Some Applications in Robotics
In this section, we describe a method based on hidden Markov models for learning and recognizing places in an indoor environment by a mobile robot. Hidden Markov models have been used for a long time in pattern recognition, especially in speech recognition. Their main advantages over other methods (e.g. neural networks, ... ) are their capabilities to modelize noisy temporal signals of variable length.
KeywordsHide Markov Model Mobile Robot Optimal Policy Markov Decision Process Reward Function
Unable to display preview. Download preview PDF.
- [Laroche et al., 1999]Laroche, P., Charpillet, J., and Schott, R. (1999). Mobile Robotics Planning Using Abstract Markov Decision Processes. pages 299–306. ICTAI’99, IEEE.Google Scholar
- [Aycard et al., 1997a]Aycard, O., Charpillet, F., Fohr, D., and Mari, J.-F. (1997a). Place Learning and Recognition Using Hidden Markov Models. In Proceedings IEEE-RSJ on International Conference on Intelligent Robots and Systems, pages 1741 — 1746, Grenoble, France.Google Scholar
- [Aycard et al., 1998]Aycard, 0., Mari, J.-F., and Charpillet, F. (1998). Second Order Hidden Markov Models for Places Recognition: New Results. In proceedings of IEEE International Conference on Tools with Artificial Intelligence.Google Scholar