Cognitive Agents Research Articles

Intertwining the social and the cognitive loops: socially enactive cognition for human-compatible interactive systems.

It is increasingly important for technical systems to be able to interact flexibly, robustly and fluently with humans in real-world scenarios. However, while current AI systems excel at narrow task competencies, they lack crucial interaction abilities for the adaptive and co-constructed social interactions that humans engage in. We argue that a possible avenue to tackle the corresponding computational modelling challenges is to embrace interactive theories of social understanding in humans. We propose the notion of socially enactive cognitive systems that do not rely solely on abstract and (quasi-)complete internal models for separate social perception, reasoning and action. By contrast, socially enactive cognitive agents are supposed to enable a close interlinking of the enactive socio-cognitive processing loops within each agent, and the social-communicative loop between them. We discuss theoretical foundations of this view, identify principles and requirements for according computational approaches, and highlight three examples of our own research that showcase the interaction abilities achievable in this way. This article is part of a discussion meeting issue 'Face2face: advancing the science of social interaction'.

Collision-Free Navigation in Human-Following Task Using a Cognitive Robotic System on Differential Drive Vehicles

As human–robot collaboration increases tremendously in real-world applications, a fully autonomous and reliable mobile robot for the collaboration has been a central research topic and investigated extensively in a large number of studies. One of the most pressing issues in such topic is the collision-free navigation that has a moving goal and unknown obstacles under the unstructured environment. In this article, a cognitive robotic system (CRS) is proposed for the robot to navigate itself to the moving target person without obstacle collision. This CRS consists of a cognitive agent, which is created based on the Soar cognitive architecture to reason its current situation and make action decision for the robot to avoid obstacles and reach the target position, and a speed planning module, which is based on dynamic window approach (DWA) to generate appropriate linear and angular velocities for driving the robot’s motors. For the implementation of the proposed system, we use a differential drive wheel robot equipped with two ultrawideband (UWB) sensors and a color depth camera as the experimental platform. Finally, to evaluate the performance of our system in actual operating conditions, we conduct experiments with a scenario that includes main tasks: avoiding consecutive unknown obstacles and turning at corner while the robot follows continuously human user along the corridor.

The Quest for Cognition in Purposive Action: From Cybernetics to Quantum Computing

Norbert Wiener and Nikolai Bernstein set the stage for a worldwide multidisciplinary attempt to understand how purposive action is integrated with cognition in a circular, bidirectional manner, both in life sciences and engineering. Such a 'workshop' is still open and far away from a satisfactory level of understanding, despite the current hype surrounding Artificial Intelligence (AI). The problem is that Cognition is frequently confused with Intelligence, overlooking a crucial distinction: the type of cognition that is required of a cognitive agent to meet the challenge of adaptive behavior in a changing environment is Embodied Cognition, which is antithetical to the disembodied and dualistic nature of the current wave of AI. This essay is the perspective formulation of a cybernetic framework for the representation of actions that, following Bernstein, is focused on what has long been considered the fundamental issue underlying action and motor control, namely the degrees of freedom problem. In particular, the paper reviews a solution to this problem based on a model of ideomotor/muscle-less synergy formation, namely the Passive Motion Paradigm (PMP). Moreover, it is shown how this modeling approach can be reformulated in a distributed manner based on a self-organizing neural paradigm consisting of multiple topology-representing networks with attractor dynamics. The computational implication of such an approach is also briefly analyzed looking at possible alternatives of the von Neuman paradigm, namely neuromorphic and quantum computing, aiming in perspective at a hybrid computational framework for integrating digital information, analog information, and quantum information. It is also suggested that such a framework is crucial not only for the neurobiological modeling of motor cognition but also for the design of the cognitive architecture of autonomous robots of industry 4.0 that are supposed to interact and communicate naturally with human partners.

How systemic cognition enables epistemic engineering.

Epistemic engineering arises as systems and their parts develop functionality that is construed as valid knowledge. By hypothesis, epistemic engineering is a basic evolutionary principle. It ensures that not only living systems identify the differences that make differences but also ensure that distributed control enables them to construct epistemic change. In tracking such outcomes in human life, we stress that humans act within poly-centered, distributed systems. Similar to how people can act as inert parts of a system, they also actively bring forth intents and vicariant effects. Human cognitive agents use the systemic function to construct epistemic novelties. In the illustration, we used a published experimental study of a cyborg cockroach to consider how an evoneered system enables a human subject to perform as an adaptor with some "thought control" over the animal. Within a wide system, brains enable the techniques to arise ex novo as they attune to the dictates of a device. Human parts act as adaptors that simplify the task. In scaling up, we turn to a case of organizational cognition. We track how adaptor functions spread when drone-based data are brought to the maintenance department of a Danish utility company. While pivoting on how system operators combine experience with the use of software, their expertise sets off epistemically engineered results across the company and beyond. Vicariant effects emerge under the poly-centered control of brains, persons, equipment, and institutional wholes. As a part of culture, epistemic engineering works by reducing entropy.

Intrinsic Lexical Intentionality and the Mathematics of Homomorphism

Moisl [1, 2] proposed a model of how the brain implements intrinsic intentionality with respect to lexical and sentence meaning, where 'intrinsic' is understood as 'independent of interpretation by observers external to the cognitive agent'. The discussion in both was mainly philosophical and qualitative; the present paper gives a mathematical account of the distance structure preservation that underlies the proposed mechanism of intrinsic intentionality. The three-layer autoassociative multilayer perceptron (aMLP) architecture with nonlinear hidden and linear output layers is the component in the model which generates representations homomorphic with the environment. The discussion first cites existing work which identifies the aMLP as an implementation architecture for principal component analysis (PCA), and then goes on to argue that the homomorphism characteristic of linear functions like PCA extends to aMLPs with nonlinear activation functions in the hidden layer. The discussion is in two main parts: the first part outlines the model, and the second presents the mathematical account.

Consciousness as a Trigger to Adaptation

Consciousness refers to mental states of a cognitive agent that make it aware of elements of its environment and its own state. Phenomena of consciousness have been studied in Philosophy, Psychology and Cognitive Science. With the advent of Artificial Intelligence (AI), the study of consciousness has broadened to include questions such as “When is an AI system conscious?”, “What role does consciousness play in the cognitive architecture of an AI system?”. This paper proposes a cognitive architecture that attempts to answer such questions and is an extension of proposals for practical reasoning, founded on the notion of epistemic goals, goals where the desired state-of-affairs is knowledge of something in the environment or within the agent itself. The proposal is illustrated with an example involving an autonomous vehicle.

How to train a self-driving vehicle: On the added value (or lack thereof) of curriculum learning and replay buffers.

Learning from only real-world collected data can be unrealistic and time consuming in many scenario. One alternative is to use synthetic data as learning environments to learn rare situations and replay buffers to speed up the learning. In this work, we examine the hypothesis of how the creation of the environment affects the training of reinforcement learning agent through auto-generated environment mechanisms. We take the autonomous vehicle as an application. We compare the effect of two approaches to generate training data for artificial cognitive agents. We consider the added value of curriculum learning-just as in human learning-as a way to structure novel training data that the agent has not seen before as well as that of using a replay buffer to train further on data the agent has seen before. In other words, the focus of this paper is on characteristics of the training data rather than on learning algorithms. We therefore use two tasks that are commonly trained early on in autonomous vehicle research: lane keeping and pedestrian avoidance. Our main results show that curriculum learning indeed offers an additional benefit over a vanilla reinforcement learning approach (using Deep-Q Learning), but the replay buffer actually has a detrimental effect in most (but not all) combinations of data generation approaches we considered here. The benefit of curriculum learning does depend on the existence of a well-defined difficulty metric with which various training scenarios can be ordered. In the lane-keeping task, we can define it as a function of the curvature of the road, in which the steeper and more occurring curves on the road, the more difficult it gets. Defining such a difficulty metric in other scenarios is not always trivial. In general, the results of this paper emphasize both the importance of considering data characterization, such as curriculum learning, and the importance of defining an appropriate metric for the task.

Learning to solve arithmetic problems with a virtual abacus

Acquiring mathematical skills is considered a key challenge for modern Artificial Intelligence systems. Inspired by the way humans discover numerical knowledge, here we introduce a deep reinforcement learning framework that allows to simulate how cognitive agents could gradually learn to solve arithmetic problems by interacting with a virtual abacus. The proposed model successfully learn to perform multi-digit additions and subtractions, achieving an error rate below 1% even when operands are much longer than those observed during training. We also compare the performance of learning agents receiving a different amount of explicit supervision, and we analyze the most common error patterns to better understand the limitations and biases resulting from our design choices.

IMAGES OF HUNGER, SATIATION AND THIRST IN THE MIRROR OF ENGLISH AND UKRAINIAN PHRASEOLOGY. Article 3

This publication is the final, third article of the thematic cycle Images of feeding/eating food in the mirror of English and Ukrainian phraseology. It is devoted to the problem of figurative understanding and phraseological description of the processes (including causes and consequences) of CONSUMING food or drinks. The material considered by us offers the possibility of ethnocultural comparative analysis of two unrelated societies — Ukrainian-speaking and English-speaking ones. Based on A. Maslow’s thesis about the basic level of needs in the phylogenetic development of a person as a biological and social being, namely the need to quench hunger and thirst, the phraseological funds of both languages, which are focused on seeing exactly these needs, are considered. It has been proven that phraseological units (PhU) of gustatory semantics verbalize the deep cognitive model AGENT FEEDS THE PATIENT SOMEHOW and its mirror second half PATIENT CONSUMES SOMETHING (FOOD/DRINK) SOMEHOW. This publication highlights exactly this second half of the specified cognitive model. The purpose of this study was to investigate the phraseological fund of a language as certain clots of cultural heritage, cast into a figuratively transformed patterns of idioms, phraseological units, proverbs, sometimes maxims, i.e. prescriptions of ancestors, which they passed on to their descendants regarding the correct worldview and successful functioning in the surrounding world. The total sample is quantitatively distributed unevenly between the two languages, the English component is twice as small as the Ukrainian one: 117 English PhUs and 265 Ukrainian PhU. The semantic component CONSUMPTION is verbalized by 13 verbs in English and 28 in Ukrainian, which indicates a greater sensitivity of Ukrainian speakers to the semantic nuances of the process of consuming food and drinks (them being excessive or insufficient, approved or critically regarded by the speaker who nominates the phenomenon). It was found that the English-speaking sample is more focused on reflecting universal, philosophical aspects of life, while the Ukrainian sample is more “home-centric”, the state of hunger and thirst in the Ukrainian-speaking sample is reflected much more broadly and more emotionally than in the English-speaking sample, overeating is a frequent object of mockery and criticism of Ukrainians, which in no way coincides with the dominant code of political correctness in modern Western culture. The analyzed material testified to a certain role of alcoholic beverages in the lives of representatives of the two ethnic groups, both ethno-specific and cross-cultural customs and traditions were revealed, the presence of English-language PhUs regarding drug use was recorded, which is not observed in Ukrainian-speaking PhUs. In conclusion, let us emphasize that gustatory phraseology of any language reflects not only the processes and customs of FEEDING / CONSUMING something edible, but a much wider spectrum of human existence: personal and social relationships, philosophical interpretations of human needs and limitations, moral prescriptions and prohibitions. In the end, we will repeat the thought of Socrates, with which we started this series of articles: “One must eat to live, not live to eat.”

Rational Coordination in Cognitive Agents: A Decision-Theoretic Approach Using ERMM

Rational Coordination in Cognitive Agents: A Decision-Theoretic Approach Using ERMM

Hybrid Cognition for Target Tracking in Cognitive Radar Networks

This work investigates online learning techniques for a cognitive radar network utilizing feedback from a central coordinator. The available spectrum is divided into channels, and each radar node must transmit in one channel per time step. The network attempts to optimize radar tracking accuracy by learning the optimal channel selection for spectrum sharing and radar performance. We define optimal selection for such a network in relation to the radar observation quality obtainable in a given channel. This is a difficult problem since the network must seek the optimal assignment from nodes to channels, rather than just seek the best overall channel. Since the presence of primary users appears as interference, the approach also improves spectrum sharing performance. In other words, maximizing radar performance also minimizes interference to primary users. Each node is able to learn the quality of several available channels through repeated sensing. We define hybrid cognition as the condition where both the independent radar nodes as well as the central coordinator are modeled as cognitive agents, with restrictions on the amount of information that can be exchanged between the radars and the coordinator. Importantly, each part of the network acts as an online learner, observing the environment to inform future actions. We show that in interference-limited spectrum, where the signal-to-interference-plus-noise ratio varies by channel and over time for a target with fixed radar cross section, a cognitive radar network is able to use information from the central coordinator in order to reduce the amount of time necessary to learn the optimal channel selection. We also show that even limited use of a central coordinator can eliminate collisions, which occur when two nodes select the same channel. We provide several reward functions which capture different aspects of the dynamic radar scenario and describe the online machine learning algorithms which are applicable to this structure. In addition, we study varying levels of feedback, where central coordinator update rates vary. We compare our algorithms against baselines and demonstrate dramatic improvements in convergence time over the prior art. A network using hybrid cognition is able to use a minimal amount of feedback to achieve much faster convergence times and therefore lower tracking error.

Cooperative Product Agents to Improve Manufacturing System Flexibility: A Model-Based Decision Framework

Due to the advancements in manufacturing system technology and the ever-increasing demand for personalized products, there is a growing desire to improve the flexibility of manufacturing systems. Multi-agent control is one strategy that has been proposed to address this challenge. The multi-agent control strategy relies on the decision making and cooperation of a number of intelligent software agents to control and coordinate various components on the shop floor. One of the most important agents for this control strategy is the product agent, which is the decision maker for a single part in the manufacturing system. To improve the flexibility and adaptability of the product agent and its control strategy, this work proposes a direct and active cooperation framework for the product agent. The directly and actively cooperating product agent can identify and actively negotiate scheduling constraints with other agents in the system. A new modeling formalism, based on priced timed automata, and an optimization-based decision making strategy are proposed as part of the framework. Two simulation case studies showcase how direct and active cooperation can be used to improve the flexibility and performance of manufacturing systems. Note to Practitioners—An intelligent product is a product in a manufacturing system that is able to make decisions based on a set of specifications and affect its own production process. Intelligent products have often been proposed to address the challenges associated with small-batch manufacturing and highly customized production. Specifically, by using intelligent products, manufacturers would be able to complete small orders without the need to reconfigure or reschedule operations in the manufacturing system. However, one of the major challenges in the implementation of this control strategy is the need to develop methods that allow intelligent products to cooperate with machines, robots, and other products in a manufacturing system. In this work, we propose a novel direct and active cooperation framework that allows intelligent products to communicate and cooperate with other resources and products on the shop floor. Using the proposed cooperation framework, intelligent products can resolve scheduling conflicts and work together to meet individual specifications (e.g., deadlines). Two case studies, a small job shop and a large semiconductor manufacturing system, showcase how the proposed cooperation framework can be leveraged for different types of applications.

Behavioural constructivist approach to the semantics of the individual in propositional analyses

The paper is concerned with an approach to the semantics of the individual within propositional expression. The objective of the paper is to propose behavioural constructivism as an analytic approach to the semantics of constative sentences. The primary focus of the essay is to present the semantics of the individual referent in a proposition. The method adopted to achieve this objective is content analysis. The analysis has shown that the individual described in any given proposition is neither its subject nor its predicate but a relation, which is a construct of the cognitive agent and expressed in a proposition. So, the central issue in the semantics of a proposition is its expression of a relation constructed upon experience, not the description of the subject's state. A proposition is a report of the existence of such a construct.

ЛОГИКО-КОГНИТИВНЫЙ АНАЛИЗ ИСПОЛЬЗОВАНИЯ ВОПРОСА-ПРЕФОРМЫ В АРГУМЕНТАТИВНОЙ ДИСКУССИИ

The article presents the results of the study of the discussion snippets in the form of question-answering structures using the “argumentative discussion” construct; the study was based on the scripts of video panel discussions on the YouTube platform. Involving the methodology of the pragma-dialectical theory of argumentation in part of the analytical reconstruction of argumentative discourse, the author does not take as a basis the concept of persuading a rational addressee, which is common in argumentative theory, but takes the idea of verifying the point of view of cognitive agents of communication. It allows to consider the dialogic structure as a multi-subject procedure for checking the objectivity of knowledge of the participants in the discussion. The purpose of the article is to explore the question utterance in the position of the preform in the question-answering unity. The article contains scientific data from the field of erothetic logic, which shows that the question can be interpreted as a fragment of reasoning. For the reconstruction of cue-question, the concept of symptosymmetric proportionality of the components of dialogical unities is used. We analyzed all speech units in dialogic syntagmas in the form of Argumentative Step. Such an analysis showed that the basis of the question contains elements that perform argumentative functions. The focal meaning of these elements is found in response cues. As the result, the symptosymmetric models Preform-thesis ↔ refutation by facts, Preform-thesis ↔ antithesis, Preform-clarification ↔ correction were obtained. The interim result of the study is that the cue-question in the position of the preform is also a marker of a violation of the logical-categorical norms of reasoning and ad hoc errors.

Self-confidence at Workplace: Cognitive Agent Modeling and Analysis

Self-confidence at Workplace: Cognitive Agent Modeling and Analysis

A Semiotic Study of the Interplay between People and Buildings

The present paper deals with the semiotic study of the interplay between people and buildings. It studies sign processes, which is any form of activity, conduct, or any process that involves signs, including the production of meaning. It aims at examining the use of semiotics, deepening our understanding of the interplay between people and buildings and providing the basis for personalizing intelligent buildings using intelligent software agents. The data is limited to "Winged Bull", relying on Saussure's model. It is hypothesized that the concerned data is full of signs denoting different things. The present study is qualitative in nature since the researcher depends on herself in analyzing the data in question. It has been observed that "Winged Bull" is informative with signs. That is, each part of it denotes a certain thing enhancing people to think deeply.

A radical embodied perspective of autism: towards ethical, and inclusive views for cognitive diversities

Autism Spectrum Disorders have been defined as a group of developmental conditions that affect the capacity to interact with the physical and social environment, among others. A core feature of autism is the presence of restricted and repetitive behaviors that vary in complexity, form, and frequency throughout life history. These core features have traditionally been defined as impairments that interfere with communication competence. From an embodied approach, however, these actions could be seen as characteristic ways of interacting with the world. In this sense, we take an enactive and embodied approach to cognition in which we conceive cognitive agents as sensorimotor systems whose perception-action occurs in terms of affordances. This framework provides an integrative view of autism considering affectivity, perception, action, exploration, and interaction within a complex and dynamic dimension. Following this, we propose different applications based on embodied, intercultural, and feminist epistemologies, to understand and participate with autistic and cognitively diverse populations. The change in theoretical and methodological paradigms within embodied cognitive science towards autism and other cognitive diversities and how they engage with the world can lead to more comprehensive, integrative, and bioethical approaches.

Towards the construction of computational models of emotions from the perspective of a software system

Computational models of emotion (CMEs) are software systems designed to emulate the diverse aspects of the human emotion process. This type of model is commonly incorporated into cognitive agent architectures to provide mechanisms underlying affective behavior. The construction of CMEs involve theories that explain human emotion as well as computational artifacts related to the design and implementation of software systems. Although most CMEs reported in the literature provide details on their theoretical foundations, it is uncommon to find details about the computational practices and artifacts utilized during their design and implementation phases. This paper presents and discusses some challenges associated with the computational nature of this type of model: (i) Software quality attributes in CMEs, (ii) Interoperability between CMEs and cognitive components, (iii) Formal procedures for the design of CMEs, and (iv) Reference schemes to validate CMEs. Software engineering is used as a reference to propose and discuss these challenges. In addition, a reference architecture designed by following software engineering practices and artifacts is proposed to discuss the implications of addressing these challenges. The present research is at the intersection of human emotion modeling and software engineering to contribute to the software development process of affective systems.

A Role for Qualia

If qualia are mental, and if the mental is functional, then so are qualia. But, arguably, qualia are not functional. A resolution of this is offered based on a formal similarity between qualia and numbers. Just as certain sets “play the role of” the number 3 in Peano’s axioms, so a certain physical implementation of a color plays the role of, say, red in a (computational) cognitive agent’s “cognitive economy”.

A Reputation-based Framework for Honest Provenance Reporting

Given the distributed, heterogenous, and dynamic nature of service-based IoT systems, capturing circumstances data underlying service provisions becomes increasingly important for understanding process flow and tracing how outputs came about, thus enabling clients to make more informed decisions regarding future interaction partners. Whilst service providers are the main source of such circumstances data, they may often be reluctant to release it, e.g., due to the cost and effort required, or to protect their interests. In response, this article introduces a reputation-based framework, guided by intelligent software agents, to support the sharing of truthful circumstances information by providers. In this framework, assessor agents , acting on behalf of clients, rank and select service providers according to reputation, while provider agents , acting on behalf of service providers, learn from the environment and adjust provider’s circumstances provision policies in the direction that increases provider profit with respect to perceived reputation. The novelty of the reputation assessment model adopted by assessor agents lies in affecting provider reputation scores by whether or not they reveal truthful circumstances data underlying their service provisions, in addition to other factors commonly adopted by existing reputation schemes. The effectiveness of the proposed framework is demonstrated through an agent-based simulation including robustness against a number of attacks, with a comparative performance analysis against FIRE as a baseline reputation model.