more random situations

• Appreciations