Cognitive Robotics

This study presents the development of an intelligent autonomous mobile robot system for object detection and classification using the combination of Faster Regional-Convolutional Neural Network (R-CNN) with a Double Deep Q-Learning Network (DDQN) for decision-making in a dynamic environment. The system adopts the Open ImageV5 dataset for testing and training, improving model performance through the use of strong preprocessing and augmentation methods. While the DDQN allows for optimum path planning and manoeuvring decisions in stochastic mobility circumstances, the faster R-CNN guarantees excellent detection accuracy by improving object categorisation and bounding box predictions. The suggested concept was put into practice and assessed in a gaming environment that mimics actual circumstances. The results presents a consistent performance in braking and stopping distances, a processing speed of 5-10 frames per second, and good detection accuracy (90-95%). The system's generalisability and dependability were confirmed using a 5-fold cross-validation approach, which also confirmed that it is appropriate for real-time applications. With applications in robotic systems, security, and environmental monitoring, this study demonstrates the possibility of combining deep learning with reinforcement learning for autonomous navigation.

This study presents the development of an intelligent autonomous mobile robot system for object detection and classification using the combination of Faster Regional-Convolutional Neural Network (R-CNN) with a Double Deep Q-Learning Network (DDQN) for decision-making in a dynamic environment. The system adopts the Open ImageV5 data-set for testing and training, improving model performance through the use of strong preprocessing and augmentation methods. While the DDQN allows for optimum path planning and manoeuvring decisions in stochastic mobility circumstances, the faster R-CNN guarantees excellent detection accuracy by improving object categorisation and bounding box predictions. The suggested concept was put into practice and assessed in a gaming environment that mimics actual circumstances. The results presents a consistent performance in braking and stopping distances, a processing speed of 5-10 frames per second, and good detection accuracy (90-95%). The system's generalisability and dependability were confirmed using a 5-fold cross-validation approach, which also confirmed that it is appropriate for real-time applications. With applications in robotic systems, security, and environmental monitoring, this study demonstrates the possibility of combining deep learning with reinforcement learning for autonomous navigation.

This document presents a structured questionnaire and prompt library (SQPL) designed to facilitate methodical, logic-driven exploration of the Morphean Framework. The SQPL addresses common pitfalls in both human and AI analysis, such as fast assumptions, semantic shortcuts, and fragmented interpretation, while promoting stepwise logical reconstruction, frame-shifting, and cross-domain synthesis. By integrating modules for grounding definitions, auditing assumptions, probing perception and subconscious patterns, and reconstructing logic paths, the SQPL enables users to systematically extract atomic claims, identify dependencies, and assess coherence. In addition, it provides a protective framework for analyzing AI or human reasoning by incorporating principles from ethics, cognition, and harmonic system design. This tool offers a comprehensive methodological approach for understanding complex, multi-scale frameworks that combine physics, consciousness studies, ethics, and computational intelligence, emphasizing logic and internal coherence over immediate validation or mainstream conformity. 
publised : 9/24/2025

In this paper, we present some topics to improve the use of Robotics in teaching, with a new approach of Embodied Cognitive Science (ECS) (Gomez Paloma, 2013) in order to facilitate learning of all students. The notion of simulation (Gallese, 2005b; 2009) has assumed a central role in the theories of the embodied cognition; in particular, it’s made reference to the motor simulation during the observation of objects or people performing an action, and the comprehension of a language. The learning experience with the robot is characterized as a relational experience that is essentially different fromthat with a computer or another electronic device. Attention for body and movement through Robotics stimulates development of basic skills and capacity for learning, as visuo- spatial, visuo-motory and social skills; these skills are very important for students, especially for students with Special Educational Needs.L’articolo presenta alcuni argomenti connessi all’utilizzo della robotica ...

This study aimed at finding out whether artificial intelligence generated pictures can increase the amount of language produced by intermediate EFL learners. To this end, sixty Iranian EFL student with an age range of 18 to 25 were selected through convenient sampling method. The aforementioned participants were studying in four different classes, two of which were assigned as the experimental group and the other two ones as the control group. In the activation stage of the lesson, the first group was given some imaginary pictures which have been made by artificial intelligence while the second group used some real pictures downloaded from the internet. The data was gathered on the number of sentences produced by each group. Finally, the data analyzed using independent t-test indicated that the use of artificial intelligence in language learning process led a salient increase in language production. Moreover, the results have pedagogical implications which could be applicable and beneficial in the field of language learning and teaching.

Use your device to scan and read the article online Objectives With the growth in the aged population and the increase in the health needs of older people, new challenges have been raised for the health care systems. Therefore, advanced methods for management of the health needs of older adults is needed. Artificial intelligence (AI) can play an effective role in this field. The present study aims to investigate the different applications of AI in geriatric care management. Methods & Materials The is a qualitative review study using the meta-synthesis approach. The related articles were searched in national and international databases. The identified data were coded and analyzed in MAXQDA software, version 2020. Results A total of 25 articles were selected for the review. From 122 initial codes, 8 main themes, 21 subthemes or concepts, and 42 indicators were extracted. The main themes included prediction and prevention of diseases, management of chronic diseases, organization and sorting of medications, smart home monitoring, online communication with doctors, car assistance systems, health service management, and psychological support. Conclusion The AI technology can be used to manage the health needs of older adults. Its different applications should be taken into consideration in geriatric care management.

In activity recognition, sensor based errors or uncertainties induce a wrong statement in the environment representation. To overcome these issues we introduce our ontology-based approach where a system, based on a mobile robot and an ambient system, is able to generate collaborative tasks when necessary to recognize activities. Using two ontologies to represent the environment, inconsistencies are detected and high level data are exchanged between both systems to correct and clarify ambiguous description of the environment. This process allows to generate adequate clarifying tasks by explicitly including knowledge and capabilities of each system. We expose our approach in two experiments where interaction between both systems are mandatory to respond a human "find an object" request in a first scenario and recognize multi user activities in a second scenario.

In activity recognition, sensor based errors or uncertainties induce a wrong statement in the environment representation. To overcome these issues we introduce our ontology-based approach where a system, based on a mobile robot and an ambient system, is able to generate collaborative tasks when necessary to recognize activities. Using two ontologies to represent the environment, inconsistencies are detected and high level data are exchanged between both systems to correct and clarify ambiguous description of the environment. This process allows to generate adequate clarifying tasks by explicitly including knowledge and capabilities of each system. We expose our approach in two experiments where interaction between both systems are mandatory to respond a human ”find an object” request in a first scenario and recognize multi user activities in a second scenario.

Since the emergence of articles by GE Alexander and his colleagues on basal ganglia-thalamacortical circuits in 90's, there has been a series of work discussing the roles of cortico-striato-thalamo-cortico circuits in different cognitive, motor processes and in emotional behaviours [1-6]. There are also some works investigating the role of cortico-striato-thalamo-cortico circuits especially for conscious behaviour and even discussing the functions of neural correlates in perceiving the one's own movements [7-9].

Cognitive robots have started to find their way into manufacturing halls. However, the full potential of these robots can only be exploited through an integration into the automation pyramid so that the system is able to communicate with the manufacturing execution system (MES). Integrating the robot with the MES allows the robot to get access to manufacturing environment and process data so that it can perform its task without human intervention. This paper describe the mobile robotic manipulator developed in the EU project STAMINA, its has been integrated with an existing MES and its application in a kitting task from the automotive industry.

With the development of Internet of Things (IoT), IoT intelligence becomes emerging technology. "Curse of Dimensionality" is the barrier of data fusion in edge devices for the success of IoT intelligence. Deep learning has attracted great attention recently, due to the successful applications in several areas, such as image processing and natural language processing. However, the success of deep learning benefits from GPU computing. A Linguistic Attribute Hierarchy (LAH), embedded with Linguistic Decision Trees (LDTs) can represent a new attribute deep learning. In contrast to the conventional deep learning, an LAH could overcome the shortcoming of missing interpretation by providing transparent information propagation through the rules, produced by LDTs in the LAH. Similar to the conventional deep learning, the computing complexity of optimising LAHs blocks the applications of LAHs. In this paper, we propose a heuristic approach to constructing an LAH, embedded with LDTs for decision making or classification by utilising the distance correlations between attributes and between attributes and the goal variable. The set of attributes is divided to some attribute clusters, and then they are heuristically organised to form a linguistic attribute hierarchy. The proposed approach was validated with some benchmark decision making or classification problems from the UCI machine learning repository. The experimental results show that the proposed self-organisation algorithm can construct an effective and efficient linguistic attribute hierarchy. Such a self-organised linguistic attribute hierarchy embedded with LDTs can not only efficiently tackle 'curse of dimensionality' in a single LDT for data fusion with massive attributes, but also achieve better or comparable performance on decision making or classification, compared to the single LDT for the problem to be solved. The self-organisation algorithm is much efficient than the Genetic Algorithm in Wrapper for the optimisation of LAHs. This makes it feasible to embed the self-organisation algorithm in edge devices for IoT intelligence.

The advancements in healthcare technology have transformed the landscape of medical practice, with robotics emerging as a prominent feature. The use of teleoperation, particularly in remote robot-assisted surgeries, has obtained significant attention and acclaim for its potential to enhance surgical outcomes and expand access to specialized care. Despite the increase in research in this domain, there remains a need for a thorough and systematic review to consolidate the diverse findings and conclusions. This work presents an organized synthesis of existing related works using Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA), facilitating easier access to vital information for researchers, practitioners, and innovators. To achieve this, the historical development of surgical robots were explored. Furthermore, different types of surgical robots with various architecture were extensively examined to highlight the relevance of their application. Imperatively, advancements in teleoperability and control systems of surgical robots were comprehensively discussed underscoring its growing influence in current healthcare delivery. Moreover, practical challenges faced by teleoperated surgical robots were highlighted and elaborated to point out their limitations. Additionally, future directions aimed to tackle the identified shortfalls in robotic surgery and teleoperation were considered. In this regard, this work provided an impactful contribution that positively influences growth in the area of robotic surgery and teleoperation by consolidating several insights into a cohesive framework which ultimately seek to improve patient care.

In this conceptual analysis contribution to the special issue on radical embodied cognition, we discuss how embodied cognition can exist with and without representations. We explore this concept through the lens of judgment and decision-making in sports (JDMS). Embodied cognition has featured in many investigations of human behavior, but no single approach has emerged. Indeed, the very definitions of the concepts "embodiment" and "cognition" lack consensus, and consequently the degree of "radicalism" is not universally defined, either. In this paper, we address JDMS not from a rigid theoretical perspective but from two embodied cognition approaches: one that assumes there is mediation between the athlete and the environment through mental representation, and another that assumes direct contact between the athlete and the environment and thus no need for mental representation. Importantly, our aim was not to arrive at a theoretical consensus or set up a competition between approaches but rather to provide a legitimate scientific discussion about how to explain empirical results in JDMS from contrasting perspectives within embodied cognition. For this, we first outline the definitions and constructs of embodied cognition in JDMS. Second, we detail the theory underlying the mental representation and direct contact approaches. Third, we comment on two published research papers on JDMS, one selected by each of us: (1) Correia et al. ( ) and ( ) Pizzera (2012). Fourth, following the interpretation of the empirical findings of these papers, we present a discussion on the commonalities and divergences of these two perspectives and the consequences of using one or the other approach in the study of JDMS.

This paper details and discusses work performed at the woodworking SME Mivelaz Techniques Bois SA within the SME-robotics FP7 project. The aim is to improve non-expert handling of the cell by introduction of cognitive abilities in the robot system. Three areas are considered; intuitive programming, process adaptation and system integration. Proposed cognitive components are described together with experiments performed.

Contemporary Artificial Intelligence and other computational systems—from machine learning models and large language models to autonomous agents and predictive simulations—usually handle time in a tenseless manner, treating past, present, and future data points as uniform elements of a timeline. They lack an explicit ontology of the present (what exists now), becoming (how the present continually updates from potential to actual), and temporal asymmetry (the one-way flow of causality from past to future). This paper proposes that Existential Realism (ER), an ontological framework distinguishing existence (entities in the present moment) from reality (a broader set including causally or informationally relevant past and future entities), can enrich the way technological systems model time. We argue that by incorporating ER’s present-centered, two-tier view of time, machines could become more temporally-aware and responsible in their decision-making. We detail key ER concepts—such as the primacy of the present, the reality of the non-present, truthmaking, and the idea of a real-but-not-yet-existent future—and map them onto machine-level analogues like sensor inputs (the machine’s “existence”), memory traces, simulation states, and predictive models. ER provides a structured approach for machines to: distinguish what exists now from what is merely remembered or anticipated; represent future states as real but not yet existent, enabling ethical foresight; anchor predictions in current data while reasoning about long-term consequences; and avoid temporal fallacies like treating the future as fixed or erasing the influence of the past. Through examples in climate modeling, medical diagnostics, robotics, and Artificial Intelligence ethics, we illustrate how an ER-informed system could better navigate time-sensitive tasks—e.g. by understanding that only the present sensor data is actual, that past data (though no longer existent) remains real evidence, and that future scenarios (though not yet actualized) demand present attention. We also draw on existing literature in philosophy and cognitive science to show that ER’s framework aligns with how humans experience time (through memory and anticipation) and how ethical reasoning already extends reality to future generations. In sum, Technology and the Reality of the Present-Centered Machine outlines an interdisciplinary vision: embedding a philosophically robust, present-centered temporal ontology into our technologies to foster more prudent, transparent, and temporally-grounded intelligent systems.

In this paper, we consider the problem of mobile robots navigating in environments with non-rigid objects. Whereas robots can plan their paths more effectively when they utilize the information about the deformability of objects, they also need to consider the influence of the interaction with the deformable objects on their measurements during the execution of their navigation task. In this paper, we present a probabilistic approach to identify the measurements influenced by the deformable objects. Based on a learned statistics about the influence of the deformable objects on the measurements, the robot is able to perform a sensor-based collision avoidance of unforeseen objects. We present experiments carried out with a real robot that illustrate the practicability of our approach.

GORAN TRAJKOVSKI, GEORGI STOJANOV, SAMUEL COLLINS , VLADIMIR EIDELMAN, CHRIS. HARMAN AND GIOVANNI VINCENTI 1 Computer and Information Sciences Department, Towson University, 8000 York Road, Towson, MD 21252, USA, E-mail: {gtrajkovski, gvince1}@towson.edu, Phone 1-410704-6310, Fax 1-410-704-3868 2 Department of Computer Science, Mathematics and Science, American University in Paris, 147, Rue de Grenelle, Paris 75007, France, E-mail: gstojanov@aup.fr 3 Department of Sociology, Anthropology and Criminal Justice, Towson University, 8000 York Road, Towson, MD 21252, USA, E-mail: scollins@towson.edu 4 Computer Science Department, Columbia University, 2960 Broadway, New York, NY 10027, USA, E-mail: vae2101@columbia.edu 5 Computer Science Department, Swarthmore College, 500 College Ave, Swarthmore, PA 19081, USA, E-mail: charman1@swarthmore.edu

Robotic manipulation in small and medium-sized enterprises (SMEs) is challenged by high product variability, small lot sizes, and frequent task reconfigurations. Under these conditions, traditional data-driven grasp planning methods are often infeasible due to their reliance on large, annotated datasets and stable object libraries. This paper presents an architecture for ontology-based semantic grasp planning that enables efficient and intuitive manual grasp pose specification without requiring extensive expertise in geometric programming or machine learning. By leveraging semantic representations of object geometries, gripper capabilities, and task-specific constraints, the system supports context-aware grasp candidate generation and prioritization. While the interpretation of the semantic models identifies suitable grasp types and involved geometric faces of objects and grippers, an optimization step generates suitable 6D poses that meet given constraints. As a result, the complexity of manually instructing robot systems for manipulation tasks is reduced and can be efficiently carried out by non-expert users.

Brushless DC (BLDC) motors are widely used in industrial applications due to their high efficiency and performance. However, accurately predicting key parameters such as torque and speed remains a challenge because of the motor's inherently nonlinear dynamics. This study presents a data-driven modeling approach using a Nonlinear Autoregressive Neural Network with Exogenous Inputs (NARX-NN) to predict the torque and speed of a BLDC motor. Input-Output data were obtained from a Simulink-based BLDC motor model under varying input voltages and load conditions. The proposed NARX-NN architecture was trained on this data, effectively learning the nonlinear Multi-Input Multi-Output (MIMO) system dynamics. The model achieved high prediction accuracy, with a Mean Squared Error (MSE) of 3.4162e-04 (training), 3.0296e-04 (validation) and 8.4225e-04 (testing) while R-values of 1 in each in case of speed. While the model also achieved high prediction accuracy, with a Mean Squared Error (MSE) of 0.0062 (training and validation), and 0.0065 (testing) while R-values of 0.9997 (training and validation) and 0.9998 (testing) in case of torque. These statistical results are compared with the work already carried out for prediction of speed of BLDC motor, dominating the superiority of the proposed approach. Hence, it confirms the model's robustness in capturing complex motor behavior. The proposed approach offers a reliable predictive tool suitable for integration into realtime control systems, enabling enhanced motor efficiency, early fault detection, and torque ripple mitigation.

Emotions have puzzled and fascinated thinkers throughout history, from Plato and Aristotle to modern cognitive psychologists. Until relatively recently, the widely accepted view on emotions has been that they are only an interference on the neutral behaviour of a person. However, there has been a rapid increase in the study of the effects of emotion on cognition, popularizing the view that an adequate theory of cognition that ignores emotion is likely to prove inadequate (Eysenck, Keane, 2009). In this paper, the question of the importance of ...

This paper introduces a meta-theoretical framework based on Kyle Heuser's cognitive ability to visualize and internally navigate recursive hyperstructures with nonillionscale parametric complexity in real time. This cognition operates beyond traditional computation, redefining cognitive recursion and intelligence itself. The framework extends the boundaries of expressible intelligence far beyond known hypercomputational thresholds including Busy Beaver sequences, ordinal logics, and TREE-type explosivity.

Cognitive science is considered to be the study of mind (consciousness and thought) and intelligence in humans. Under such definition variety of unsolved/unsolvable problems appear. This article argues for a broad understanding of cognition based on empirical results from i.a. natural sciences, selforganization, artificial intelligence and artificial life, network science and neuroscience, that apart from the high level mental activities in humans, includes subsymbolic and sub-conscious processes, such as emotions, recognizes cognition in other living beings as well as extended and distributed/social cognition. The new idea of cognition as complex multiscale phenomenon evolved in living organisms based on bodily structures that process information, linking cognitivists and EEEE (embodied, embedded, enactive, extended) cognition approaches with the idea of morphological computation (info-computational self-organisation) in cognizing agents, emerging in evolution through interactions of a (living/ cognizing) agent with the environment. Cognitive science is currently defined as a study of processes of knowledge generation through perception, thinking (reasoning), memory, learning, problem solving, and similar. Thagard (2013) makes an extension of the idea of "thinking" to include emotional experience. This move bridges some of the distance between cognition as thinking and its (sub-)processes, but the fundamental problem of generative mechanisms that can dynamically overarch the chasm between matter and mind remains. The definition of cognitive science does not mention biology, chemistry, (quantum-nano-, etc.) physics or chaos theory, self-organisation, and artificial life, artificial intelligence or data science, extended mind, or distributed cognition as studied with help of network science, sociology or ecology. On the current view, cognition is about high-level processes remote from physicalchemical-biological substrate. It is modeled either by classical sequential computation, understood as symbol manipulation, or by neural networks. On the other hand, historically, behaviorism offered an alternative view of cognition with the focus on the observable behavior of a subject. This divide is mirrored in the present day schism between cognitivism/computationalism on one side and EEEE (embodied, embedded, enactive, extended) cognition on the other. There have been numerous attempts to bridge this gap AQ1 AQ2

As robots are expected to get more involved in people's everyday lives, frameworks that enable intuitive user interfaces are in demand. Hand gesture recognition systems provide a natural way of communication and, thus, are an integral part of seamless Human-Robot Interaction (HRI). Recent years have witnessed an immense evolution of computational models powered by deep learning. However, state-of-the-art models fall short in expanding across different gesture domains, such as emblems and co-speech. In this paper, we propose a novel hybrid hand gesture recognition system. Our Snapture architecture enables learning both static and dynamic gestures: by capturing a socalled snapshot of the gesture performance at its peak, we integrate the hand pose along with the dynamic movement. Moreover, we present a method for analyzing the motion profile of a gesture to uncover its dynamic characteristics and which allows regulating a static channel based on the amount of motion. Our evaluation demonstrates the superiority of our approach on two gesture benchmarks compared to a CNNLSTM baseline. We also provide an analysis on a gesture class basis that unveils the potential of our Snapture architecture for performance improvements. Thanks to its modular implementation, our

The attempts to model cognitive phenomena effectively have split the research community in two paradigms: symbolic and connectionist. The extension of grounding phenomenon for abstract words is very important for social interactions of cognitive robots in real scenarios. This paper reviews the strength of symbolic and connectionist methods to address the abstract word grounding problem in cognitive robots. In particular, the presented work is focused on designing and simulating cognitive robotics model to achieve a grounding mechanism for abstract words by using the semantic network approach, as well as examining the utility of connectionist computation for the same problem. Two neuro-robotics models based on feed forward neural network and recurrent neural network are presented to see the pros and cons of connectionist approach. The simulation results and review of attributes of these methods reveal that the proposed symbolic model offers the solution to the problem of grounding abstract words with attributes like high data storage capacity with recall accuracy, structural integrity and temporal sequence handling. Whereas, connectionist computation based solutions give more natural solution to this problem with some shortcomings that include combinatorial ambiguity, low storage capacity and structural rigidity. The presented results are not only important for the advancement in communication system of cognitive robot, also provide evidence for embodied nature of abstract language. B Nadia Rasheed

Modern robots have been used in different applications including welding, painting, soldering, assembly of different products and in education. List of applications is getting even longer because robot performance is improving. Faculties are following industries involving robots in their curriculum, while industry is interested in new ideas including new applications and their improvements from the university. Modern robots are user-friendly for programming so the lack of knowledge about robot applications seems to be the main obstacle in their wider implementation. Collaborative robots or cobots are sophisticated robots which could operate with other robots and with workers in the factory. Recent opening of Yaskawa factory in Kočevje, Slovenia, near border with Croatia, has significant impact on integrating the robots in production and education in central and South-east Europe.

We present a new optimization-based approach for robotic motion planning among obstacles. Like CHOMP (Covariant Hamiltonian Optimization for Motion Planning), our algorithm can be used to find collision-free trajectories from naïve, straight-line initializations that might be in collision. At the core of our approach are (a) a sequential convex optimization procedure, which penalizes collisions with a hinge loss and increases the penalty coefficients in an outer loop as necessary, and (b) an efficient formulation of the no-collisions constraint that directly considers continuous-time safety Our algorithm is implemented in a software package called TrajOpt. We report results from a series of experiments comparing TrajOpt with CHOMP and randomized planners from OMPL, with regard to planning time and path quality. We consider motion planning for 7 DOF robot arms, 18 DOF full-body robots, statically stable walking motion for the 34 DOF Atlas humanoid robot, and physical experiments with...

Ontologies are a powerful means for expressing and sharing knowledge in a meaningful way, and are becoming accepted as a viable modelling approach. The purpose of this paper is to enhance the representations used by robots by incorporating ontologies and implementing reasoning services that can exploit the information inherent within ontology based representations. Our objective is to explore the use of ontological concepts for object categorisation in agents and issues related to the grounding of ontology based representations. The research is driven by the need to make progress towards the development of a generalised solution for the grounding problem which would allow intelligent agents to achieve more adaptive behaviours. Object categorisation is important for intercommunication between agents because it plays an important role in supporting problem solving and the achievement of goals. Ontologies allow concepts to be easily shared meaningfully between agents and this can enable interoperability between multiple heterogenous systems. In order to illustrate our ideas we focus on the robot soccer domain because it is an application where agents, namely robots, must make decision, communicate and collaborate in a complex and dynamic environment . .

Previously, an approach based on the Situation Calculus was published for specifying feature coordination of a software system, but without a physical model or any additional autonomous agent in the environment. Hence, no verification of the feature coordination was possible in spite of its formal specification. Verification of safety-critical feature coordination is important, however, and requires additional models. This paper shows that a specification of a software coordinator can be formally verified using the Fluent Calculus (a derivative of the Situation Calculus), when combined with additional models. The overall qualitative model is a reimplementation of a recently published one based on synchronized finite-state machines, which was used for model checking. In fact, we show how the model in Fluent Calculus can be systematically derived from the finite-state machines. The results of verification using the Fluent Calculus correspond to those using model checking. We also contrast our approach using the Fluent Calculus with model checking. In summary, we present verification of (safety-critical) feature coordination using the Fluent Calculus.

Robots need to exhibit proactive behavior if they are to be accepted in human-centered environments. A proactive robot must reason about the actions it can perform, the state of the environment, the state and the intentions of its users, and what the users deem desirable. This paper proposes a computational framework for proactive robot behavior that formalizes the above ingredients. The framework is grounded on the notion of Equilibrium Maintenance: current and future states are continuously evaluated to identify opportunities for acting that steer the system into more desirable states. We show that this process leads a robot to proactively generate its own goals and enact them, and that the obtained behavior depends on a model of user intentions, preferences, and the temporal horizon used in prediction. A number of examples show that our framework accounts for even slight variations in user preference models and perceived user intentions. We also show how the level of informedness of the system is easily customizable.

In order to be proactive, robots should be capable of generating and selecting their own goals, and pursuing activities towards their achievement. Goal reasoning has focused on the former set of cognitive abilities, and automated planning on the latter. Despite the existence of robots that possess both capabilities, we lack a general understanding of how to combine goal generation and goal achievement. This paper introduces the notion of equilibrium maintenance as a contribution to this understanding. We provide formal evidence that equilibrium maintenance is conducive to proactive robots, and demonstrate our approach in a closed loop with a real robot in a smart home.

We have developed a self-propelling robotic pet, in which the robot audition software HARK (Honda Research Institute Japan Audition for Robots with Kyoto University) was installed to equip it with sound source localization functions, thus enabling it to move in the direction of sound sources. The developed robot, which is not installed with cameras or speakers, can communicate with humans by using only its own movements and the surrounding audio information obtained using a microphone. We have confirmed through field experiments, during which participants could gain hands-on experience with our developed robot, that participants behaved or felt as if they were touching a real pet. We also found that its highprecision sound source localization could contribute to the promotion and facilitation of human-robot interactions.

Autonomous urban vehicle prototypes are expected to be efficient even in not explicitly planned circumstances and dynamic environments. The development of autonomous vehicles for urban driving needs real-time information from vehicles and road network to optimize traffic flows. In traffic agent-based models, each vehicle is an agent, while the road network is the environment. Cognitive agents are able to reason on the perceived data, to evaluate the information obtained by reasoning, and to learn and respond, preserving their self-sufficiency, independency, self-determination, and self-reliance. In this paper a bio-inspired cognitive agent for autonomous urban vehicles routing optimization is proposed. The use of selected bio-inspired analyzing techniques, which are commonly employed to investigate the topological and functional features of a Metabolic Network, allows the agent to analyze the structural aspects of a road network, find its extreme pathways and outline the balanced flow combinations. This approach optimizes traffic flows over network, minimizes road congestions and maximizes the number of autonomous vehicles reaching their destination target. Agent behavior has been tested using data coming from Palermo urban road network, Italy, while the adopted bio-inspired analysis techniques have been compared with the A* literature algorithm. Experimental results demonstrate that the approach permits to find a better global routing optimization solution. To the best of our knowledge, it is the first time that metabolic mechanisms involved in a cell survival process have been used to design a congestion solution.

This article presents a service robotic system for people loosing their autonomy developed at CEA LIST. In the past on SAM robot, we have developed a method for automatic manipulation and object grasping using visual servoing. This method is too stereotyped to correctly grasp objects with complex geometry or to assign particular use to the manipulated object. In this article, we present a new study to adapt the grasping and the usage of an object designed by the user. Our method uses vision object recognition (CBIR) and an ontology for robotic manipulation. This recognition is implemented as a Web Service. It relies on passive vision and does not use a geometric model for grasping. The implementation of this method enables us to automatically search objects in the surrounding areas and to play cognitive and physical stimulation games with the user.

Chatty Factories is a three-year investment by the Engineering and Physical Sciences Research Council (EPSRC) through its programme for New Industrial Systems. The project explores the transformative potential of placing IoT-enabled data driven systems at the core of design and manufacturing processes. The research focuses on the opportunity to collect data from IoTenabled sensors embedded in products during real-time use by consumers, explores how that data might be immediately transferred into usable information to inform design, and considers what characteristics of the manufacturing environment might optimise the response to such data. The project also considers implications arising for skills development in the education sector as well as ethics in manufacturing. In this paper we provide a vision for future "Chatty Factories".

With increasing development and widespread interest in artificial intelligence and robotics over the last several years, novel solutions are being considered for addressing specific problems in a number of domains. In particular, caring for elderly individuals in regions where human labour is insufficient is of special interest. One aspect of this involves an ability to communicate and socialize with people in a familiar and humanlike manner, with an ability to understand human emotion through behavioural cues and language. Furthermore, social robots should be able to act with empathy if we are interested in using them for tasks related to eldercare and healthcare, as empathy involves the adoption of another person’s perspective. This work investigates whether social robots are capable of meeting these requirements, and ultimately demonstrates that they cannot exhibit genuine acts of empathy. By investigating one robot in particular named iCub, it becomes apparent that it will not be able to understand human emotions given its cognitive architecture. iCub’s framework lacks the kind of affective regulation observed in people and animals, and as such, is unable to experience its own form of emotions. Consequently, iCub is incapable of understanding what emotions are and what they mean to humans. For social robots, an alternative solution which relies on experiences of emotions should instead be pursued. The cognitive architecture developed by Pentti Haikonen is preferable because it is modelled on biological functionality, creating better analogues of living beings than previous efforts in AI. By creating associative networks of neurons which establish connections between stimuli and their effects on the robot’s body, it is able to learn what a stimulus means for its continued functioning. By using signals representing analogues of pain and pleasure, emotional information learned by the robot is grounded on how stimuli impact the robot’s body. This architecture provides a foundation for empathy since the robot is able to appeal to its own experiences of pain and pleasure to understand the meanings of behavioural cues exhibited by humans.

با ظهور گسترده هوش مصنوعی در دهه اخیر، ساختار سنتی آموزش در جهان و به ویژه در ایران با دگرگونی های بنیادینی مواجه شده است. این مقاله با رویکرد آینده پژوهانه، به بررسی تاثیرات عمیق هوش مصنوعی بر صنعت آموزش و تدریس در ایران می پردازد. روش پژوهش حاضر کیفی-تحلیلی است و از طریق تحلیل منابع معتبر جهانی و داده های رسمی داخلی، روندها، فرصت ها و تهدیدهای هوش مصنوعی در آموزش بررسی شده اند. یافته ها نشان می دهند که در ایران، با وجود ضعف در زیرساخت های فناورانه، فرصت های قابل توجهی در حوزه شخصی سازی یادگیری، ارزیابی های هوشمند، و توسعه آموزش مهارت محور با کمک هوش مصنوعی وجود دارد. همچنین چالش هایی همچون مقاومت نهادی، خلاهای سیاست گذاری، و نابرابری دیجیتال نیز مانع تحقق کامل این ظرفیت ها شده اند. در پایان، مقاله با ارائه پیشنهادهایی برای سیاست گذاران، دانشگاه ها و فعالان حوزه آموزش، چارچوبی برای انطباق با آینده هوش مصنوعی محور ترسیم می کند. این پژوهش تلاشی است در راستای بومی سازی تحلیل های جهانی در زمینه آینده آموزش، با توجه به مختصات فرهنگی، اقتصادی و فناورانه ایران 1404.

The mobile robot is an intelligent device that can achieve many tasks in life. For autonomous, navigation based on the line on the ground is often used because it helps the robot to move along a predefined path, simplifies the path planning, and reduces the computational load. This paper presents a method for navigating the four-wheel mobile robot to track a line based on a deep Q-network as a control algorithm to desire the action of the mobile robot and a camera as a feedback sensor to detect the line. The control algorithm uses a convolution neural network (CNN) to generate the mobile robot action, defined as an agent of deep Q-network. CNN uses images from the camera to define the state of the deep Q network. The simulations are performed based on Gazebo software which includes a 3D environment, mobile robot model, line, and Python programming. The results demonstrate the high-performance tracking of mobile robots with complex line trajectories, achieving errors of less than 100 px, which is compared with the traditional vision method (VNS), the MSE of the proposal method is 0.0264 lower than VNS with 0.0406. Showcases proved convincingly that effectiveness suggested a control approach.

Learning and teaching second language skills requires many different techniques and approaches. In the modern world, students have many opportunities to learn many different languages with the help of technology and with the help of many different modern and traditional approaches. Embodied cognition approach plays a great role in second language acquisition. When foreign language teachers or professors develop embodied cognition in their classes students can learn many different languages easily. This study deals with embodied cognition in foreign language learning classes. The definitions of embodied cognition and the embodied approach in foreign language education will be given. General characteristics of embodied cognition will be told. Different views of embodied cognition will be shared. Sample classroom activities will also be shared.  Article visualizations:

The trustworthiness of robots and autonomous systems (RAS) has taken a prominent position on the way towards full autonomy. This work is the first to systematically explore the key facets of human-centred AI for trustworthy RAS. We identified five key properties of a trustworthy RAS, i.e., RAS must be (i) safe in any uncertain and dynamic environment; (ii) secure, i.e., protect itself from cyber threats; (iii) healthy and fault-tolerant; (iv) trusted and easy to use to enable effective human-machine interaction (HMI); (v) compliant with the law and ethical expectations. While the applications of RAS have mainly focused on performance and productivity, not enough scientific attention has been paid to the risks posed by advanced AI in RAS. We analytically examine the challenges of implementing trustworthy RAS with respect to the five key properties and explore the role and roadmap of AI technologies in ensuring the trustworthiness of RAS in respect of safety, security, health, HMI, and ethics. A new acceptance model of RAS is provided as a framework for human-centric AI requirements and for implementing trustworthy RAS by design. This approach promotes human-level intelligence to augment human capabilities and focuses on contribution to humanity.

In this paper we present a model free hybrid visual servoing system. The "model free" term refers to the system with the unknown kinematics model that has to be estimated on-line, while "hybrid" specifies the visual controller architecture. The proposed system has a conventional Jacobian estimation part necessary for control output generation and it is supplemented with an additional adaptive neural network (ANN). It is shown that ANN could be used to improve the visual servoing performances of the conventional visual servoing controller, as well as to enable the mimetic control of the robot which dynamics differs from the robot which it mimics.

In this paper we present a model free hybrid visual servoing system. The ? model free? term refers to the system with the unknown kinematics model that has to be estimated on-line, while ? hybrid? specifies the visual controller architecture. The proposed system has a conventional Jacobian estimation part necessary for control output generation and it is supplemented with an additional adaptive neural network (ANN). It is shown that ANN could be used to improve the visual servoing performances of the conventional visual servoing controller, as well as to enable the mimetic control of the robot which dynamics differs from the robot which it mimics.

With the support of intelligent machinery systems and control software, the manufacturing industry has rapidly transformed. The application of technology is making production processes increasingly smart and delivering significant benefits. Businesses can adopt smart manufacturing to modernize operations, enhance productivity, maintain competitiveness, and prepare for future challenges. Therefore, developing a workforce capable of working within smart manufacturing systems is an urgent task. It is essential to have human resources equipped with the knowledge and skills to design, install, operate, troubleshoot, and maintain intelligent machinery and systems. This paper provides reliable research data and comprehensive information about smart manufacturing and its ecosystem. It also proposes several solutions to improve the quality of training in higher education institutions. Based on these findings, educational institutions specializing in technological and engineering fields can make appropriate and flexible decisions when implementing training programs aligned with smart manufacturing systems. This ensures optimal teaching effectiveness and produces a skilled workforce that meets the demands of flexible manufacturing enterprises in the era of advanced technology.

In this paper, we build on previous work on Belief Revision operators based on the use of logic programming with Answer Set semantics as a representation language. We present a set of postulates for Answer Set Revision with respect to a set of sentences and with respect to explanations. We focus on the non-prioritized revision operator with respect to explanations, or arguments, which is intended to model situations in which agents revise their knowledge as a result of dialogues with other agents in a multi-agent setting.

Faced with a vast, dynamic environment, some animals and robots often need to acquire and segregate information about objects. The form of their internal representation depends on how the information is utilised. Sometimes it should be compressed and abstracted from the original, often complex, sensory information, so it can be efficiently stored and manipulated, for deriving interpretations, causal relationships, functions or affordances. We discuss how salient features of objects can be used to generate compact representations, later allow-ing for relatively accurate reconstructions and reasoning. Particular moments in the course of an object-related process can be selected and stored as 'key frames'. Specifically, we consider the problem of representing and reasoning about a de-formable object from the viewpoint of both an artificial and a natural agent.

Classical computing has well-established formalisms for specifying, refining, composing, proving, and otherwise reasoning about computations. These formalisms have matured over the past 70 years or so. Unconventional Computing includes the use novel kinds of substrates -from black holes and quantum effects, through to chemicals, biomolecules, even slime moulds -to perform computations that do not conform to the classical model. Although many of these substrates can be "tortured" to perform classical computation, this is not how they "naturally" compute. Our ability to exploit unconventional computing is partly hampered by a lack of corresponding programming formalisms: we need models for building, composing, and reasoning about programs that execute in these substrates. What might, say, a slime mould programming language look like? Here I outline some of the issues and properties of these unconventional substrates that need to be addressed to find "natural" approaches to programming them. Important concepts include embodied real values, processes and dynamical systems, generative systems and their meta-dynamics, and embodied self-reference.