Autonomous Object Research Articles

МОРФЕМНЫЙ АНАЛИЗ КАК ОБРАЗОВАТЕЛЬНЫЙ ПАРАДОКС

The theoretically untenable and empirically inadequate code model of linguistic communication predetermines the paradoxical situation in education, when the Russian language, as a school subject, becomes one of the hardest in the school curriculum, while the didactic goal it aims to achieve is vague and indeterminate. The hypostatization of linguistic signs into autonomous container-like objects with meanings as their contents motivates the so-called morphemic analysis - the breaking down of words into their components (morphemes) that possess specific «quanta» of meaning, while the educational purpose of such an “analysis” is unclear, and its cognitive value is negligible, because morphemic analysis does not relate to the practice of living in language.

Fog-based Edge AI for Robotics: Cutting-edge Research and Future Directions

The fusion of Fog-based Edge Artificial Intelligence (AI) is an emerging and transformative research area within robotics. This research examines the significant potential of augmenting robotic systems by integrating Edge AI and Fog Computing, aiming to enhance their cognitive abilities, independence, and operational effectiveness. The feasibility of real-time data analysis and decision-making is enhanced by deploying AI algorithms at the network edge, near the robots, and by leveraging fog computing capabilities. This study investigates the diverse implementations of Fog-based artificial intelligence (AI) in robotics. These applications encompass autonomous navigation, object detection, and human-robot interaction. By showcasing these examples, the research demonstrates the potential for a transformative impact on the capabilities of robotic systems through the integration of Fog-based AI. Additionally, this study explores the obstacles and potential advantages within this interdisciplinary field, providing valuable perspectives on the promising avenues that can facilitate advancements in robotics by leveraging the combined power of Fog-based Edge Artificial Intelligence. This study elucidates how the amalgamation of Fog Computing and Edge AI confers enhanced capabilities upon intelligent robotic systems, enabling them to operate autonomously in real time. This integration effectively addresses the obstacles commonly encountered in conventional cloud-based AI systems, such as latency, internet connectivity, and data security concerns. The study highlights the importance of architecture, security, and ethical factors in utilizing robotic intelligence. It emphasizes the need for data protection standards and transparency to ensure responsible and reliable utilization of this technology in a rapidly changing environment.

Web-based Efficiency of Distributed Systems and IoT on Functionality of Smart City Applications

Abstract In the current technological environment, the Internet of Things (IoT) has arisen as a significant subject of research because of its importance. A robust cloud computing framework is established via the collaboration of sensors and actuators. This framework has the potential to be used in the creation of autonomous object networks in real-time systems. The Internet of Things (IoT) is playing a significant role in the redefinition of other significant ideas, such as urbanism and smart cities. The Internet of Things (IoT) technology has the potential to improve the quality of life for inhabitants of smart cities, which are relatively new developments. This might be accomplished by providing people with enhanced facilities and services. The Internet of Things is seeing a fast expansion in a variety of sectors, including smart cities, everyday life, and other fields. Through the use of home automation, smart wearables, security solutions, and smart healthcare, the Internet of Things makes it possible to create intelligent environments. In the realm of the Internet of Things, some of the possible topics of study include intelligent transportation systems for cities and intelligent electrical systems. This article offers a succinct summary of the most recent advancements in the Internet of Things (IoT) and the influence those advancements have had on the lives of humans in their day-to-day activities. In addition to this, the Internet of Things (IoT) is also considered in connection to artificial intelligence, autonomous control, and cloud computing. It is important to synchronise a number of technologies, such as wireless sensors, actuators, the internet, and distributed computing, in order to successfully allow upcoming Internet of Things technologies.

Человек в контексте биологической гипотезы сознания

The article analyzes the problem of human consciousness, which is commonly called the main mystery of the Universe. The authors proceed from the fact that traditional views on it do not permit to properly investigate the essence of human consciousness. According to the authors of the article, the allocation of human conscious-ness as a special autonomous object of cognition does not correspond to the idea of genetic organization of living matter between different levels. Of particular difficulty is the task of explaining the birth of mental events from neurophysiological processes occurring in the human brain. In this connection, the authors propose a new formulation of the human problem in the context of the biological hypothesis of consciousness, according to which the latter is defined as the result of the activity of special microorganisms inside man, the essence of which he knows little about, since he is accustomed to consider himself the “crown of nature” as per the con-cept of European culture. Reference is made to the consistency of the assertion that man in general and his consciousness in particular should be subject to the same biological laws of existence as other living organ-isms, since they are all part of a single physical reality.

The ethical challenges of artificial intelligence and autonomous objects: a preamble

Analisam-se os desafios éticos suscitados pelo vertiginoso avanço dos sistemas de inteligência artificial (IA) e dos objetos autônomos incorporados em seu funcionamento. Problematizam-se as perspectivas éticas subjacentes às recentes comissões criadas em instâncias internacionais (Organização das Nações Unidas e Parlamento Europeu) para avaliar os riscos das IAs. Pontua-se que as reflexões éticas sobre IAs estão permeadas por um utilitarismo consequencialista, visto que as comissões geralmente são formadas por agentes, em sua maioria, diretamente interessados nos avanços e na lucratividade das IAs.

Modal synthesis of observers of state variables of ship dynamical systems

The purpose of the work is to increase the information content of ship control systems through the use of dynamic observers, which are, in essence, mathematical information sensors and allow you to fully restore the vector of state variables of the object model with high accuracy by measuring the output vector of a smaller dimension. An algorithm for the synthesis of observers based on the modal method of parametric evaluation of their model is proposed. It provides obtaining the parameters of the regulator according to the given spectra of the matrices of the state of the observed system and the object by means of the Control Toolbox of the MATLAB computing environment. The use of the modal method (subject to the conditions of observability and controllability) guarantees the stability of observers, which allows them to be used for stable and unstable observed objects and systems. The algorithm of modal synthesis of observers is suitable for increasing the information content of a wide range of ship dynamic systems and, above all, control systems for ship energy complexes and their components. These include autopilots, control systems for ship power plants and their elements, dynamic complexes of satellite and inertial navigation systems and positioning of moving objects in remote control conditions, monitoring and safety tools, identifiers, etc. It has been shown that in the conditions of digital transformation, the use of observers dramatically improves the quality and reduces the time for modeling the dynamics of ship systems and energy complexes operated under conditions of external disturbances, which makes it possible to improve the algorithms for estimating state variables of a class of autonomous objects modeled by nonlinear equations that allow the transition in the working area to quasi linear models with time-invariant parameters. The proposed algorithm is demonstrated by the example of the synthesis of a three-dimensional observer for the control system of a supertanker with deadweight of 150 thousand tons. The simulation of the control object is performed with an input signal of triangular shape, which most fully corresponds to the real control signal, and it is implemented in the form of a program compiled in MATLAB codes. The obtained values of state variables and errors of their recovery correspond to the specified speed and the required stability of the control system.

Use of Fish Resources and Prospects for Aquaculture Conservation in Water Bodies of West Kazakhstan Regions

The ability to meet the needs of the population in fish and fish products and its food security is one of the most acute problems in the Republic of Kazakhstan. The purpose of this study is to study the current state of fisheries in the Republic of Kazakhstan and to propose the development of fisheries in the West Kazakhstan region. Methods for studying of a condition of a fishery of Republic Kazakhstan statistical methods of the data analysis have been used, and exclusively the catch of fish and other water animals, and also dependence of physical volume of fish farming production on total quantity of the made production. In research topical questions of production capacity of fishing and fish-canning enterprises, by kinds and volumes of output production, economic indicators, and also on the enterprises which are carrying out purchase and realization of fish production, wholesale and retail trade, problems of marketing researches in the field of manufacture and safety of fish production are considered. Conclusions - proceeding from the received results it has been concluded that it is necessary to create laboratories and fish farming in autonomous objects, that will allow to develop innovative technologies of cultivation, conservation and replenishment of fish resources in water bodies of region, will provide educational base for training of future specialists, will create conditions for conservation and multiplication of fish resources of Kazakhstan, will increase food safety of the country, will solve key problems of fish industry development. Artificial fish farming involves intervention in the development of organisms in order to increase their productivity, such as regular restocking, feeding, protection from predators, etc.

Object Fetching UAV using Autonomous Flight and Object Detection Algorithms

Abstract: Autonomous UAVs (Unmanned Aerial Vehicles) are being used in various applications around the world like surveillance and aerial security, construction, agriculture, delivery, etc. These applications require heavy duty UAVs with high payload capacity and long battery life. The aim of this project is to use the principles of autonomous flight and object detection for indoor autonomous flight with the target to fetch and deliver lightweight objects with minimum energy and time consumption to create a viable prototype for indoor applications like delivering objects to bedridden patients, smart home applications, warehouse management and more.

Dynamic Operator Extraction Method

A "black box" is used to mean an object whose internal structure is unknown and information about its structure and functioning can only be partially obtained by analyzing the input-output connections of this object. Not only those material, energy and/or informational flows that are necessary for its functioning in accordance with the goals set before it - signals, but also those that actually complicate the realization of the set goal by the system - obstacles come to the input of the system from the external environment. An unregulated facility is being explored here. When studying such an object, it is important that the signals always describe the behavior of the object as a whole and reflect the individual movements of a large number of its microparticles of the same type. The analysis of the structure of the object based on its established signal is insufficient, if only the dynamic dependence on time is taken into account, even the most detailed registration of the single solution of the established dynamic equation does not allow revealing the structure of the operator in real situations. The inadequacy of the usual black box scheme for studying an unregulated object based on a settled signal leads to the need to account for internal fluctuations in the equations of the object signal. Therefore, the article considers autonomous objects, in the dynamic equations of which time t is not explicitly included. The work formulates and to some extent substantiates a fairly general and fairly simple principle of signal description. According to this basic premise, the properties of the signal, which are quantitatively significant and regularly manifest under the given conditions of observation, are connected to each other by some dynamic structure of the object. The role of object movements, which are less important under these conditions, as well as the role of the external environment, is reflected in this description by the time-fluctuating force that disturbs the dynamic system. The study of the statistical properties of the response of the dynamic system to the fluctuating disturbance allows, in a fairly wide range of problems, to evaluate the dynamic characteristics of an unregulated object based on the established signal. The behavior of the signal, which is described by a linearized equation, requires the estimation of the coefficient , so the article considers possible schemes for estimating this coefficient

Honey-list based authentication protocol for industrial IoT swarms

Industrial Internet of Things (IIoT) systems are advanced IoT systems composed of sensor devices supported with dynamic objects such as smart vehicles and drones. The collaboration among static and heterogeneous mobile objects makes the topologies of IIoT systems dynamic and complex. This dynamic topology is also partially due to the fact that the static devices are typically partitioned into categories of collaborating sensors (called swarms) managed by side servers. However, existing authentication techniques for IIoT systems do not consider realistic system models simultaneously hosting different types of dynamic objects. For such scenarios, there is a need for a protocol that guarantees a secure Entity-to-Entity (E2E) communication, thus ensuring a smooth and safe production process.In this paper, for IIoT with swarms (SIIoT), we propose a novel key agreement and authentication protocol, HASAO (Honey-list Authentication for SIIoT with Autonomous Objects). HASAO enables efficient and secure E2E communication between devices in the same or different swarms. HASAO fills the gap of considering a realistic system model simultaneously hosting different types of dynamic objects. We employ Honey lists (lists with algorithms used to prevent guessing passwords) and mutual authentication technologies in HASAO to guarantee its security against different attacks, even in public-channel communication scenarios. Using the well-established Real-Or-Random (ROR) model, we proved the security of HASAO in detail. We also provide a prototype implementation of HASAO in the Automated Validation of Internet Security Protocols and Applications (AVISPA) tool. This tool confirms the results of our theoretical proofs, thus verifying the security of HASAO. We also carried out a detailed comparative study of HASAO against existing related authentication techniques. Compared to these techniques, HASAO offers more functionality (serving more types of dynamic objects) and superior security (via proving backup plans for session key establishment). Finally, we prove that HASAO is practical by implementing it in a well-known network simulator, Omnet++.

Optimal solutions in systems consisting of rational agents

Rational agents and systems consisting of such agents are considered. An agent is an autonomous object that has sources of information about the environment (for example, physical sensors) and affects this environment (for example, with the help of actuators). A rational agent is an agent who, in order to achieve a set goal, is able to act effectively, that is, to use behavioral strategies that are close to optimal. It is assumed that there is a utility function, which is defined on the set of possible sequences of actions of the agent (agents, if a system of agents is considered) and takes values in the set of real numbers. A rational agent acts in such a way as to maximize the utility function. A system of rational agents is a system consisting of rational agents that have a common goal and act in an optimal way to achieve it. Agents act using the optimal (or close to optimal) solution of the extreme problem formulated for the system. The work gives examples of systems consisting of rational agents. The main groups of problems and the corresponding mathematical methods of their solution related to the management of agents and systems of rational agents are determined: cooperation of agents (creation of a system of agents), planning and coordination of actions of agents, search of placement of the system of agents, recognition. Cooperation is necessary when no single agent has sufficient experience, resources, and information to solve a problem, but different agents have the expertise and capabilities to solve different parts of the problem. Planning is the development of a method of action of agents and the entire system in the future depending on the situations that may arise, the choice of an effective method of action, optimal distribution of resources. Coordination is such an organization of the actions of various agents that make up the system, which ensures the efficiency of this system. The tasks of finding the optimal placement of agent system and the task of recognizing the state of the environment are important. Examples of such problems are given and mathematical methods of their solution are indicated.

Breathable Metal-Organic Framework Enhanced Humidity-Responsive Nanofiber Actuator with Autonomous Triboelectric Perceptivity.

Autonomous object manipulation and perception with environmental factor-triggered and self-powered actuation is one of the most attractive directions for developing next-generation soft robotics with a smart human-machine-environment interface. Humidity, as a sustainable energy source ubiquitous in the surrounding environment, can be used for triggering smart grippers. In this work, it is proposed that by contacts between the gripper and objects upon humidity-induced actuation, real-time distinguishable triboelectric signals can be generated to realize the humidity-driven object manipulation and identification. Herein, a thermo-modified electrospun polyvinylpyrrolidone/poly(acrylic acid)/MIL-88A (T-PPM) nanofibrous film with micro-to-nano cross-scale porosity is developed, and a bilayer humidity-responsive actuator (T-HRA) was designed, mimicking the tamariskoid spikemoss to enhance the humidity-driven actuation. The breathing effect of MIL-88A and hierarchical porous structure of the T-PPM facilitate moisture diffusion and offer huge actuation (2.41 cm-1) with a fast response (0.084 cm-1 s-1). For autonomous object manipulation perception, T-PPM was verified as a tribo-positive material located between paper and silk. Accordingly, the T-HRA was demonstrated as a smart soft gripper that generates a different electric signal upon contact with objects of different material. This work proposes a concept of soft robots that are interactive with the environment for both autonomous object manipulation and information acquisition.

Optimality of Safe Game and Non-Game Control of Marine Objects

The article presents a model of the process of safe and optimal control of an autonomous surface object in a group of encountered objects. An algorithm for determining the optimal and safe trajectory based on a multi-object game model was proposed, and an algorithm for determining the optimal trajectory was proposed for comparative analysis, not taking into account the maneuverability of other objects. Simulation studies of the algorithms made it possible to assess the optimality of the trajectories for various acceptable object strategies. An analysis of the characteristics of the sensitivity of the safe control—assessed with the risk of collision, both on the inaccuracy of navigation data and on the number of possible strategies of objects, was carried out.

Survey of Point Cloud Registration Methods and New Statistical Approach

The use of a 3D range scanning device for autonomous object description or unknown environment mapping leads to the necessity of improving computer methods based on identical point pairs from different point clouds (so-called registration problem). The registration problem and three-dimensional transformation of coordinates still require further research. The paper attempts to guide the reader through the vast field of existing registration methods so that he can choose the appropriate approach for his particular problem. Furthermore, the article contains a regression method that enables the estimation of the covariance matrix of the transformation parameters and the calculation of the uncertainty of the estimated points. This makes it possible to extend existing registration methods with uncertainty estimates and to improve knowledge about the performed registration. The paper’s primary purpose is to present a survey of known methods and basic estimation theory concepts for the point cloud registration problem. The focus will be on the guiding principles of the estimation theory: ICP algorithm; Normal Distribution Transform; Feature-based registration; Iterative dual correspondences; Probabilistic iterative correspondence method; Point-based registration; Quadratic patches; Likelihood-field matching; Conditional random fields; Branch-and-bound registration; PointReg. The secondary purpose of this article is to show an innovative statistical model for this transformation problem. The new theory needs known covariance matrices of identical point coordinates. An unknown rotation matrix and shift vector have been estimated using a nonlinear regression model with nonlinear constraints. The paper ends with a relevant numerical example.

Intelligent state assessment of complex autonomous objects based on wavelet analysis

The evolutionary development of complex autonomous technical objects (CATOs), which include bodynets, unmanned vehicles, aircraft, and other robotic systems, is characterized by increased requirements for the quality of their functioning, security, and reliability under the influence of various kinds of destabilizing factors. This determines the importance of the problem of assessing their technical state, including monitoring degradation (aging) and supporting the dynamic adaptation of CATOs. To solve this problem, the article proposes a new method for intelligent assessment of the CATO technical state. The method is based on the representation of knowledge about the results of interval estimation of controlled parameters in the knowledge base of the system for assessing the CATO technical state. In this case, the process of estimating the controlled parameters is based on the application of wavelet analysis. The article discusses the architecture and implementation issues of the intelligent system for assessing the CATO technical state. A special place in this system is occupied by the knowledge base containing information about the emergency and normal states of controlled parameters. An experimental evaluation of the proposed assessment method showed that the joint use of knowledge representation processes in the knowledge base and wavelet analysis for the formation of CATO operability regions increases the accuracy and credibility of the state identification results. In addition, this approach expands the possibilities of applying technical means of control and diagnostics concerning evolving CATO.

Application of the reversible step-up and step-down pulse converter as a charging and discharging device in an autonomous system of electric power supply

Formulation of the problem. The structure shown in Figure 1 is widely used to build spacecraft power supply systems. It contains a solar battery in series and voltage regulator, which a load is connected to its output. To supply power to the load when the solar panel has no or insufficient capacity, the power supply system uses a battery pack which is charged and discharged by means of a charge-discharge device connected between the output of the voltage regulator and the battery pack. The power supply can be used to build power supply systems for a wide range of autonomous objects, such as unmanned aerial vehicles with long flight times, unattended weather stations, and environmental monitoring stations. In a power supply system with the structure shown in Figure 1, each of the devices can stabilize the output voltage: a voltage regulator, a discharge device and a battery charger. In such a power supply system, the operation of the charger and the discharger are separated in time, allowing them to function together. The use as a charge-discharge boost-decrease reversible pulse voltage converter with a high efficiency allows minimizing the number of elements in the power circuit of the device due to the possibility of reversing the energy flow reversal, which will improve the weight and size characteristics of the system and increase to increase its reliability. The purpose is to show the feasibility of using a converter with a high efficiency factor and the possibility of reversing the energy flow as a charge-discharge device as part of the power supply system of an autonomous object. To develop a model and confirm the possibility of operating the pulse converter as a charger in two modes: in the mode of providing a given charging current of the battery and in the mode of charging the battery with a decreasing current at a given voltage on the battery. Results. The expediency of using a reversible pulse converter with a high efficiency factor and the possibility of reversing the energy flow as a charger in the power supply system of an autonomous object is shown. A model has been developed and confirmed of the converter as a charger in two modes: in the mode of providing a given charging current of the battery and in the mode of charging the battery with a decreasing current at a given voltage on the battery pack. Practical Significance. The use of a reversible pulse converter as a single charge-discharge converter in the power supply system of an autonomous object will improve the mass-size characteristics, efficiency and reliability of the power supply system and increase life time of active operation of autonomous object as a whole Keywords: power supply system, autonomous object, solar battery, accumulator battery, pulse converter, charge-discharge device.

Research on Synthesis of Multi-Layer Intelligent System for Optimal and Safe Control of Marine Autonomous Object

The article presents the synthesis of a multi-layer group control system for a marine autonomous surface vessel with the use of modern control theory methods. First, an evolutionary programming algorithm for determining the optimal route path was presented. Then the algorithms—dynamic programming with neural state constraints, ant colony, and neuro-phase safe control algorithms—were presented. LMI and predictive line-of-sight methods were used for optimal control. The direct control layer is implemented in multi-operations on the principle of switching. The results of the computer simulation of the algorithms were used to assess the quality control.

Deep Learning for Localized Detection of Optic Disc Hemorrhages

To develop an automated deep learning system for detecting the presence and location of disc hemorrhages in optic disc photographs. Development and testing of a deep learning algorithm. Optic disc photos (597 images with at least 1 disc hemorrhage and 1075 images without any disc hemorrhage from 1562 eyes) from 5 institutions were classified by expert graders based on the presence or absence of disc hemorrhage. The images were split into training (n=1340), validation (n=167), and test (n=165) datasets. Two state-of-the-art deep learning algorithms based on either object-level detection or image-level classification were trained on the dataset. These models were compared to one another and against 2 independent glaucoma specialists. We evaluated model performance by the area under the receiver operating characteristic curve (AUC). AUCs were compared with the Hanley-McNeil method. The object detection model achieved an AUC of 0.936 (95% CI=0.857-0.964) across all held-out images (n=165 photographs), which was significantly superior to the image classification model (AUC=0.845, 95% CI=0.740-0.912; P=.006). At an operating point selected for high specificity, the model achieved a specificity of 94.3% and a sensitivity of 70.0%, which was statistically indistinguishable from an expert clinician (P=.7). At an operating point selected for high sensitivity, the model achieves a sensitivity of 96.7% and a specificity of 73.3%. An autonomous object detection model is superior to an image classification model for detecting disc hemorrhages, and performed comparably to 2 clinicians.

INCREASING THE MAXIMUM TORQUE OF SPECIAL DC MOTORS WITH PERMANENT MAGNETS

In the article proposes methods of increasing the maximum torque of built-in direct current torque motors by varying their design (the diameter of the armature winding wire; the dimensions of the armature in order to increase the number of conductors located on its outer surface; by changing the winding scheme) while maintaining the connection dimensions, which is an urgent task when designing or modernizing electric motors for autonomous transport devices. A number of calculations and experiments were carried out, the analysis of which showed that when the diameter of the winding wire increases, the resistance of the armature winding decreases and, as a result, the starting torque increases, the power consumption and losses in the armature winding also decrease. But at the same time, the starting current at a constant voltage increases by more than two times, which requires an increase in the installed capacity of the power source. Increasing the diameter of the armature allows you to increase the number of conductors and the cross-section of the armature copper while simultaneously reducing the width of the magnet and reducing the magnetic flux. As a result, the starting torque of the electric motor decreases. It is shown that changing the winding scheme can significantly complicate the technological process of manufacturing a simple loop winding and a complex multi-pass wave winding with a larger number of parallel branches and can create problems with the commutation of the armature winding. The work confirmed that increasing the diameter of the winding wire is the most effective and least expensive way to increase the maximum torque of built-in DC torque motors with excitation from permanent magnets and a slotless armature design, which have found their application in devices of autonomous objects (platforms). At the same time, changes are made only in the design of the anchor - the diameter of the anchor iron is reduced and the number of turns in the section is reduced. The magnetic system, brush-collector unit, bearing shields (if available) remain structurally unchanged.

UAV Dynamic Object Tracking with Lightweight Deep Vision Reinforcement Learning

Several approaches have applied Deep Reinforcement Learning (DRL) to Unmanned Aerial Vehicles (UAVs) to do autonomous object tracking. These methods, however, are resource intensive and require prior knowledge of the environment, making them difficult to use in real-world applications. In this paper, we propose a Lightweight Deep Vision Reinforcement Learning (LDVRL) framework for dynamic object tracking that uses the camera as the only input source. Our framework employs several techniques such as stacks of frames, segmentation maps from the simulation, and depth images to reduce the overall computational cost. We conducted the experiment with a non-sparse Deep Q-Network (DQN) (value-based) and a Deep Deterministic Policy Gradient (DDPG) (actor-critic) to test the adaptability of our framework with different methods and identify which DRL method is the most suitable for this task. In the end, a DQN is chosen for several reasons. Firstly, a DQN has fewer networks than a DDPG, hence reducing the computational resources on physical UAVs. Secondly, it is surprising that although a DQN is smaller in model size than a DDPG, it still performs better in this specific task. Finally, a DQN is very practical for this task due to the ability to operate in continuous state space. Using a high-fidelity simulation environment, our proposed approach is verified to be effective.