Search
prof. dr hab. inż. Zdzisław Kowalczuk
Employment
- Head of Department at Department of Decision Systems and Robotics
- Professor at Department of Decision Systems and Robotics
Research fields
- Control
- robotics
- decision-making systems
- diagnosis
- modeling and identification
- adaptive systems
- optimization
- artificial intelligence
- humanoids
- haptic systems
- control system, control engineering, system modeling and identification, state estimation, system optimisation, failure detection, signal processing, artificial intelligence, computer science, computer implementation, adaptive and predictive control.
Publications
Filters
total: 219
Catalog Publications
Year 2024
-
Adaptive Optimal Discrete-Time Output-Feedback Using an Internal Model Principle and Adaptive Dynamic Programming
PublicationIn order to address the output feedback issue for linear discrete-time systems, this work suggests a brand-new adaptive dynamic programming (ADP) technique based on the internal model principle (IMP). The proposed method, termed as IMP-ADP, does not require complete state feedback, merely the measurement of input and output data. More specifically, based on the IMP, the output control problem can first be converted into a stabilization...
Year 2023
-
Cognitive motivations and foundations for building intelligent decision-making systems
PublicationConcepts based on psychology fit well with current research trends related to robotics and artificial intelligence. Biology-inspired cognitive architectures are extremely useful in building agents and robots, and this is one of the most important challenges of modern science. Therefore, the widely viewed and far-reaching goal of systems research and engineering is virtual agents and autonomous robots that mimic human behavior in...
-
Discrete identification of continuous non-linear and non-stationary dynamical systems that is insensitive to noise correlation and measurement outliers
PublicationThe paper uses specific parameter estimation methods to identify the coefficients of continuous-time models represented by linear and non-linear ordinary differential equations. The necessary approximation of such systems in discrete time in the form of utility models is achieved by the use of properly tuned `integrating filters' of the FIR type. The resulting discrete-time descriptions retain the original continuous parameterization...
-
International Conference on Diagnostics of Processes and Systems 2022
PublicationWydarzenie stanowiło 15 ogniwo cyklu organizowanego od 1996 roku, naprzemiennie przez Politechnikę Warszawską, Uniwersytet Zielonogórski oraz Politechnikę Gdańską. Tegoroczna edycja konferencji została objęta patronatem JM Rektora Politechniki Gdańskiej, prof. Krzysztofa Wilde, Komitetu Automatyki i Robotyki Polskiej Akademii Nauk, Towarzystwa Konsultantów Polskich (FSNT-NOT) oraz Polskiego Stowarzyszenia Pomiarów Automatyki i...
-
Zarząd POLSPAR w latach 2020-2023
PublicationW trakcie kadencji 2020-2023 na zebraniach Zarządu Członkowie często podejmowali dyskusję na temat najbardziej dokuczliwych problemów działania uczelni wynikających ze zmian w ustawie Prawo o Szkolnictwie Wyższym i Nauce, kompetencjach i formach naukowej aktywności rad naukowych dyscyplin, procedur nadawania stopni i tytułów naukowych, czy w końcu o nowej nazwie dyscypliny Automatyka, Elektronika, Elektrotechnika i Technologie...
Year 2022
-
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is not uncommon for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected...
-
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is common for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected as...
-
Autonomous Perception and Grasp Generation Based on Multiple 3D Sensors and Deep Learning
PublicationGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Autonomous pick-and-place system based on multiple 3Dsensors and deep learning
PublicationGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Categorization of emotions in dog behavior based on the deep neural network
PublicationThe aim of this article is to present a neural system based on stock architecture for recognizing emotional behavior in dogs. Our considerations are inspired by the original work of Franzoni et al. on recognizing dog emotions. An appropriate set of photographic data has been compiled taking into account five classes of emotional behavior in dogs of one breed, including joy, anger, licking, yawning, and sleeping. Focusing on a particular...
-
COVID-19 severity forecast based on machine learning and complete blood count data
PublicationProper triage of COVID-19 patients is a key factor in eective case management, especially with limited and insucient resources. In this paper, we propose a machine-aided diagnostic system to predict how badly a patient with COVID-19 will develop disease. The prognosis of this type is based on the parameters of commonly used complete blood count tests, which makes it possible to obtain data from a wide range of patients.We chose...
-
COVID-19 severity forecast based on machine learning and complete blood count data
PublicationProper triage of COVID-19 patients is a key factor in eective case management, especially with limited and insucient resources. In this paper, we propose a machine-aided diagnostic system to predict how badly a patient with COVID-19 will develop disease. The prognosis of this type is based on the parameters of commonly used complete blood count tests, which makes it possible to obtain data from a wide range of patients.We chose...
-
Machine-aided detection of SARS-CoV-2 from complete blood count
PublicationThe current gold standard for SARS-CoV-2 detection methods lacks the functionality to perform population screening. Complete blood count (CBC) tests are a cost-effective way to reach a wide range of people – e.g. according to the data of the Central Statistical Office of Poland from 2016, there are 3,000 blood diagnostic laboratories in Poland, and 46% of Polish people have at least one CBC test per year. In our work, we show...
-
Qualia: About Personal Emotions Representing Temporal Form of Impressions - Implementation Hypothesis and Application Example
PublicationThe aim of this article is to present the new extension of the xEmotion system as a computerized emotional system, part of an Intelligent System of Decision making (ISD) that combines the theories of affective psychology and philosophy of mind. At the same time, the authors try to find a practical impulse or evidence for a general reflection on the treatment of emotions as transitional states, which at some point may lead to the...
-
Resistant to correlated noise and outliers discrete identification of continuous non-linear non-stationary dynamic objects
PublicationIn this article, specific methods of parameter estimation were used to identify the coefficients of continuous models represented by linear and nonlinear differential equations. The necessary discrete-time approximation of the base model is achieved by appropriately tuned FIR linear integral filters. The resulting discrete descriptions, which retain the original continuous parameterization, can then be identified using the classical...
-
Resistant to correlated noise and outliers discrete identification of continuous non-linear non-stationary dynamic objects
PublicationIn this study, dedicated methods of parameter estimation were used to identify the coefficients of continuous models represented by linear and nonlinear differential equations. The necessary discrete-time approximation of the base model is achieved by appropriately tuned FIR linear integral filters. The resulting discrete descriptions, which retain the original continuous parameterization, can then be identified using the classical...
-
System diagnostyki oddechowej oparty na konwolucyjnych sieciach neuronowych
PublicationChoroby układu oddechowego człowieka od zawsze były obciążeniem dla całego społeczeństwa. Sytuacja stała się szczególnie trudna po wybuchu pandemii COVID-19. Jednak nawet teraz nierzadko zdarza się, że ludzie konsultują się ze swoim lekarzem zbyt późno, już po niepożądanym rozwinięciu się choroby. W celu ochrony pacjentów przed ciężką chorobą płuc, zaleca się jak najwcześniejsze wykrycie wszelkich objawów zaburzających pracę układu...
-
Training of Deep Learning Models Using Synthetic Datasets
PublicationIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
Year 2021
-
A Simple Neural Network for Collision Detection of Collaborative Robots
PublicationDue to the epidemic threat, more and more companies decide to automate their production lines. Given the lack of adequate security or space, in most cases, such companies cannot use classic production robots. The solution to this problem is the use of collaborative robots (cobots). However, the required equipment (force sensors) or alternative methods of detecting a threat to humans are usually quite expensive. The article presents...
-
Analytical ‘Steady-State’-Based Derivation and Clarification of the Courant-Friedrichs-Lewy Condition for Pipe Flow
PublicationThis article addresses the problem of choosing the optimal discretization grid for emulating fluid flow through a pipeline. The aggregated basic flow model is linearized near the operating point obtained from the steady state analytic solution of the differential equations under consideration. Based on this model, the relationship between the Courant number (μ) and the stability margin is examined. The numerically set coefficient...
-
Flow Process Models for Pipeline Diagnosis
PublicationThis chapter examines the problem of modeling and parameterization of the transmission pipeline flow process. First, the base model for discrete time is presented, which is a reference for other developed models. Then, the diagonal approximation (AMDA) method is proposed, in which the tridiagonal sub-matrices of the recombination matrix are approximated by their diagonal counterparts, which allows for a simple determination of...
-
Inteligentny system decyzyjny jako maszynowa realizacja procesów poznawczych i motywacyjnych
PublicationW niniejszej książce przedstawiono własny, kompletny i spójny oraz realizowalny model Inteligentnego Systemu Decyzji (ISD), oparty na wiedzy zaczerpniętej z psychologii z elementami motywacyjnymi, w skład którego wchodzi podsystem xEmotion. Wykorzystuje on funkcję i strukturę ludzkich procesów decyzyjnych oraz pewne szczegółowe mechanizmy dedykowane dla obliczeniowych systemów emocji. Model ISD jest w szczególności przeznaczony...
Year 2020
-
Diagnostic Models and Estimators for LDI in Transmission Pipelines
PublicationThis article considers and compares four analytical models of the pipeline flow process for leak detection and location tasks. The synthesis of these models is briefly outlined. Next, the methodology for generating data and diagnosing pipes is described, as well as experimental settings, assumptions and implemented scenarios. Finally, the quality of model-based diagnostic estimators has been evaluated for their bias, standard deviations...
-
Improved model of isothermal and incompressible fluid flow in pipelines versus the Darcy–Weisbach equation and the issue of friction factor
PublicationIn this article, we consider the modelling of stationary incompressible and isothermal one-dimensional fluid flow through a long pipeline. The approximation of the average pressure in the developed model by the arithmetic mean of inlet and outlet pressures leads to the known empirical Darcy–Weisbach equation. Most importantly, we also present another improved approach that is more accurate because the average pressure is estimated...
-
Interpretation and modeling of emotions in the management of autonomous robots using a control paradigm based on a scheduling variable
PublicationThe paper presents a technical introduction to psychological theories of emotions. It highlights a usable ideaimplemented in a number of recently developed computational systems of emotions, and the hypothesis thatemotion can play the role of a scheduling variable in controlling autonomous robots. In the main part ofthis study, we outline our own computational system of emotion – xEmotion – designed as a key structuralelement in...
-
Modele rurociągowych procesów przepływowych
PublicationW rozdziale analizowane jest zagadnienie modelowania oraz parametryzacji procesu przepływu w rurociągach przemysłowych. W pierwszej kolejności przedstawia się bazowy model dyskretny, do którego odnoszone są pozostałe syntezowane rozwiązania. Następnie proponuje się metodę aproksymacji diagonalnej (AMDA), w której stosuje się przybliżenia trójdiagonalnych podmacierzy macierzy rekombinacji za pomocą ich diagonalnych odpowiedników...
-
Rozpoznawanie urządzeń i wykrywanie nieautoryzowanego poboru energii elektrycznej na podstawie pomiaru napięcia
PublicationW pracy rozpatrywany jest problem wykrywania nieautoryzowanego poboru energii z sieci elektrycznej przez identyfikację podłączonych urządzeń. Estymacja stanu sieci, rozumianej jako zbiór podpiętych układów, wraz z ustaloną listą urządzeń dopuszczonych, pozwala określić, czy w danej chwili ma miejsce pobór nieautoryzowany. W celu wykrywania urządzeń, proponuje się wykorzystać prostą metodę opartą na analizie wysokoczęstotliwościowego...
Year 2019
-
Classification of objects in the LIDAR point clouds using Deep Neural Networks based on the PointNet model
PublicationThis work attempts to meet the challenges associated with the classification of LIDAR point clouds by means of deep learning. In addition to achieving high accuracy, the designed system should allow the classification of point clouds covering an area of several dozen square kilometers within a reasonable time interval. Therefore, it must be characterized by fast processing and efficient use of memory. Thus, the most popular approaches...
-
Elementy psychologii w kontekście autonomii robotów
PublicationW niniejszym opracowaniu zaprezentowano szerokie spektrum zagadnień związanych z psychologią poznawczą w kontekście antropoidalnej robotyki. W szczególności omówiono sposób przetwarzania informacji u człowieka, od bodźca do reakcji, tak aby przedstawioną wiedzę można było wykorzystać przy projektowaniu robotów autonomicznych. Na początku pracy szczegółowo omówiono procesy poznawcze: percepcję sensoryczną, spostrzeganie,...
-
Emotion monitoring system for drivers
PublicationThis article describes a new approach to the issue of building a driver monitoring system. Actual systems focus, for example, on tracking eyelid and eyebrow movements that result from fatigue. We propose a different approach based on monitoring the state of emotions. Such a system assumes that by using the emotion model based on our own concept, referred to as the reverse Plutchik’s paraboloid of emotions, the recognition of emotions...
-
Implementation of control system and tracking objects in a Quadcopter
PublicationIn this paper, we implement a quadcopter assembly with control and navigation module. The project also includes the design of the control panel for the operator which consists of a set of the micro-controller and the glove equipped with sensors and buttons. The panel has a touch screen which displays current parameters such as vehicle status, including information about orientation and geographical coordinates. The concept of quadcopter...
-
Intelligent Autonomous Vehicles
PublicationAdvanced mobile vehicles and robots have long been one of the main issues in engineering. They have various applications in emergency, lifeguarding and entertainment as well as in various industrial, civil and military systems. Among them, you can distinguish robots that can move in an open environment or operate only in predetermined confined spaces. Open world robots are very demanding because they have...
-
Intelligent monitoring the vertical dynamics of wheeled inspection vehicles
PublicationThe problem of intelligent monitoring of the vertical dynamics of wheeled inspection vehicles is addressed. With the independent MacPherson suspension system installed, the basic analysis focuses on the evaluation of the parameters of the so-called quarter car model. To identify a physically motivated continuous description, in practice, dedicated integral-horizontal filters are used. The obtained discrete model, which retains...
-
JamesBot - an intelligent agent playing StarCraft II
PublicationThe most popular method for optimizing a certain strategy based on a reward is Reinforcement Learning (RL). Lately, a big challenge for this technique are computer games such as StarCraft II which is a real-time strategy game, created by Blizzard. The main idea of this game is to fight between agents and control objects on the battlefield in order to defeat the enemy. This work concerns creating an autonomous bot using reinforced...
-
Sphere Drive and Control System for Haptic Interaction With Physical, Virtual, and Augmented Reality
PublicationA system for haptic interaction with physical, virtual, and augmented realities, founded on drive and measurement elements (DMEs), is considered. The system consists of eight DME rolls equipped with linear actuators, able to measure their angular velocity, drive the sphere, and adjust downforce (pressing the roll against the sphere). Two modeling issues are addressed. Special effort is put in to compensate for various technical...
-
The impact of the temperament model on the behavior of an autonomous driver
PublicationBecause it is generally believed that the personality and temperament of a human driver influence his/her behavior on the road, the article presents a computational model of the temperament of an autonomous agent - a driver. First, a short review of the four ideas of Galen’s temperament in psychology is presented. Temperament traits are grouped into four other sets, one of which is chosen for implementation in the project of integration...
Year 2018
-
An Intelligent Decision-Making System for Autonomous Units Based on the Mind Model
PublicationThis article presents a specific part of current trends in autonomous robotics. It pays special attention to the basic aspects of cognitive architecture. After a brief introduction, we shortly describe the Intelligent System of Decision-making developed at the Gdansk University of Technology.
-
Analytical Steady-State Model of the Pipeline Flow Process
PublicationThe paper addresses the issue of modeling the flow process in transmission pipelines. A base model used for numerical simulation is introduced. Under certain assumptions concerning steady state analysis, the differential equations describing the process are solved analytically for two cases: zero and nonzero inclination angle α. These equations describe a constant flow rate and a corresponding distribution of the pressure along...
-
Approximate Criteria for the Evaluation of Truly Multi-Dimensional Optimization Problems
PublicationIn this paper we propose new improved approximate quality criteria useful in assessing the efficiency of evolutionary multi-objective optimization (EMO). In the performed comparative study we take into account the various EMO algorithms of the state-of-the-art, in order to objectively assess the EMO performance in highly dimensional spaces. It is well known that useful executive criteria, such as those based on the true Pareto...
-
Approximate Quality Criteria for Difficult Multi-Objective Optimization Problems
PublicationThis paper introduces approximate analytic quality criteria useful in assessing the efficiency of evolutionary multi-objective optimization (EMO) procedures. We present a summary of extensive research into computing. In the performed comparative study we take into account the various approaches of the state-of-the-art, in order to objectively assess the EMO performance in highly dimensional spaces; where some executive criteria,...
-
Approximate Quality Criteria for Difficult Multi-Objective Optimization Problems
PublicationThis paper introduces approximate analytic quality criteria useful in assessing the efficiency of evolutionary multi-objective optimization (EMO) procedures. We present a summary of extensive research into computing. In the performed comparative study we take into account the various approaches of the state-of-the-art, in order to objectively assess the EMO performance in highly dimensional spaces; where some executive criteria,...
-
Constructing autonomous agents using the cognitive-emotional architecture of the mind
PublicationThe article discusses an important issue regarding the humanoid aspects of modern science related to the autonomy of systems and robotization. Particular attention is paid to the basic aspects of cognitive architecture. After a short introduction, the Intelligent Decision Making System, developed at the ETI Faculty of the Gdańsk University of Technology, is described.
-
Embodying Intelligence in Autonomous and Robotic Systems with the Use of Cognitive Psychology and Motivation Theories
PublicationThe article discusses, on a certain level of abstraction and generalization, a coherent anthropological approach to the issue of controlling autonomous robots or agents. A contemporary idea can be based on appropriate modeling of the human mind using the available psychological knowledge. One of the main reasons for developing such projects is the lack of available and effective top-down approaches resulting from the known research...
-
Estimation of a Stochastic Burgers' Equation Using an Ensemble Kalman Filter
PublicationIn this work, we consider a difficult problem of state estimation of nonlinear stochastic partial differential equations (SPDE) based on uncertain measurements. The presented solution uses the method of lines (MoL), which allows us to discretize a stochastic partial differential equation in a spatial dimension and represent it as a system of coupled continuous-time ordinary stochastic differential equations (SDE). For such a system...
-
Gender approaches to evolutionary multi-objective optimization using pre-selection of criteria
PublicationA novel idea to perform evolutionary computations (ECs) for solving highly dimensional multi-objective optimization (MOO) problems is proposed. Following the general idea of evolution, it is proposed that information about gender is used to distinguish between various groups of objectives and identify the (aggregate) nature of optimality of individuals (solutions). This identification is drawn out of the fitness of individuals...
-
Identification of Continuous Systems - Practical Issues of Insensitivity to Perturbations
PublicationIn this paper the issue of continuous systems estimation, insensitive to certain perturbations, is discussed. Such an approach has rational advantages, especially when robust schemes are used to assist a target system responsible for industrial diagnostics. This requires that estimated model parameters are generated on-line, and their values are reliable and to a great extent accurate. Practical hints are suggested to challenge...
-
Identification of Emotions Based on Human Facial Expressions Using a Color-Space Approach
PublicationHCI technology improves human-computer interaction. Such communication can be carried out with the use of emotions that are visible on the human face since birth. In this paper the Emotion system for detecting and recognizing facial expressions, developed in the MSc work, is presented. The system recognizes emotion from webcam video in real time. It is based on color segmentation and morphological operations. The system uses a...
-
Reduction of Computational Complexity in Simulations of the Flow Process in Transmission Pipelines
PublicationThe paper addresses the problem of computational efficiency of the pipe-flow model used in leak detection and identification systems. Analysis of the model brings attention to its specific structure, where all matrices are sparse. With certain rearrangements, the model can be reduced to a set of equations with tridiagonal matrices. Such equations can be solved using the Thomas algorithm. This method provides almost the same values...
-
River Flow Simulation Based on the HEC-RAS System
PublicationThis work considers the problem of river floods, and presents a computer solution that can be used to predict such a threat. The basic tool, called Hydrologic Engineering Centers for River Analysis System (HEC-RAS), and created by the US Army Corps of Engineering, is well developed; and the models created in the system HEC-RAS are quite realistic. For the purpose of solving practical national flood problems, simplified static and...
-
The Use of an Autoencoder in the Problem of Shepherding
PublicationThis paper refers to the problem of shepherding clusters of passive agents consisting of a large number of objects by a team of active agents. The problem of shepherding and the difficulties that arise with the increasing number of data describing the location of agents have been described. Several methods for reducing the dimensionality of data are presented. Selected autoencoding method using a Restricted Boltzmann Machine is...
seen 7170 times