Memory systems within a cognitive architecture

This article addresses the division of memory systems in relation to an overall cognitive architecture. As understanding the architecture is essential to understanding the mind, developing computational cognitive architectures is an important enterprise in computational psychology (computational cognitive modeling). The article proposes a set of hypotheses concerning memory systems from the standpoint of a cognitive architecture, in particular, the four-way division of memory (including explicit and implicit procedural memory and explicit and implicit declarative memory). It then discusses in detail how these hypotheses may be validated through examining qualitatively the literature on memory. A quick review follows of computational simulations of a variety of quantitative data (which are not limited to narrowly conceived “memory tasks”). Results of accounting for both qualitative and quantitative data point to the promise of this approach.     

Brain-inspired distributed cognitive architecture

In this paper we present a brain-inspired cognitive architecture that incorporates sensory processing, classification, contextual prediction, and emotional tagging. The cognitive architecture is implemented as three modular web-servers, meaning that it can be deployed centrally or across a network for servers. The experiments reveal two distinct operations of behaviour, namely high- and low-salience modes of operations, which closely model attention in the brain. In addition to modelling the cortex, we have demonstrated that a bio-inspired architecture introduced processing efficiencies. The software has been published as an open source platform, and can be easily extended by future research teams. This research lays the foundations for bio-realistic attention direction and sensory selection, and we believe that it is a key step towards achieving a bio-realistic artificial intelligent system.     

A neural cognitive architecture

It is difficult to study the mind, but cognitive architectures are one tool. As the mind emerges from the behaviour of the brain, neuropsychological methods are another method to study the mind, though a rather indirect method. A cognitive architecture that is implemented in spiking neurons is a method of studying the mind that can use neuropsychological evidence directly. A neural cognitive architecture, based on rule based systems and associative memory, can be readily implemented, and would provide a good bridge between standard cognitive architectures, such as Soar, and neuropsychology. This architecture could be implemented in spiking neurons, and made available via the Human Brain Project, which provides a good collaborative environment. The architecture could be readily extended to use spiking neurons for subsystems, such as spatial reasoning, and could evolve over time toward a complete architecture. The theory behind this architecture could evolve over time. Simplifying assumptions, made explicit, such as those behind the rule based system, could gradually be replaced by more neuropsychologically accurate behaviour. The overall task of collaborative architecture development would be eased by direct evidence of the actual neural cognitive architectures in human brains. While the initial architecture is biologically inspired, the ultimate goal is a biological cognitive architecture.     

Using a cognitive architecture to examine what develops

Different theories of development propose alternative mechanisms by which development occurs. Cognitive architectures can be used to examine the influence of each proposed mechanism of development while keeping all other mechanisms constant. An ACT-R computational model that matched adult behavior in solving a 21-block pyramid puzzle was created. The model was modified in three ways that corresponded to mechanisms of development proposed by developmental theories. The results showed that all the modifications (two of capacity and one of strategy choice) could approximate the behavior of 7-year-old children on the task. The strategy-choice modification provided the closest match on the two central measures of task behavior (time taken per layer, r = .99, and construction attempts per layer, r = .73). Modifying cognitive architectures is a fruitful way to compare and test potential developmental mechanisms, and can therefore help in specifying "what develops."     

The CORTEX cognitive robotics architecture: Use cases

CORTEX is a cognitive robotics architecture inspired by three key ideas: modularity, internal modelling and graph representations. CORTEX is also a computational framework designed to support early forms of intelligence in real world, human interacting robots, by selecting an a priori functional decomposition of the capabilities of the robot. This set of abilities was then translated to computational modules or agents, each one built as a network of software interconnected components. The nature of these agents can range from pure reactive modules connected to sensors and/or actuators, to pure deliberative ones, but they can only communicate with each other through a graph structure called Deep State Representation (DSR). DSR is a short-term dynamic representation of the space surrounding the robot, the objects and the humans in it, and the robot itself. All these entities are perceived and transformed into different levels of abstraction, ranging from geometric data to high-level symbolic relations such as “the person is talking and gazing at me”. The combination of symbolic and geometric information endows the architecture with the potential to simulate and anticipate the outcome of the actions executed by the robot. In this paper we present recent advances in the CORTEX architecture and several real-world human-robot interaction scenarios in which they have been tested. We describe our interpretation of the ideas inspiring the architecture and the reasons why this specific computational framework is a promising architecture for the social robots of tomorrow.     

Declarative working memory: A bio-inspired cognitive architecture proposal

Memory is considered one of the most important functions since it allows us to code, store and retrieve knowledge. These qualities make it an indispensable function for a virtual creature. In general, memory can be classified based on the durability of the stored data in working memory and long-term memory. Working memory refers to the capacity to maintain temporarily a limited amount of information in mind, which can then be used to support various abilities, including learning, reasoning, planning and decision-making. Unlike short-term memory, working memory is not only a storage site, but it is also a framework of interacting processes that involve the temporary storage and manipulation of information in the service of performing complex cognitive activities. Declarative memory is a type of long-term memory related with the storage of facts and events. This research focuses on the development of a cognitive architecture for the type of working memory that maintains and manipulates declarative information. The construction of the model was grounded in theoretical evidence taken from cognitive sciences such as neuroscience and psychology, which gave us the components and their processes. The model was evaluated through a case study that covers the encoding, storing, and retrieval stages. Our hypothesis is that a virtual creature endowed with our working memory model will provide faster access to the information needed for the ongoing task. Therefore, it improves the planning and decision-making processes.     

The TROCA Project: An autonomous transportation robot controlled by a cognitive architecture

Autonomous mobile robots emerged as an important kind of transportation system in warehouses and factories. In this work, we present the use of MECA cognitive architecture in the development of an artificial mind for an autonomous robot responsible for multiple tasks, including transportation of packages along a factory floor, environment exploration, warehouse inventory, its internal energy management, self-monitoring and dealing with human operators and other robots. The present text provides a detailed specification for the architecture and its software implementation. Future work will present the simulation results under different configurations, together with a detailed analysis of the architecture performance and its generalization for autonomous robot control.     

Causal cognitive architecture 1: Integration of connectionist elements into a navigation-based framework

The brain-inspired Causal Cognitive Architecture 1 (CCA1) tightly integrates the sensory processing capabilities found in neural networks with many of the causal abilities found in human cognition. Causality emerges not from a central controlling stored program but directly from the architecture. Sensory input vectors are processed by robust association circuitry and then propagated to a navigational temporary map. Instinctive and learned objects and procedures are applied to the same temporary map, with a resultant navigation signal obtained. Navigation can similarly be for the physical world as well as for a landscape of higher cognitive concepts. There is good explainability for causal decisions. A simulation of the CCA1 controlling a search and rescue robot is presented with the goal of finding and rescuing a lost hiker within a grid world. A simulation of the CCA1 controlling a repair robot is presented that can predict the movement of a series of gears.     

Acquisition of hierarchical reactive skills in a unified cognitive architecture

In this paper, we review Icarus, a cognitive architecture that utilizes hierarchical skills and concepts for reactive execution in physical environments. In addition, we present two extensions to the framework. The first involves the incorporation of means-ends analysis, which lets the system compose known skills to solve novel problems. The second involves the storage of new skills that are based on successful means-ends traces. We report experimental studies of these mechanisms on three distinct domains. Our results suggest that the two methods interact to acquire useful skill hierarchies that generalize well and that reduce the effort required to handle new tasks. We conclude with a discussion of related work on learning and prospects for additional research, including extending the framework to cover developmental phenomena.     

Bio-inspired cognitive architecture of episodic memory

Memory and learning are essential functions in human beings as they allow us to acquire and store in the brain representations of thoughts, experiences, and behaviors, which are required for problem-solving in our daily life and mainly for survival. Episodic memory is a type of memory that provides the ability to re-experience events in one’s life, and it is associated with their conscious recollection. Since episodic memory can represent our experiences about the environment, similar to a mental journey, it is desired in systems that attempt to create human-like behavior. Currently, the main problem is that state of the art proposals do not consider neuroscientific evidence like memory dynamics for forgetting or bottom-up inputs, and most of them do not consider episodic memory as a different memory but as part of general declarative memory. We consider these omissions to limit the generation of human-like behavior. In this work, we propose a bio-inspired cognitive architecture of episodic memory. Neuroscientific evidence provides us with the brain structures associated with this type of memory, the connections, and the operations these areas perform. We hypothesize that virtual entities endowed with our episodic memory cognitive architecture will plan and make decisions in a more human-like fashion. To test the capabilities of the proposal, we endowed a virtual creature with a distributed and concurrent implementation of our architecture, and it was given two tasks. The first task validated the functions of the memory independently, and in the second task, the creature used episodic memory to solve a planning problem. From the results of these experiments, we validate our proposal and show that it is possible to create a system that behaves as the human brain does.     

A cognitive architecture for inner speech

A cognitive architecture for inner speech is presented. It is based on the Standard Model of Mind, integrated with modules for self-talking. Briefly, the working memory of the proposed architecture includes the phonological loop as a component which manages the exchanging information between the phonological store and the articulatory control system. The inner dialogue is modeled as a loop where the phonological store hears the inner voice produced by the hidden articulator process. A central executive module drives the whole system, and contributes to the generation of conscious thoughts by retrieving information from long-term memory. The surface form of thoughts thus emerges by the phonological loop. Once a conscious thought is elicited by inner speech, the perception of new context takes place and then repeating the cognitive loop. A preliminary formalization of some of the described processes by event calculus, and early results of their implementation on the humanoid robot Pepper by SoftBank Robotics are discussed.     

Multilayer cognitive architecture for UAV control

Extensive use of unmanned aerial vehicles (UAVs) in recent years has induced the rapid growth of research areas related to UAV production. Among these, the design of control systems capable of automating a wide range of UAV activities is one of the most actively explored and evolving. Currently, researchers and developers are interested in designing control systems that can be referred to as intelligent, e.g. the systems which are suited to solve such tasks as planning, goal prioritization, coalition formation, etc. and thus guarantee high levels of UAV autonomy. One of the principal problems in intelligent control system design is tying together various methods and models traditionally used in robotics and aimed at solving such tasks as dynamics modeling, control signal generation, location and mapping, path planning, etc. with the methods of behavior modeling and planning which are thoroughly studied in cognitive science. Our work is aimed at solving this problem. We propose layered architecture—STRL (strategic, tactical, reactive, layered)—of the control system that automates the behavior generation using a cognitive approach while taking into account complex dynamics and kinematics of the control object (UAV). We use a special type of knowledge representation—sign world model—that is based on the psychological activity theory to describe individual behavior planning and coalition formation processes. We also propose path planning methodology which serves as the mediator between the high-level cognitive activities and the reactive control signals generation. To generate these signals we use a state-dependent Riccati equation and specific method for solving it. We believe that utilization of the proposed architecture will broaden the spectrum of tasks which can be solved by the UAV’s coalition automatically, as well as raise the autonomy level of each individual member of that coalition.     

The cognitive and neural architecture of sequence representation

The authors theorize that 2 neurocognitive sequence-learning systems can be distinguished in serial reaction time experiments, one dorsal (parietal and supplementary motor cortex) and the other ventral (temporal and lateral prefrontal cortex). Dorsal system learning is implicit and associates noncategorized stimuli within dimensional modules. Ventral system learning can be implicit or explicit It also allows associating events across dimensions and therefore is the basis of cross-task integration or interference, depending on degree of cross-task correlation of signals. Accordingly, lack of correlation rather than limited capacity is responsible for dual-task effects on learning. The theory is relevant to issues of attentional effects on learning; the representational basis of complex, sequential skills; hippocampal-versus basal ganglia-based learning; procedural versus declarative memory; and implicit versus explicit memory.     

Relevance theory,pragmatic inference and cognitive architecture

Relevance Theory (RT) argues that human language comprehension processes tend to maximize “relevance,” and postulates that there is a relevance-based procedure that a hearer follows when trying to understand an utterance. Despite being highly influential, RT has been criticized for its failure to explain how speaker-related information, either the speaker’s abilities or her/his preferences, is incorporated into the hearer’s inferential, pragmatic process. An alternative proposal is that speaker-related information gains prominence due to representation of the speaker within higher level goal-directed schemata. Yet the goal-based account is still unable to explain clearly how cross-domain information, for example linguistic meaning and speaker-related knowledge, is integrated within a modular system. On the basis of RT’s cognitive requirements, together with contemporary cognitive theory, we argue that this integration is realized by utilizing working memory and that there exist conversational constraints with which the constructed utterance interpretation should be consistent. We illustrate our arguments with a computational implementation of the proposed processes within a general cognitive architecture.

Abbreviations: ACT-R Adaptive Control of Thought - RationalCOGENT Cognitive Objects within a Graphical ENvironmenTCS/SS Contention Scheduling/Supervisory SystemRBCP Relevance-Based Comprehension ProcedureRT Relevance Theory     

A cognitive architecture that combines internal simulation with a global workspace

This paper proposes a brain-inspired cognitive architecture that incorporates approximations to the concepts of consciousness, imagination, and emotion. To emulate the empirically established cognitive efficacy of conscious as opposed to non-conscious information processing in the mammalian brain, the architecture adopts a model of information flow from global workspace theory. Cognitive functions such as anticipation and planning are realised through internal simulation of interaction with the environment. Action selection, in both actual and internally simulated interaction with the environment, is mediated by affect. An implementation of the architecture is described which is based on weightless neurons and is used to control a simulated robot.     

Unpacking the cognitive architecture of emotion processes

The results of 2 electroencephalographic studies confirm Component Process Model (CPM) predictions that different appraisal checks have specific brain state correlates, occur rapidly in a brief time window after stimulation, and produce results that occur in sequential rather than parallel fashion. The data are compatible with the assumption that early checks (novelty and intrinsic pleasantness) occur in an automatic, unconscious mode of processing, whereas later checks, specifically goal conduciveness, require more extensive, effortful, and controlled processing. Overall, this work, combined with growing evidence for the CPM's response patterning predictions concerning autonomic physiological signatures, facial muscle movements, and vocalization changes, suggests that this model provides an appropriate basis for the unpacking of the cognitive architecture of emotion and its computational modeling.