My Thesis Subject

In order to handle very different types of tasks and objects involved in robotics, a GeNeric Object ModEl (GNOME) has been developed. For example, one could want to model spare parts in an assembly line in the context of their assembly, or a robot's environment for the purpose of navigation. For a particular task and a particular agent performing the task, a given object has a particular representation (an instance of the model). But the model itself is independent of the task and the agent. This allows a change of representation when the task or the agent changes.

GNOME is a multiple-level model to represent objects through their various attributes (geometry, colour, texture, density, etc.). Each attribute is represented independently of the others by a tree of hierarchical decomposition of attribute-objects (objects defined in the attribute's representation space), and by a graph representing relations between these attribute-objects, e.g. connections, relative pose, etc. The set of all trees and graphs for all attributes constitutes the object's structure.

Each attribute-object and relation can be quantified by an application. The application's equation of an attribute-object's quantification specifies the shape (e.g. a cube or a sphere), while values of the equation's parameters specify the dimensions (e.g. the side or the radius). Quantifying the relations consist in appointing a function to the relations' graph which indicates the relations and their quantification for each graph's arc: this gives a labeled graph. The set of all the quantifications (of the attribute-objects and relations) constitutes the object's quantification.

Up to now, the attributes have been represented independently, but they are in fact not independent, and inter-attribute relations must be introduced. Since these relations can be quantified, they are represented by a labeled graph. One example of such a relation is correspondence. This relation gives, for example, the color (through color attribute-objects) of the different geometrical parts of the object (through geometry attribute-objects).

Due to the model's modularity and the data structures (graphs and trees) chosen, a representation can easily be modified when it is not appropriate anymore (e.g. because of a change of task or agent). Moreover, some information present in the current representation can be used for the new one. Only new attributes require new measures.

A formalisation of GNOME can be found in [LHC96] as well as a simple example: a car representation for, e.g., a recognition task.

A poster (in French) describes this work.

As an example, we have developed a mine model.