Artificial Cognitive Systems Research Articles

Development of numerical cognition in children and artificial systems: a review of the current knowledge and proposals for multi‐disciplinary research

Numerical cognition is a distinctive component of human intelligence such that the observation of its practice provides a window in high-level brain function. The modelling of numerical abilities in artificial cognitive systems can help to confirm existing child development hypotheses and define new ones by means of computational simulations. Meanwhile, new research will help to discover innovative principles for the design of artificial agents with advanced reasoning capabilities and clarify the underlying algorithms (e.g. deep learning) that can be highly effective but difficult to understand for humans. This study promotes new investigation by providing a common resource for researchers with different backgrounds, including computer science, robotics, neuroscience, psychology, and education, who are interested in pursuing scientific collaboration on mutually stimulating research on this topic. The study emphasises the fundamental role of embodiment in the initial development of numerical cognition in children. This strong relationship with the body motivates the cognitive developmental robotics (CDR) approach for new research that can (among others) help standardise data collection and provide open databases for benchmarking computational models. Furthermore, the authors discuss the potential application of robots in classrooms and argue that the CDR approach can be extended to assist educators and favour mathematical education.

Advantage of prediction and mental imagery for goal‐directed behaviour in agents and robots

Mental imagery and planning are important aspects of cognitive behaviour. Being able to predict outcomes through mental simulation can increase environmental fitness and reduce uncertainty. Such predictions reduce surprise and fit with thermodynamically driven theories of brain function by attempting to reduce entropy. In the present work, the authors tested these ideas in a predator–prey scenario where agents with a limited energy budget had to maximise food intake, while avoiding a predator. Forward planning agents, with the ability to mentalise, to Actor Critic agents that do not plan beyond the current state were also compared. The authors show that the ability to mentalise has distinct advantages when in noisy, uncertain stimuli. These advantages are even more prevalent when tested in the real world on physical robots. The authors’ results highlight the importance of taking into consideration mental imagery and embodiment when constructing artificial cognitive systems.

The Nature and Legal Features of Cyber-Physical, Cyber-Biological and Artificial Cognitive Systems

In the article, such categories as cyber-physical, cyber-biological and artificial cognitive systems (artificial intelligence) are analyzed in order to determine their characteristics important for legal science and practice. Different ways of defining the above mentioned concepts are examined. It is determined that a cyber-physical system includes a variety of technical means and is not easily placed within legal framework. Incorporation of this term in legal regulations through the description of its key characteristics is recommended. A cyber-biological system has the same structure as a cyber-physical system except that the physical component is replaced by biological one. It is argued that the relevance of the analysis of cyber-biological systems will depend on further scientific achievements in this area. The crucial property of the artificial cognitive system (artificial intelligence) is the ability to act independently and rationally. The authors conclude that the technical means covered by cyber-physical and cyber-biological systems acquire autonomy only if they have artificial intelligence. Finally, it is stated that the scope of social relations arising in the new reality will include only the technical means (objects regardless of their nature: physical, biological or virtual) able to perform legally significant actions independent from an individual person.

Basic functional trade-offs in cognition: An integrative framework

Trade-offs between advantageous but conflicting properties (e.g., speed vs. accuracy) are ubiquitous in cognition, but the relevant literature is conceptually fragmented, scattered across disciplines, and has not been organized in a coherent framework. This paper takes an initial step toward a general theory of cognitive trade-offs by examining four key properties of goal-directed systems: performance, efficiency, robustness, and flexibility. These properties define a number of basic functional trade-offs that can be used to map the abstract “design space” of natural and artificial cognitive systems. Basic functional trade-offs provide a shared vocabulary to describe a variety of specific trade-offs including speed vs. accuracy, generalist vs. specialist, exploration vs. exploitation, and many others. By linking specific features of cognitive functioning to general properties such as robustness and efficiency, it becomes possible to harness some powerful insights from systems engineering and systems biology to suggest useful generalizations, point to under-explored but potentially important trade-offs, and prompt novel hypotheses and connections between disparate areas of research.

Artificial Cognitive Systems That Can Answer Human Creativity Tests: An Approach and Two Case Studies

Creative cognitive systems are rarely assessed with the same tools as human creativity. In this paper, an approach is proposed for building cognitive systems which can solve human creativity tests. The importance of using cognitively viable processes, cognitive knowledge acquisition and organization, and cognitively comparable evaluation when implementing creative problem-solving systems is emphasized. Two case studies of artificial cognitive systems evaluated with human creativity tests are reviewed. A general approach is put forward. The applicability of this general approach to other creativity tests and artificial cognitive systems, together with ways of performing cognitive knowledge acquisition for these systems are then explored.

Cooperative Intersection Support System Based on Mirroring Mechanisms Enacted by Bio-Inspired Layered Control Architecture

This paper presents a cooperative intersection support system implemented with an artificial cognitive system enacted by an agent that replicates human driver longitudinal sensorimotor control in the application domain. The engineering of the agent exploits recent ideas from Cognitive Science, among which the notion of mirroring (the agent discovering driver intentions by simulating possible human actions). The paper introduces the design principles for the agent and the following implementation. The system is evaluated with experimental data and compared to state of the art implementations that use different approaches.

A Hybrid Approach to Cognition in Radars

In many engineering domains, cognition is emerging to play vital role. Cognition will play crucial role in radar engineering as well for the development of next generation radars. In this paper, a cognitive architecture for radars is introduced, based on hybrid cognitive architectures. The paper proposes deep learning applications for integrated target classification based on high-resolution radar range profile measurements and target revisit time calculation as case studies. The proposed architecture is based on the artificial cognitive systems concepts and provides a basis for addressing cognition in radars, which is inadequately explored for radar systems. Initial experimental studies on the applicability of deep learning techniques under this approach provided promising results.

Towards lifelong assistive robotics: A tight coupling between object perception and manipulation

Abstract This paper presents an artificial cognitive system tightly integrating object perception and manipulation for assistive robotics. This is necessary for assistive robots, not only to perform manipulation tasks in a reasonable amount of time and in an appropriate manner, but also to robustly adapt to new environments by handling new objects. In particular, this system includes perception capabilities that allow robots to incrementally learn object categories from the set of accumulated experiences and reason about how to perform complex tasks. To achieve these goals, it is critical to detect, track and recognize objects in the environment as well as to conceptualize experiences and learn novel object categories in an open-ended manner, based on human–robot interaction. Interaction capabilities were developed to enable human users to teach new object categories and instruct the robot to perform complex tasks. A naive Bayes learning approach with a Bag-of-Words object representation are used to acquire and refine object category models. Perceptual memory is used to store object experiences, feature dictionary and object category models. Working memory is employed to support communication purposes between the different modules of the architecture. A reactive planning approach is used to carry out complex tasks. To examine the performance of the proposed architecture, a quantitative evaluation and a qualitative analysis are carried out. Experimental results show that the proposed system is able to interact with human users, learn new object categories over time, as well as perform complex tasks.

On Revealing and Resolving the Scientific Paradoxes within the Artificial Cognitive System

The concept of scientific paradox and the possibility to reveal and resolve the paradox by means of artificial intelligence are discussed. The scientific paradox represents the contradictory description of the same reality within different scientific disciplines. Under the original Natural-Constructive Cognitive Architecture this paradox can be reproduced as impossibility to merge different representations of the same object. It is shown that this architecture involves, in particular, the high-level symbolic information that could be associated with concept of “scientific discipline”. The scientific paradox is treated as impossibility to integrate (merge) the symbols referring to different scientific disciplines. It is shown that the paradox could be resolved within the proposed architecture by decomposition of the high-level symbols down to low-level of corresponding raw mages, with subsequent revision of the object’s memorization procedure. One of the main distinctive features of the proposed architecture is the raw-image processor responsible for recording all the information on the presented object including even rare, seemingly inessential one, which correspond to rather weak connections between involved (halo) neurons. This processor could be associated with human sub-consciousness. The role of weak connections in resolution of paradox and scientific discovery (chef-d’oeuvre) is discussed.

Simulation of serotonin mechanisms in NEUCOGAR cognitive architecture

This work aims at demonstrating that the neuromodulatory mechanisms that control the emotional states of mammals (specifically rat’s brains) can be represented and re-implemented in a computational model processed by a machine. In particular we specifically focus on two neuro-transmitters, serotonin and dopamine, starting from their fundamental role in basic cognitive processes. In our specific implementation, we represent the simulation of the ‘disgust-like’ state based on the three dimensional neuromodulatory model of affects or emotions, according to the ‘cube of emotions’. These functional mechanisms can be transferred into an artificial cognitive system: inhibition, for example, can elicit a blocking behaviour that, depending on its intensity and duration, can push the system to a general emotional state. We have simulated 1000 milliseconds of the serotonin and dopamine systems using NEST Neural Simulation Tool with the rat brain as the model to artificially reproduce this mechanism on a computational system.

Early and Accurate Recognition of Highway Traffic Maneuvers Considering Real World Application: A Novel Framework Using Bayesian Networks

This paper presents a novel application of artificial cognitive systems to traffic scene understanding and early recognition of highway maneuvers. This is achieved by use of Bayesian networks for knowledge representation, to mimic the human reasoning on situation analysis and to manage inherited uncertainties in the automotive domain, that requires efficient and effective analysis of high volume and frequency data streams. The maneuver recognition uses features, analyzing the observed vehicles behavior and available free space on the target lane.

A Study on the Adaptability of Immune models for Wireless Sensor Network Security

Researchers in the field of artificial cognitive systems have persistently tried to adopt mechanisms and paradigms deployed in biological systems. Artificial neural network is one of the early examples adopting brain cell architecture and its computational practices. Similarly, Human Immune System (HIS) can be adopted for intrusion detection systems (IDS). The HIS recognizes and tries to eliminate external entities such as bacteria and viruses and works towards defending it from such threats. Detection and prevention mechanisms from HIS has been studied and adopted for Wireless Sensor Networks (WSN). Three well known techniques in the field of HIS-based IDS are studied and their adaptability to WSN’s is reported. These techniques include prominent immune models such as Negative Selection, Positive Selection, Danger Theory and Clonal Selection.

Optimization of Non-rigid Demons Registration Using Cuckoo Search Algorithm

Video processing including registration has a significant role in surveillance and real-time applications. Image registration is considered a compulsory step in video registration for numerous aspects. One of the major challenges in image registration is to determine the optimal parameters during the registration process. Bio-inspired computational including natural and artificial cognitive systems can be employed to define the optimal solutions. The present work proposed a comprehensive automatic non-rigid video set registration algorithm using Demons algorithm. For optimal velocity smoothing kernels, the demons registration is optimized using cuckoo search (CS) algorithm, where there are no previous studies that have optimized demons algorithm using CS algorithm. A comparison between the CS algorithm and the particle swarm optimization (PSO)-based demons registration is conducted to evaluate the proposed system performance. Thus, the correlation coefficient is taken as a fitness function. The obtained results using CS show a minor increment of the optimized fitness value compared to PSO-based framework value. The proposed CS-based approach reports faster convergence rate than the PSO-based approach.

A Bayesian hierarchy for robust gaze estimation in human–robot interaction

In this text, we present a probabilistic solution for robust gaze estimation in the context of human–robot interaction. Gaze estimation, in the sense of continuously assessing gaze direction of an interlocutor so as to determine his/her focus of visual attention, is important in several important computer vision applications, such as the development of non-intrusive gaze-tracking equipment for psychophysical experiments in neuroscience, specialised telecommunication devices, video surveillance, human–computer interfaces (HCI) and artificial cognitive systems for human–robot interaction (HRI), our application of interest. We have developed a robust solution based on a probabilistic approach that inherently deals with the uncertainty of sensor models, but also and in particular with uncertainty arising from distance, incomplete data and scene dynamics. This solution comprises a hierarchical formulation in the form of a mixture model that loosely follows how geometrical cues provided by facial features are believed to be used by the human perceptual system for gaze estimation. A quantitative analysis of the proposed framework's performance was undertaken through a thorough set of experimental sessions. Results show that the framework performs according to the difficult requirements of HRI applications, namely by exhibiting correctness, robustness and adaptiveness.

Anthropomorphic grasp generation through probabilistic modelling in an optimised eigen‐space

Artificial cognitive systems are increasingly drawn towards ‘human-like’ gestural exhibits while performing various manipulative acts. Representing such actions in a natural settings requires temporal extractions of their grasp progressions. A novel optimisation-based hidden Markov framework is offered, to generate natural hand prehensions through maximisation of a composite grasp function built of individual finger trajectory likelihoods. In order to produce the desired motion in an intuitive framework, the final grasp frame (represented in terms of standard discriminants z ∈ ℜ2 in a condensed grasp eigen-space) is extended in a temporal sequence by equi-spaced increments of z, over their conventional joint-space representations.

Guest Editorial Cognitive Agents and Robots for Human-Centered Systems

A current challenge for artificial cognitive systems is to acquire the capability to freely interact with humans in such a way that the burden of learning and adaptation lies with the machine and not with the human. This special issue presents a variety of recent developments in artificial cognitive agents, embedded in human-centric environments, with a particular focus on robotic applications. It aims to capture potential multidisciplinary research directions in order to further expand artificial system capabilities in an open-ended process while socially interacting in real environments for the humans’ benefit.

A computational analysis of general intelligence tests for evaluating cognitive development

The progression in several cognitive tests for the same subjects at different ages provides valuable information about their cognitive development. One question that has caught recent interest is whether the same approach can be used to assess the cognitive development of artificial systems. In particular, can we assess whether the ‘fluid’ or ‘crystallised’ intelligence of an artificial cognitive system is changing during its cognitive development as a result of acquiring more concepts? In this paper, we address several IQ tests problems (odd-one-out problems, Raven’s Progressive Matrices and Thurstone’s letter series) with a general learning system that is not particularly designed on purpose to solve intelligence tests. The goal is to better understand the role of the basic cognitive operational constructs (such as identity, difference, order, counting, logic, etc.) that are needed to solve these intelligence test problems and serve as a proof-of-concept for evaluation in other developmental problems. From here, we gain some insights into the characteristics and usefulness of these tests and how careful we need to be when applying human test problems to assess the abilities and cognitive development of robots and other artificial cognitive systems.

Evaluation of uncertainty in the measurement of sense of natural language constructions

The task of evaluating uncertainty in the measurement of sense in natural language constructions (NLCs) was researched through formalization of the notions of the language image, formalization of artificial cognitive systems (ACSs) and the formalization of units of meaning. The method for measuring the sense of natural language constructions incorporated fuzzy relations of meaning, which ensures that information about the links between lemmas of the text is taken into account, permitting the evaluation of two types of measurement uncertainty of sense characteristics. Using developed applications programs, experiments were conducted to investigate the proposed method to tackle the identification of informative characteristics of text. The experiments resulted in dependencies of parameters being obtained in order to utilise the Pareto distribution law to define relations between lemmas, analysis of which permits the identification of exponents of an average number of connections of the language image as the most informative characteristics of text.

On evolution of thinking about semiosis: semiotics meets cognitive science

The aim of the paper is to sketch an idea—seen from the point of view of a cognitive scientist—of cognitive semiotics as a discipline. Consequently, the article presents aspects of the relationship between the two disciplines: semi- otics and cognitive science. The main assumption of the argumentation is that at least some semiotic processes are also cognitive processes. At the methodo- logical level, this claim allows for application of cognitive models as explana- tions of selected semiotic processes. In particular, the processes of embedded interpretation (in contrast to interpretability in principle) are considered: belief revision, dynamic organization of meaning and metaknowledge. The explanations are formulated in terms of artificial cognitive agents of the GLAIR/SNePS cognitive architecture. Finally, it is suggested that even if some- one rejects the idea of artificial cognitive systems as simulations of semiotic processes, they may acknowledge the usefulness of cognitive modeling in analysis of semiotic processes in virtual, simulated worlds and in the area of “new media”.

Developing Dynamic Field Theory Architectures for Embodied Cognitive Systems with cedar.

Embodied artificial cognitive systems, such as autonomous robots or intelligent observers, connect cognitive processes to sensory and effector systems in real time. Prime candidates for such embodied intelligence are neurally inspired architectures. While components such as forward neural networks are well established, designing pervasively autonomous neural architectures remains a challenge. This includes the problem of tuning the parameters of such architectures so that they deliver specified functionality under variable environmental conditions and retain these functions as the architectures are expanded. The scaling and autonomy problems are solved, in part, by dynamic field theory (DFT), a theoretical framework for the neural grounding of sensorimotor and cognitive processes. In this paper, we address how to efficiently build DFT architectures that control embodied agents and how to tune their parameters so that the desired cognitive functions emerge while such agents are situated in real environments. In DFT architectures, dynamic neural fields or nodes are assigned dynamic regimes, that is, attractor states and their instabilities, from which cognitive function emerges. Tuning thus amounts to determining values of the dynamic parameters for which the components of a DFT architecture are in the specified dynamic regime under the appropriate environmental conditions. The process of tuning is facilitated by the software framework cedar, which provides a graphical interface to build and execute DFT architectures. It enables to change dynamic parameters online and visualize the activation states of any component while the agent is receiving sensory inputs in real time. Using a simple example, we take the reader through the workflow of conceiving of DFT architectures, implementing them on embodied agents, tuning their parameters, and assessing performance while the system is coupled to real sensory inputs.