Efficient knowledge representation in intelligent human-robot co-operation

With the spreading of intelligent machines, manmachine co-operation has become an important research area. Today, intelligent robots collaborating with humans usually have to be able to store, retrieve, and update information about their environment, interpret and execute commands, offer existing and gain/learn new services. In these processes, the efficient knowledge representation and storage are of key importance. In this paper, a new graph based knowledge storage and representation form is introduced which distinguishes between theoretical knowledge and linkage-possibilities among virtual tools and their real-word embodiments. The proposed modular structure makes easy to store, retrieve, modify, and extend theoretical and practical knowledge, to interpret commands and to associate them with physical means and actions, to adapt to changes, learn and build in new knowledge. These aspects are especially important when the robots are involved in human-robot communication, as well.