Cognitive Agents Research Articles

Evolution of a cognitive architecture on the basis of a functional core

Industry 4.0 assumes the use of intelligent components integrated into a single system and capable of interacting with each other without human intervention. Autonomous cognitive agents are the technological basis for building such systems. One of the main problems of modern cognitive architectures is an excessively schematic approach to modeling the processes of cognitive activity. It does not allow the creation of a universal architecture that would be capable of reproducing higher nervous functions without using a predetermined set of perception patterns. This paper proposes an evolutionary approach to creating a cognitive architecture. The basis of this approach is the use of some functional core, which consistently generates the intellectual functions of an autonomous agent. We are considering a cognitive architecture that includes components, the interaction of which ensures the evolution of the agent. The discussion of the development of intelligence is carried out using the conceptual apparatus of semiotics. This allows us to consider the task of developing cognitive functions as a problem of establishing a connection between the Merkwelt and the Werkwelt through the creation of the Innenwelt. The problem of early postnatal ontogenesis is investigated on the basis of the theory of constructivism: we discuss the requirements for the functional core and its composition, as well as the mechanism that initiates the process of cognition. We have developed a numerical method for modeling cognitive activities present at an early stage of ontogenesis. The method was used for the creation of the Cognitive Sensory System.

Meta-brain Models: biologically-inspired cognitive agents

Artificial Intelligence (AI) systems based solely on neural networks or symbolic computation present a representational complexity challenge. While minimal representations can produce behavioral outputs like locomotion or simple decision-making, more elaborate internal representations might offer a richer variety of behaviors. We propose that these issues can be addressed with a computational approach we call meta-brain models. Meta-brain models are embodied hybrid models that include layered components featuring varying degrees of representational complexity. We will propose combinations of layers composed using specialized types of models. Rather than using a generic black box approach to unify each component, this relationship mimics systems like the neocortical-thalamic system relationship of the mammalian brain, which utilizes both feedforward and feedback connectivity to facilitate functional communication. Importantly, the relationship between layers can be made anatomically explicit. This allows for structural specificity that can be incorporated into the model's function in interesting ways. We will propose several types of layers that might be functionally integrated into agents that perform unique types of tasks, from agents that simultaneously perform morphogenesis and perception, to agents that undergo morphogenesis and the acquisition of conceptual representations simultaneously. Our approach to meta-brain models involves creating models with different degrees of representational complexity, creating a layered meta-architecture that mimics the structural and functional heterogeneity of biological brains, and an input/output methodology flexible enough to accommodate cognitive functions, social interactions, and adaptive behaviors more generally. We will conclude by proposing next steps in the development of this flexible and open-source approach.

Перцептивные и градуально-оценочные парадигмы переводного поэтического текста

The article deals with semantic variation in textual, perceptual and gradual-evaluative paradigms in translation of English poetic texts into Russian. The research material is comprised of the poem A sepal – petal – and a thorn written by an American poet Emily E. Dickinson, and three variants of its translation into Russian carried out by T. Stamova, L. Vagurina, A. Pustogarov. The perceptual narrative plan and sense generation in the source text and its translated target textual variants have been studied considering such relevant criteria as cognitive subject, forms of perception, reference and autoreference, and modal gradual-evaluative frame. The integrative power of a text as a unit of upper layer of the language is noted to be manifested in the complex of compositional, content, and formal linguistic factors of text-building within the rhetoric frame of the poem. The key method of linguistic reconstruction of poetic text cognitive element has been applied to describe the cognitive agent as the subject of perception and subject of speech. Its position is determined within perceptual and gradual-evaluative paradigms. The formation of textual paradigms has also been shown to vary crucially in inter-language communication, to deviate in the target textual variants, and cause multiple interpretations of the source-text meaning.

AI and We in the Future in the Light of the Ouroboros Model: A Plea for Plurality

Artificial Intelligence (AI) is set to play an ever more important role in our lives and societies. Here, some boundary conditions and possibilities for shaping and using AI as well as advantageously embedding it in daily life are sketched. On the basis of a recently proposed cognitive architecture that claims to deliver a general layout for both natural intelligence and general AI, a coarse but broad perspective is developed and an emphasis is put on AI ethics. A number of findings, requirements, and recommendations are derived that can transparently be traced to the hypothesized structure and the procedural operation of efficient cognitive agents according to the Ouroboros Model. Including all of the available and possibly relevant information for any action and respecting a “negative imperative” are the most important resulting recommendations. Self-consistency, continual monitoring, equitable considerations, accountability, flexibility, and pragmatic adaptations are highlighted as foundations and, at the same time, mandatory consequences for timely answers to the most relevant questions concerning the embedding of AI in society and ethical rules for this.

Quantum-inspired cognitive agents

The concept of intelligent agents is—roughly speaking—based on an architecture and a set of behavioral programs that primarily serve to solve problems autonomously. Increasing the degree of autonomy and improving cognitive performance, which can be assessed using cognitive and behavioral tests, are two important research trends. The degree of autonomy can be increased using higher-level psychological modules with which needs and motives are taken into account. In our approach we integrate these modules in architecture for an embodied, enactive multi-agent system, such that distributed problem solutions can be achieved. Furthermore, after uncovering some weaknesses in the cognitive performance of traditionally designed agents, we focus on two major aspects. On the one hand, the knowledge processing of cognitive agents is based on logical formalisms, which have deficiencies in the representation and processing of incomplete or uncertain knowledge. On the other hand, in order to fully understand the performance of cognitive agents, explanations at the symbolic and subsymbolic levels are required. Both aspects can be addressed by quantum-inspired cognitive agents. To investigate this approach, we consider two tasks in the sphere of Shannon's famous mouse-maze problem: namely classifying target objects and ontology inference. First, the classification of an unknown target object in the mouse-maze, such as cheese, water, and bacon, is based on sensory data that measure characteristics such as odor, color, shape, or nature. For an intelligent agent, we need a classifier with good prediction accuracy and explanatory power on a symbolic level. Boolean logic classifiers do work on a symbolic level but are not adequate for dealing with continuous data. Therefore, we demonstrate and evaluate a quantum-logic-inspired classifier in comparison to Boolean-logic-based classifiers. Second, ontology inference is iteratively achieved by a quantum-inspired agent through maze exploration. This requires the agent to be able to manipulate its own state by performing actions and by collecting sensory data during perception. We suggest an algebraic approach where both kinds of behaviors are uniquely described by quantum operators. The agent's state space is then iteratively constructed by carrying out unitary action operators, while Hermitian perception operators act as observables on quantum eigenstates. As a result, an ontology emerges as the simultaneous solution of the respective eigenvalue equations.

On the Premise of a Swarm Guidance Ontology for Human-Swarm Teaming

Effective Human-Swarm Teaming (HST) relies on bi-directional information flow between the human and the swarm. Systems with human control or oversight rely on information flow from the swarm to the humans to inform decisions, while information that flows back from humans is only that necessary for actuation, which remains primarily physical. To unlock the full potential of HSTs, the augmentation must extend into the overall logic of teaming, including both the human’s and machine’s cognitive domains, whereby an AI-equipped robot teammate is capable of complex cognitive functions. The effectiveness of HST will need a sufficient level of transparency in the interaction space formed by the bi-directional information flow between the human and the swarm. This transparency must continuously and constructively interpret the information exchanged between the human and the swarm to afford both cognitive agents with the capacity to form shared understanding and situation awareness, and thus, facilitating effective teaming through trust. An ontology is one formal representational construct that enables bi-directional interpretation, thus, transparency. In this paper, we conceptualise and present a meta-ontology for transparent HST interactions.

Examining the Effects of Cognitive Assistive Agents on Team Coordination in Manufacturing Teams

This article details the motivation and design of an experiment to investigate the effects of artificially intelligent cognitive assistive agents on coordination efforts in manufacturing teams. As automation solutions become more accessible and products rapidly grow in complexity, there are significant calls to leverage abilities of both artificial agents and human workers to maximize team functioning and product output. As such, we propose an experimental design where we introduce a cognitive agent with two levels of autonomy (low, and high) into a team of participants during an assembly task. We hypothesized that cognitive assistive technologies would enhance coordination within assembly teams, leading to higher productivity and reduced errors, with initial data suggesting trends in support of these hypotheses. We seek to demonstrate the value of cognitive agents in augmenting human workers, allowing manufacturers to see the benefit of increased productivity while retaining value and relevance of human labor in the face of technological development.

Could a Computer Learn to Be an Appeals Court Judge? The Place of the Unspeakable and Unwriteable in All-Purpose Intelligent Systems

I will take it that general intelligence is intelligence of the kind that a typical human being—Fred, say—manifests in his role as a cognitive agent, that is, as an acquirer, receiver and circulator of knowledge in his cognitive economy. Framed in these terms, the word “general” underserves our ends. Hereafter our questions will bear upon the all-purpose intelligence of beings like Fred. Frederika appears as Fred’s AI-counterpart, not as a fully programmed and engineered being, but as a presently unrealized theoretical construct. Our basic question is whether it is in principle possible to equip Frederika to do what Fred does as an all-purpose participant in his own cognitive economy. Can she achieve a sufficiency of relevant similarity to him to allow us to say that she herself can do what Fred can do, perhaps even better? One of the things that Fred can do—or at least could learn from experience to do—is discharge the duties of an Appeals Court judge. As set down in the ancient doctrine of lex non scripta, Fred must be able to detect, understand and correctly apply certain tacit and implicit rules of law which defy express propositional formulation and linguistic articulation. Fred has an even more widespread capacity for the epistemically tacit and implicit, clearly one of his most cost-saving kinds of intelligence. Indeed, most by far of what Fred will ever know he will know tacitly and implicitly. So we must ask: how tightly bound to the peculiarities of Fred’s cognitive enablement conditions is the character of the intelligence that he manifests? And how far down Fred’s causal make-up does intelligence actually go?

Using cognitive models to design dynamic task allocation systems

Many operations in Intelligence, Surveillance, and Reconnaissance (ISR) involve balancing multiple simultaneous interdependent tasks and coordinating between multiple teammates. Recently, autonomous managers (AMs) were proposed as a method for optimizing performance in team-based workflows using dynamic reallocation in response to changes in workload and performance. We demonstrate how cognitive models can be used in the design and evaluation of AMs. Specifically, cognitive models can be used to inform an AM’s decision policy, and to stress test an AM under a wide variety of conditions. Simulation 1 tested the robustness of numerous AMs across a wide range of cognitive agents. We found that a simpler cognitive model in the AM’s decision system was more robust than more complex models. In the second simulation study, we compared dynamic task reallocation and corrective feedback to improve performance of cognitive agents based on the ACT-R cognitive architecture. Our results indicate that both interventions have the potential to improve performance, and that the most robust AM from simulation 1 can improve the performance of a model with realistic learning dynamics. Our simulations demonstrate that cognitive models are useful for designing and evaluating AMs for multiple military applications, including ISR.

Using affective criteria in the decision-making of cognitive agents on flexible passenger transportation domain

Using affective criteria in the decision-making of cognitive agents on flexible passenger transportation domain

Spatial relation learning in complementary scenarios with deep neural networks.

A cognitive agent performing in the real world needs to learn relevant concepts about its environment (e.g., objects, color, and shapes) and react accordingly. In addition to learning the concepts, it needs to learn relations between the concepts, in particular spatial relations between objects. In this paper, we propose three approaches that allow a cognitive agent to learn spatial relations. First, using an embodied model, the agent learns to reach toward an object based on simple instructions involving left-right relations. Since the level of realism and its complexity does not permit large-scale and diverse experiences in this approach, we devise as a second approach a simple visual dataset for geometric feature learning and show that recent reasoning models can learn directional relations in different frames of reference. Yet, embodied and simple simulation approaches together still do not provide sufficient experiences. To close this gap, we thirdly propose utilizing knowledge bases for disembodied spatial relation reasoning. Since the three approaches (i.e., embodied learning, learning from simple visual data, and use of knowledge bases) are complementary, we conceptualize a cognitive architecture that combines these approaches in the context of spatial relation learning.

An adaptive, probabilistic, cognitive agent architecture for modelling sugarcane growers’ operational decision-making

Building computational models of agents in dynamic, partially observable and stochastic environments is challenging. We propose a cognitive computational model of sugarcane growers’ daily decision-making to examine sugarcane supply chain complexities. Growers make decisions based on uncertain weather forecasts; cane dryness; unforeseen emergencies; and the mill’s unexpected call for delivery of a different amount of cane. The Belief-Desire-Intention (BDI) architecture has been used to model cognitive agents in many domains, including agriculture. However, typical implementations of this architecture have represented beliefs symbolically, so uncertain beliefs are usually not catered for. Here we show that a BDI architecture, enhanced with a dynamic decision network (DDN), suitably models sugarcane grower agents’ repeated daily decisions. Using two complex scenarios, we demonstrate that the agent selects the appropriate intention, and suggests how the grower should act adaptively and proactively to achieve his goals. In addition, we provide a mapping for using a DDN in a BDI architecture. This architecture can be used for modelling sugarcane grower agents in an agent-based simulation. The mapping of the DDN’s use in the BDI architecture enables this work to be applied to other domains for modelling agents’ repeated decisions in partially observable, stochastic and dynamic environments

Towards VEsNA, a Framework for Managing Virtual Environments via Natural Language Agents

Automating a factory where robots are involved is neither trivial nor cheap. Engineering the factory automation process in such a way that return of interest is maximized and risk for workers and equipment is minimized, is hence of paramount importance. Simulation can be a game changer in this scenario but requires advanced programming skills that domain experts and industrial designers might not have. In this paper we present the preliminary design and implementation of a general-purpose framework for creating and exploiting Virtual Environments via Natural language Agents (VEsNA). VEsNA takes advantage of agent-based technologies and natural language processing to enhance the design of virtual environments. The natural language input provided to VEsNA is understood by a chatbot and passed to a cognitive intelligent agent that implements the logic behind displacing objects in the virtual environment. In the VEsNA vision, the intelligent agent will be able to reason on this displacement and on its compliance to legal and normative constraints. It will also be able to implement what-if analysis and case-based reasoning. Objects populating the virtual environment will include active objects and will populate a dynamic simulation whose outcomes will be interpreted by the cognitive agent; explanations and suggestions will be passed back to the user by the chatbot.

Towards ontological interoperability of cognitive IoT agents based on natural language processing¶

The interoperability of devices from distinct brands on the Internet of Things (IoT) domain is still an open issue. The main reason is that pioneer companies always deliberately neglected to deploy devices able to interoperate with competitors products. The key factors that may invert such a trend derive, on one hand, from the abstraction of communication protocols that facilitates the migration from vertical to horizontal paradigms and, on the other hand, from the introduction of common and shared ontologies encoding devices specifications. The Semantic Web, with all its layers, can be considered the main framework for delivering ontologies, and by virtue of its features, it is surely the ideal means for providing shared knowledge. In this paper we present a framework that instantiates cognitive agents operating in IoT context, endowed with meta-reasoning in the Semantic Web. The framework, called SW-Caspar, is also provided with a module that performs semi-automatic ontology learning from sentences expressed in natural language; such a learning process generates a conceptual space reflecting the domain of discourse with an instance of a novel foundational ontology called Linguistic Oriented Davidsonian Ontology (LODO), whose main feature is to increase the deepness of reasoning without compromising linguistic-related features. LODO is inspired by the First-Order Logic Davidsonian notation and is serialized in OWL 2. Well-known examples derived from the theory of logical reasoning and a case-study applied to automation on health scenarios are also provided.

Simultaneous Learning and Planning in a Hierarchical Control System for a Cognitive Agent

Simultaneous Learning and Planning in a Hierarchical Control System for a Cognitive Agent

Zaawansowane procedury NLP jako przesłanka rekonstrukcji idei wiedzy

Advanced NLP Procedures as Premises for the Reconstruction of the Idea of Knowledge The article presents the current state of development of the Natural Language Processing (NLP) technology, in particular the GPT-3 language model, and presents its consequences for understanding the phenomenon of knowledge. The NLP technology has been experiencing remarkable development recently. The GPT-3 language model presents a level of advancement that allows it to generate texts as answers to general questions, as summaries of the presented text, etc., which reach the level surpassing the analogous level of human texts. These algorithmic operations lead to the determination of the probability distribution of its components. Texts generated by such a model should be considered as autonomous texts, using immanent, implicit knowledge embedded in language. This conclusion raises questions about the status of such knowledge. Help in the analysis is provided also by the theory of discourse, as well as the theory of discursive space based on it, that proposes the interpretation of knowledge as a trajectory of discourses in a dynamical space. Recognizing that knowledge may also be autonomous, and in particular not be at the exclusive disposal of humans, leads to the question of the status of artificial cognitive agents, such as the GPT-3 language model.

Comparative Analytical Survey on Cognitive Agents with Emotional Intelligence

Comparative Analytical Survey on Cognitive Agents with Emotional Intelligence

A Cognitive Agent Model of Burnout for Front-line Healthcare Professionals in Times of COVID-19 Pandemic

A Cognitive Agent Model of Burnout for Front-line Healthcare Professionals in Times of COVID-19 Pandemic

Lateral Pre-crash Sensing and Avoidance in Emotion Enabled Cognitive Agent based Vehicle-2-Vehicle Communication System

A novel inter-vehicle communication system based on emotion enabled cognitive (EEC) agent has been anticipated as an intelligent solution to evade the road catastrophe due to hasty decisions by drivers. An input stimulus is processed in human brain using a short route and a long route during any emergency situation. The proposed EEC agent, mounted inside a vehicle, acts like a human brain and is stirred by short route information processing mechanism of human brain in fear condition. The results are acquired for the decisions made by the proposed approach through the EEC agent using short route and human drivers using long route during urgent situations. A pre crash sensing and avoidance algorithm has been proposed as well to mitigate the lateral or side by side collision using EEC agent. Experimental findings reveal that by commencing emotions with cognition, and using formulated L-PCSA algorithm, lateral collisions chances can be sensed and avoided to secure the valued lives of passengers. It has been pragmatic that the new approach is very effectual and useful in shunning the lateral road collisions.

Number of Autonomous Cognitive Agents in a Neural Network

This paper considers several aspects of the relationship between size, structure, speed of propagation and the number of autonomous cognitive agents in a neural network. While memory and function generation capacities of neural networks with scale-invariant structure have been investigated extensively, the number of autonomous agents, associated with the simultaneous processing of the independent components of the data, has not received prior attention. We propose the emergence of the dichotomy of causal and noncausal regions created by the speed of propagation, in which the autonomous cognitive agents are not bound in a causal relationship with other agents. Arguments are presented for why the count of autonomous agents is best estimated with respect to the dimensionality of the underlying space. The number of autonomous agents obtained for the human brain equals 25, and it is significant that the number in the sub-system modules also turns out to be close to the same value. This number equals the number of enumerative categories of reality in at least one philosophical tradition, and this coincidence may be attributed to the capacity of consciousness to reflect on its own structure. It is possible that near equality across layers provides a special uniqueness to the human brain. We propose that the findings of this study will be useful in the design of neural-network-based AI systems that are designed to emulate human cognitive capacity.