Enhancing Action Execution by Using Spatial Relational Knowledge

Robots, which are able to carry out their tasks robustly in real world environments, are not only desirable but necessary if we want them to be more welcome for a wider audience. But very often they may fail to execute their actions successfully because of insufficient information about behaviour of objects used in the actions. In this article we propose an approach to avoid the unsuccessful completion of robot’s actions by more careful description of them. This description characterises the expected behaviour of the objects in both states before as well as after the execution of an action. The description of each state consists of conjunction of a set of spatial relations between the objects. Each of these relations captures the different aspect of the object in the corresponding states. In addition, we present how by the case of the simulation these aspects can be extended and improved autonomously.