Figure - available from: Artificial Intelligence Review
This content is subject to copyright. Terms and conditions apply.
Two taxonomic levels are distinguished: Building level for every theoretical and intentional aspect to achieve meta-architectural foundations, and Operational level for those aspects developed to solve specific tasks

Two taxonomic levels are distinguished: Building level for every theoretical and intentional aspect to achieve meta-architectural foundations, and Operational level for those aspects developed to solve specific tasks

Source publication
Article
Full-text available
In the field of Artificial Intelligence (AI), efforts to achieve human-like behavior have taken very different paths through time. Cognitive Architectures (CAs) differentiate from traditional AI approaches, due to their intention to model cognitive and behavioral processes by understanding the brain’s structure and their functionalities in a natura...

Similar publications

Preprint
Full-text available
Over the past decades, research in cognitive and affective neuroscience has emphasized that emotion is crucial for human intelligence and in fact inseparable from cognition. Concurrently, there has been a significantly growing interest in simulating and modeling emotion in robots and artificial agents. Yet, existing models of emotion and their inte...

Citations

... A comparative analysis of the cognitive architectures of Cyc, Soar, Society of Mind and Neurocognitive Networks is given in [13], ACT-R, Epic, Soar in [12], ACT-R, ICARUS, PRODIGY in [15], ACT-R, Soar, LIDA, SiMA, NEF (SPAUN), iCub, SEMLINCS, Summary in [20]; ACT-R, Soar, NARS, OSCAR, AKIRA, CLARION, LIDA and Ikon Flux in [17]; Soar, ACT-R, EPIC, Clarion in [14], SOAR, ACT-R, CLARION and Vector-LIDA in [21]. ...
Full-text available
Preprint
This paper questions the feasibility of a strong (general) data-centric artificial intelligence (AI). The disadvantages of this type of intelligence are discussed. As an alternative, the concept of co-evolutionary hybrid intelligence is proposed. It is based on the cognitive interoperability of man and machine. An analysis of existing approaches to the construction of cognitive architectures is given. An architecture seamlessly incorporates a human into the loop of intelligent problem solving is considered. The article is organized as follows. The first part contains a critique of data-centric intelligent systems. The reasons why it is impossible to create a strong artificial intelligence based on this type of intelligence are indicated. The second part briefly presents the concept of co-evolutionary hybrid intelligence and shows its advantages. The third part gives an overview and analysis of existing cognitive architectures. It is concluded that many do not consider humans part of the intelligent data processing process. The next part discusses the cognitive architecture for co-evolutionary hybrid intelligence, providing integration with humans. It finishes with general conclusions about the feasibility of developing intelligent systems with humans in the problem-solving loop.
... This article proposes a computational bioinspired model of IV learning, which emphasizes the setup, recovery, and updating of the IV associated with the smell stimulus perceived based on the MS using Pavlovian conditioning. To achieve this proposal, we follow the methodology proposed in [12]. First, we review neuroscientific studies to understand how the human brain carries out the ILP. ...
Article
Nowadays, the general artificial intelligence field aims to emulate some human behavior features in computational models for different objectives. This article proposes a model grounded in neurosciences focusing on individual behavior under appetitive circumstances. Environmental stimuli inspire human behavior because they represent a (learned) incentive value (IV) linked to the satisfaction of motivational states (MSs). That is, the expected behavior is goal-directed. We describe the generation of the incentive learning process. To reach this objective, we propose a computational-bioinspired model exemplifying the IV encoding process of a perceived smell stimulus for its setup, recovery and updating using Pavlovian conditioning. The proposed model highlights the main processes involved in Pavlovian incentive learning (PIL) and complementaries, e.g., an early integration between a smell stimulus and an MS, the generation of a temporal reward history, the prediction of a reward, the calculation of the obtained reward, the evaluation of reward error, among others. The model’s functionality was validated in two phases: the first stage was the acquisition of the IV and the second stage was a go/nogo task based on an incentive value and its MS.
... As Marvin Minsky quoted, "To get around these constraints, we must develop systems that combine the expressiveness and procedural versatility of symbolic systems with the fuzziness and adaptiveness of connectionist representations". The theoretical concepts and advancement of cognitive architecture make it a solid option for the representation and modelling of intelligent behaviours, but there is still the question of how precise existing representations are to correctly reflect human cognitive processes [10,11]. ...
Full-text available
Article
This study approaches adaptability for mobility assistive technologies by proposing an adaptable framework for mobility assistive technologies, inspired by ACT-R, the desiderata for developing cognitive architectures as highlighted by R. Sun and Vernon et al. and human behaviour. This study proposes an adaptable framework for shared control and autonomous mobility as the first step towards the formation of a comprehensive adaptive framework. This study proposes a minimalist four-module adaptive framework consisting of the perception/motor module, the cognitive module, the memory module, and the action module. The minimum requirements for the implementation of this framework on an intelligent wheelchair for shared/collaborative control were highlighted. Although an overview of the proposed adaptive framework for mobility assistive technologies was presented, there are still numerous concerns to address. One of the main issues remains the most suitable connectionist and symbolic process to be used in the hybrid framework, which will be investigated in future work. In addition, it is still essential to resolve details of the adaptation/learning process in the framework, so it will be necessary to develop learning mechanisms in cooperation with reward systems as well as observation/inference systems for the framework.
... We conclude by showing the types of information flow inside the model. Overall, the proposed model is developed following the methodology for cognitive architecture construction proposed by Jiménez et al. [138]. ...
Full-text available
Article
Episodic memory and emotions are considered essential functions in human cognition. Both allow us to acquire new knowledge from the environment, ranging from the objects around us to how we feel towards them. These qualities make them crucial functions for systems trying to create human-like behaviour. In the field of cognitive architectures (CAs), there are multiple studies covering memory and emotions. However, most of them treat these subjects in an isolated manner, considering emotions only as a reward signal unrelated to a retrieved experience. To address this lack of direct interaction, we propose a computational model that covers the common processes that are related to memory and emotions. Specifically, this proposal focuses on affective evaluations of episodic memories. Neurosciences and psychology are the bases of this model. That is, the model’s components and the processes that they carry out on the information they receive are designed based on evidence from these cognitive sciences. The proposed model is a part of Cuáyóllótl, a cognitive architecture for cybernetic entities such as virtual creatures and robots. Case studies validate our proposal. They show the relevance of the integration of emotions and memory in a virtual creature. The virtual creature endowed with our emotional episodic model improves its learning and modifies its behaviour according to planning and decision-making processes.
... Newell's initial approach is based mainly on psychological evidence [11]. Currently, the components of some bioinspired CAs or BICAs, represent human cognitive functions grounded in different disciplines, for instance, psychology, neuroscience and philosophy, among others [12]. The appropriate work of these cognitive functions generates intelligent, human-like behavior [13]. ...
... For the development of this work, we used a combination of methodologies. The first is the methodology for the construction of cognitive architectures [12] where we focus on the main flow. The first step is making a general definition of the system we want; this includes the context it is implemented, the applicability and the abilities desired for the system. ...
Full-text available
Article
Pervasive service composition is useful in many scenarios, for instance, in urban planning or controlled harvest. Currently, there is no standard to develop solutions using pervasive service composition. However, big companies propose their frameworks to develop complex services, but their frameworks are appropriate in specific applications, such as home automation and agriculture. On the other hand, there are different very well-grounded academic proposals for pervasive service composition. However, these do not solve the problems of traditional approaches that are appropriate to specific areas of application, and adaptation is needed to deal with the dynamism of the environment. This article presents a cognitive approach for pervasive service composition where InfoCom devices and the implementation of cognitive functions interact to create pervasive composite services. Our central hypothesis is that cognitive theory can help solve actual problems requiring pervasive service composition, as it addresses the above-mentioned problems. To test our approach, in this article we present a case of urban insecurity. Specifically, in different countries, street robbery using firearms is one of the problems with a high impact because of its frequency. This article proposes to compose a pervasive service for deterring criminals from committing their crimes. The results obtained by simulating our proposal in our case study are promising. However, more research needs to be achieved before applying the proposed approach to actual problems. The research needed ought to address various problems, some of which are discussed in this article.
... This work's objective is to propose and implement a bioinspired cognitive model of learning by imitation, based on psychological and neuroscientific evidence by following the methodology proposed in (Jiménez, Martin, Dounce, Á vila-Contreras, & Ramos, 2020). To test our proposal, we endow a virtual creature with our implementation. ...
Article
Learning, and even more so by imitation, is an essential Cognitive Functions because it is carried out throughout life and allows us to adapt our behaviors from other beings through observation. In this work, we propose a model, and implementation of the cognitive function of imitation motor learning (IML), based on psychological and neuroscientific evidence. According to the evidence, learning by imitation includes imitation of action and imitation of action over an object sub-processes. The imitation of action consists of the movement of the limbs. The imitation of action over an object consists of the interaction with an object within the environment. We achieve an implementation of the proposed model for IML and endow a virtual entity with it. In order to validate the proposal, we use a case study to analyze the sub-processes performance. From results, we conclude that both imitation of action and imitation of action over an object sub-processes play an essential role in getting the agent to interact with stimuli within the environment.
... And we conclude by showing the types of information flow inside the model. It is worth to notice that the design stages presented in this section were established by following the methodology proposed in (Jiménez, Martin, Dounce, Á vila-Contreras, & Ramos, 2020). ...
Article
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.
Article
Обеспечение высокой экономичности не только на режимах номинальной мощности, но и на частичных режимах при изменении внешних параметров приводит к необходимости оптимизации проточной части турбины с объективным учетом ее характеристик на переменных режимах. Приводятся результаты многорежимной оптимизации МРТ в составе ЭУ АНПА на базе подхода разработанного авторами. Представлены основные результаты сравнительного анализа многорежимной оптимизации МРТ с оптимизацией на i-тый режим и работающей на остальных режимах как переменных для различных программ регулирования мощности. Выявлено сильное влияние на результаты многорежимной оптимизации основного ограничения в виде равенства мощности турбины мощности задаваемой графиком нагрузки, а также программ регулирования. Возможность применения соплового регулирования приводит к ослаблению степени воздействия основного ограничения. Установлено, что оптимальные геометрические характеристики стремятся к режиму с большей работой. Представлены результаты многорежимной оптимизации МРТ для различных программ регулирования и графиков нагрузок по отношению к результатам многорежимной оптимизации с программой реализующей сопловое регулирование в сочетании с изменением начальных параметров перед турбиной. Многорежимная оптимизация для программы, реализующей сопловое регулирование в сочетании с изменением только начальной температуры перед турбиной, выявила узкую регулировочную способность начальной температуры, и невозможность в некоторых случаях удовлетворения основным ограничениям по равенству мощностей для всех исследуемых графиков нагрузки в пределах заданных ограничений на режимные параметры. Результаты численного эксперимента свидетельствуют, что разработанный автором подход к многорежимной оптимизации МРТ позволяет снизить расход топлива при условии обеспечения заданного графика нагрузок по сравнению с традиционными методами проектирования на номинальный режим. Ensuring high efficiency not only at nominal power modes, but also at partial modes when changing external parameters leads to the need to optimize the flow path of the turbine with objective consideration of its characteristics at variable modes. The results of multi-mode optimization of a low-consumption turbine as part of a power unit of remotely operated underwater vehicle based on the approach developed by the authors are presented. The main results of a comparative analysis of multi-mode optimization of a low-consumption turbine with optimization for the i-mode and operating in other modes as variables for various power control programs are presented. A strong influence on the results of multi-mode optimization of the main limitation in the form of equality of the turbine power to the power set by the load schedule, as well as control programs is revealed. The possibility of using nozzle regulation leads to a weakening of the degree of influence of the main restriction. It was found that the optimal geometric characteristics tend to the regime with more work. The results of multi-mode optimization of a low-consumption turbine for various control programs and load schedules are presented in relation to the results of multi-mode optimization with a program that implements nozzle control in combination with a change in the initial parameters in front of the turbine. Multimode optimization for a program that implements nozzle regulation in combination with changing only the initial temperature in front of the turbine revealed a narrow adjusting ability of the initial temperature and the impossibility, in some cases, of satisfying the basic constraints on the equality of powers for all the studied load curves within the specified constraints on operating parameters. The results of the numerical experiment indicate that the approach developed by the author to the multi-mode optimization of a low-consumption turbine makes it possible to reduce fuel consumption, provided that a given load schedule is provided in comparison with traditional design methods for the nominal mode.
Article
В настоящей работе дано описание многопоточной параллельной организации работы алгоритмов, входящих в состав программной части подводной системы технического стереозрения подводного робота. Данные, полученные системой технического стереозрения, в последствии поступают на систему управления для выполнения операций по управлению роботом и оператору на экран монитора для последующего принятия им управленческих решений. В большинстве случаев выполнение алгоритмов происходит последовательно. Суммарное время обработки одного кадра складывается из времени работы всех алгоритмов, входящих в состав программной части. Таким образом, в однопоточном режиме даже самые быстрые алгоритмы будут ожидать своей очереди на выполнение. Следовательно, система управления и оператор в случаях, требующих большие вычислительные мощности, будут получать данные недостаточно быстро. Естественно для увеличения быстродействия всей программной части возникает потребность организовать работу входящих в состав алгоритмов параллельно, многопоточно, но такой способ организации работы дополнительно создаёт ряд проблем, которых бы не было, если работа алгоритмов была организована последовательно, однопоточно. В статье приведены способы решения этих проблем, проведено сравнение времени работы многопоточной и однопоточной реализации алгоритмов. This paper describes the multithreaded parallel organization of the algorithms that are part of the software of the underwater system of technical stereo vision of an underwater robot. The data obtained by the technical stereo vision system is subsequently transmitted to the control system to perform robot control operations and to the operator on the monitor screen for subsequent management decisions. In most cases, the algorithms are executed sequentially. The total processing time of one frame consists of the operating time of all algorithms included in the software part. Thus, in single-threaded mode, even the fastest algorithms will be waiting for their turn to execute. Consequently, the control system and the operator in cases requiring large computing power will not receive data quickly enough. Naturally, in order to increase the speed of the entire software part, there is a need to organize the work of the algorithms included in parallel, multithreaded, but this way of organizing work additionally creates a number of problems that would not exist if the algorithms were organized sequentially, single-threaded. The article presents ways to solve these problems, compares the operating time of multithreaded and single-threaded implementation of algorithms.
Article
Статья посвящена разработке методики проектирования однофазного асинхронного электродвигателя без внешних фазосдвигающих устройств для систем судовой автоматики. Отмечается, что существующие на сегодняшний день известные методики расчёта микромашин не учитывает потерь в стали, что приводит к значительным погрешностям при расчёте двигателя. Авторами предлагается применять разработанную уточненную методику расчёта двигателя для дальнейшего его проектирования. Отмечается, что из выявленных в работе зависимостей важнейшей является зависимость пускового момента от электрического угла между осями обмоток 1 и 44 - α. Где выбор не оптимального электрического угла - крайне негативно сказывается на величине пускового момента однофазной микромашины. Для пояснения особенностей определения активной части двигателя авторами строится график зависимости наружной поверхности и потерь от полезной мощности. Также, в статье авторы приводят номограммы, позволяющие принимать проектировочные решения не только на основания расчёта, но и графоаналитическим методом. Результатом работы является получение новой методики расчёта и проектирования однофазной микромашины для систем судовой автоматики, используя для расчёт математическую модель, полученную с помощью методов планирования эксперимента. The article is devoted to the development of a design technique for a single-phase asynchronous electric motor without external phase-shifting devices for ship automation systems. It is noted that the currently known methods for calculating micromachines do not take into account losses in steel, which leads to significant errors in calculating the engine. The authors propose to apply the developed refined methodology for calculating the engine for its further design. It is noted that of the dependences identified in the work, the most important is the dependence of the starting torque on the electric angle between the axes of the windings 1 and 44 - α. Where the choice of a non-optimal electrical angle has an extremely negative effect on the magnitude of the starting torque of a single-phase micromachine. To clarify the features of determining the active part of the engine, the authors build a graph of the dependence of the outer surface and losses on the net power. Also, in the article, the authors provide nomograms that allow making design decisions not only on the basis of calculation, but also by the graphical analytical method. The result of the work is to obtain a new methodology for calculating and designing a single-phase micromachine for ship automation systems, using for the calculation a mathematical model obtained using experimental planning methods.