We present a novel approach of active object categorization based on an iterative Bayesian method using capacitive sensing during object manipulation. The approach uses a novel type of capacitive sensor, which can measure internal properties of materials that are inaccessible to vision or tactile sensing. The electrodes of this capacitive sensor are sufficiently flexible and thin to be attached...

The problem of grasping is widely studied in the robotics community. This project focuses on the identification of object graspable features using images and object structural information. The primary aim is the creation of a framework in which the information gathered by the vision system can be integrated with automatically generated knowledge, modelled by means of fuzzy description logics.

Recent work in robotic manipulation focuses on object retrieval cluttered spaces under occlusion. Nevertheless, the majority of efforts lack an analysis conditions for completeness approaches or methods apply only when objects can be removed from workspace. This formulates general, occlusion-aware task, and safe reconstruction a confined space with in-place rearrangement. It proposes framework ...