Abstraction and Multiple Abstraction in the Symbolic Modeling of the Environment of Mobile Robots

Except for pure reactive robots, that do not work with any explicit representation of their world [1], an intelligent robot must possess some symbolic representation of its environment in order to reason, plan (prediction), and perform efficiently (due to the intractable amount of subsymbolic information acquired from the real world). We have been working on that area during the last decade, in particular exploring the advantages of using abstraction and multiple abstraction for modeling the environment of a mobile robot. In this sense we have addressed the following main issues: – Automatic construction of the model. Assistive approaches (involving human operators) are possible [4] but limit the autonomy of the robot. – Automatic optimization (adaptation) of the model, for coping with the different situations that the robot may face during its operation without constructing an entirely new model each time from scratch. – Coherence between the symbols in the model and the real world. This must be addressed as a dynamic procedure since the real world changes continuously. –Efficiency in using the model. We believe that the best model for a given robot is the one that improves the most the robot's planning of operations. Up to now, we have been working on obtaining a comprehensive solution with abstraction as a basis for coping with all these issues at once. In the next we describe in more detail our solutions to each one.

[1]  Alessandro Saffiotti,et al.  An introduction to the anchoring problem , 2003, Robotics Auton. Syst..

[2]  Javier González,et al.  Multihierarchical Graph Search , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Cipriano Galindo,et al.  SELF-ADAPTATION OF THE SYMBOLIC WORLD MODEL OF A MOBILE ROBOT: AN EVOLUTION-BASED APPROACH , 2004 .

[4]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[5]  Cipriano Galindo,et al.  Improving efficiency in mobile robot task planning through world abstraction , 2004, IEEE Transactions on Robotics.

[6]  Javier González,et al.  Hierarchical graph search for mobile robot path planning , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[7]  Cipriano Galindo,et al.  Assistive navigation of a robotic wheelchair using a multihierarchical model of the environment , 2004, Integr. Comput. Aided Eng..