This paper introduces a new approach to robust path planning for mobile rob
ots entirely based on information from environment perception sensors. This
method avoids the use of odometry which leads to the accumulation of error
s resulting from the robot's position computing. We proceed as follows: we
create regions inside which the robot detects the same obstacle segments. A
node graph represents all the regions and their links. Then a planning alg
orithm is used to find a path which joins a start to a goal region. The fin
al stage consists in applying a robust robot motion control as regards the
uncertainties of the environment model. This approach contributes to a cont
rol system for indoor robots which is environment referenced. The sensors w
e deal with are first a continuous laser or ultrasonic scanning system, the
n a discrete ultrasonic belt whose limits of use we skew.