In the last decade, several international researchers have developed intelligent wheelchairs for disabled people. Many of these projects have founded their control structure on a sensor-referenced control. Many types of control are available in this area, but the final choice is in charge of the user. A previous work has established a behavior based control, multi agent based control, which ensures the best choice of the control in a given local context according to user's preferences. In fact, this control tries to merge the man and the machine, in order to make a symbiosis to make the machine easily acceptable and the control more efficient. In this paper another approach, based on this behavior based structure, tries to assist the user in a global way. Using a modeling of the more often used routes, the intelligent system will assist the user in navigation by proposing the next movement in the case of a recognized route. This will avoid a new direction definition for the user, which can be long and difficult according to the pathology.
[1]
Dr. James F. Smith.
Fuzzy Rule Determination By Coevolutionary Data Mining
,
2001
.
[2]
L. Rabiner,et al.
An introduction to hidden Markov models
,
1986,
IEEE ASSP Magazine.
[3]
Pierre Baldi,et al.
Hidden Markov Models in Molecular Biology: New Algorithms and Applications
,
1992,
NIPS.
[4]
L. Baum,et al.
A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
,
1970
.
[5]
M. Allouche.
Classification of Temporal Information in Situation Analysis
,
2001
.
[6]
Lawrence R. Rabiner,et al.
A tutorial on hidden Markov models and selected applications in speech recognition
,
1989,
Proc. IEEE.
[7]
M. Wozniak,et al.
Rule-based algorithms with learning for sequential recognition problem
,
2000,
Proceedings of the Third International Conference on Information Fusion.
[8]
Julian M. Kupiec,et al.
Robust part-of-speech tagging using a hidden Markov model
,
1992
.