An integrated epigenetic robot architecture via context-influenced long-term memory

Abstract

In this paper, we present a conceptual design for a context-influenced Long-Term Memory architecture. The notion of context is used as a means to organize the information flow between the Working Memory and Long-Term Memory components. In particular, we discuss the major influence of the notion of context within the Episodic Memory on the Semantic and Procedural Memory, respectively. In other words, we address how the occurrence of specific events in time impacts on the meaning of those events and the subsequent use of objects through robot actions. The general architecture design and its implementation in a simulated scenario are described. Such issues as memory items representation, individual structures of Long-Term Memory components, as well as memory-based recognition and item retrieval processes, are discussed in detail.