Automatic goal allocation for a planetary rover with DSmT

In this chapter, we propose an approach for assigning aninterest level to the goals of a planetary rover. Assigning an interest level to goals, allows the rover to autonomously transform and reallocate the goals. The interest level is defined by data-fusing payload and navigation information. The fusion yields an 'interest map',that quantifies the level of interest of each area around the rover. In this way the planner can choose the most interesting scientific objectives to be analysed, with limited human intervention, and reallocates its goals autonomously. The Dezert-Smarandache Theory of Plausible and Paradoxical Reasoning was used for information fusion: this theory allows dealing with vague and conflicting data. In particular, it allows us to directly model the behaviour of the scientists that have to evaluate the relevance of a particular set of goals. This chaptershows an application of the proposed approach to the generation of a reliable interest map.

[1]  Lucien Wald,et al.  Some terms of reference in data fusion , 1999, IEEE Trans. Geosci. Remote. Sens..

[2]  Mauro Massari,et al.  A non-deterministic planner for planetary rover autonomy , 2006 .

[3]  Jean Dezert,et al.  Foundations for a new theory of plausible and paradoxical reasoning , 2002 .

[4]  L. Hubert-Moy,et al.  Land cover change prediction with a new theory of plausible and paradoxical reasoning , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[5]  Albena Tchamova,et al.  Estimation of target behavior tendencies using dezert-smarandache theory , 2003, Sixth International Conference of Information Fusion, 2003. Proceedings of the.

[6]  Jürgen Schmidhuber,et al.  Artificial curiosity based on discovering novel algorithmic predictability through coevolution , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[7]  Steve Hanks,et al.  Optimal Planning with a Goal-directed Utility Model , 1994, AIPS.

[8]  Eugene Fink,et al.  Integrating planning and learning: the PRODIGY architecture , 1995, J. Exp. Theor. Artif. Intell..

[9]  Massimiliano Vasile,et al.  WISDOM: An Advanced Intelligent, Fault-Tolerant System for Autonomy in Risky Environments , 2006 .

[10]  Martial Hebert,et al.  A complete navigation system for goal acquisition in unknown environments , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[11]  Manuela Veloso,et al.  Goal Transformations in Continuous Planning , 1998 .