In the context of cognitive architectures, memory is typically considered as a passive storage device with the sole purpose of maintaining and retrieving information relevant to ongoing cognitive processing. If memory is instead considered to be a fundamentally active aspect of cognition, as increasingly suggested by empirically-derived neurophysiological theory, this passive role must be reinterpreted. In this perspective, memory is the distributed substrate of cognition, forming the foundation for cross-modal priming, and hence soft cross-modal coordination. This paper seeks to describe what a cognitive architecture based on this perspective must involve, and initiates an exploration into how human-level cognitive competencies (namely episodic memory, word label conjunction learning, and social behaviour) can be accounted for in such a low-level framework. This proposal of a memory-centred cognitive architecture presents new insights into the nature of cognition, with benefits for computational implementations such as generality and robustness that have only begun to be exploited.
LIDA's architecture and mechanisms were inspired by a variety of computational paradigms and LIDA implements the Global Workspace Theory of consciousness. The LIDA architecture's cognitive modules include perceptual associative memory, episodic memory, functional consciousness, procedural memory and action-selection. Cognitive robots and software agents controlled by the LIDA architecture will be capable of multiple learning mechanisms. With artificial feelings and emotions as primary motivators and learning facilitators, such systems will'live' through a developmental period during which they will learn in multiple, humanlike ways to act effectively in their environments. We also provide a comparison of the LIDA model with other models of consciousness. LIDA implements Global Workspace Theory (GWT) (Baars 1988; 1997), which has become the most widely accepted psychological and neurobiological theory of consciousness (Baars 2002; Dehaene & Naccache 2001; Kanwisher 2001). In the process of implementing GWT, the LIDA model also implements imagination in the form of deliberation as a means of action selection (Franklin 2000a; Sloman 1999), as well as volition à la ideomotor theory (Franklin 2000a; James 1890). Comprising a complete control structure for software agents (Franklin & Graesser 1997) and, potentially for autonomous robots (Franklin & McCauley 2003), the computational LIDA can be thought of as a virtual machine (Sloman & Chrisley 2003), built on top of a series of other virtual machines: a Java development environment, an operating system, microcode, etc. The LIDA model employs feelings and emotions throughout, both as motivators (Sloman 1987) and as modulators of learning.
In this paper we present a broad overview of the last 40 years of research on cognitive architectures. Although the number of existing architectures is nearing several hundred, most of the existing surveys do not reflect this growth and focus on a handful of well-established architectures. Thus, in this survey we wanted to shift the focus towards a more inclusive and high-level overview of the research on cognitive architectures. Our final set of 84 architectures includes 49 that are still actively developed, and borrow from a diverse set of disciplines, spanning areas from psychoanalysis to neuroscience. To keep the length of this paper within reasonable limits we discuss only the core cognitive abilities, such as perception, attention mechanisms, action selection, memory, learning and reasoning. In order to assess the breadth of practical applications of cognitive architectures we gathered information on over 900 practical projects implemented using the cognitive architectures in our list. We use various visualization techniques to highlight overall trends in the development of the field. In addition to summarizing the current state-of-the-art in the cognitive architecture research, this survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.