A Knowledge-Based Approach to Robotic Perception Using Unstructured Information Management

In order to achieve a human-like skill level in manipulation, autonomous robots that perform everyday manipulation tasks require perception capabilities that go beyond recognition delivered by single perception algorithms. In previous work we have presented RO-BOSHERLOCK, an ensemble-based, knowledge driven robotic perception system and OPENEASE an online framework for knowledge representation and reasoning. We propose to demonstrate, by combining these two frameworks, how knowledge processing can boosts the perception capabilities of a robotic agent performing household chores.