Integrated multimedia understanding for ubiquitous intelligence based on mental image directed semantic theory

An ideal ubiquitous computing environment can be a network system of such intelligent and human-friendly robots that never appear in front of humans except when needed. In this paper the distributed intelligent robot network (DIRN) is proposed as one kind of wireless sensor and actor networks (WSAN) consisting of one brain node and numerous sensor and actor nodes with human-friendly interfaces. In order to realize well-coordinated DIRNs, it is very important to develop a systematically computable knowledge representation language universal for any kind of device as well as efficient networking technologies. As a candidate for this purpose, the multimedia description language L-md was evaluated by applying it to simulation of DIRN-world interaction.