This work describes 3D reconstruction using stereo vision. It presents methods for automatic localization of corresponding points in both images and their reprojection into 3D space. Application created can be used for navigation of a robot and object avoidance. Second part of the document describes chosen components of the robot. Path finding algorithms are also discussed, particulary Voronoi's diagram.

Hexapod, ROS, Gazebo, Simulation, C++, Python, Node, Service, Publisher, Subscriber, Topic, URDF, SDF, AX-12+, USB2Dynamixel, CM-530, King Spider, Robotis, Navigation

<p>У дисертацији је представљен нови рачунарски модел<br />дуготрајне меморије, намењен за примене у конверзаци-<br />оним роботским агентима. Предложени модел је симболи-<br />чки, са методолошког аспекта, и инспирисан је изабраним<br />когнитивним механизмима људског меморијског система,<br />који укључују интеграцију менталних репрезентација,<br />семантичку категоризацију, асоцијативно учење и контек-<br />стно зависно селектовање информација. У основи модела<br />се налази симболички приступ за аутоматско моделовање<br />домена интеракције између човека и робота. Релевантни<br />функциoнaлни aспeкт предложеног модела oднoси се нa<br />прoблeме адекватног aктивирaњa делова дуготрајне<br />мeмoриje, у складу са спољашњим стимулансима, истори-<br />јом интеракције и тренутним контекстом интеракције. Ниво<br />апстракције у спецификацији модела је довољан да<br />омогући примену модела у широком спектру просторних,<br />униформних домена који су карактеристични за интеракцију<br />између човека и робота, а ниво детаља у спецификацији је<br />довољан за рачунарску имплементацију модела.</p> / <p>U disertaciji je predstavljen novi računarski model<br />dugotrajne memorije, namenjen za primene u konverzaci-<br />onim robotskim agentima. Predloženi model je simboli-<br />čki, sa metodološkog aspekta, i inspirisan je izabranim<br />kognitivnim mehanizmima ljudskog memorijskog sistema,<br />koji uključuju integraciju mentalnih reprezentacija,<br />semantičku kategorizaciju, asocijativno učenje i kontek-<br />stno zavisno selektovanje informacija. U osnovi modela<br />se nalazi simbolički pristup za automatsko modelovanje<br />domena interakcije između čoveka i robota. Relevantni<br />funkcionalni aspekt predloženog modela odnosi se na<br />probleme adekvatnog aktiviranja delova dugotrajne<br />memorije, u skladu sa spoljašnjim stimulansima, istori-<br />jom interakcije i trenutnim kontekstom interakcije. Nivo<br />apstrakcije u specifikaciji modela je dovoljan da<br />omogući primenu modela u širokom spektru prostornih,<br />uniformnih domena koji su karakteristični za interakciju<br />između čoveka i robota, a nivo detalja u specifikaciji je<br />dovoljan za računarsku implementaciju modela.</p> / <p>This dissertation proposes a novel computational model of<br />long-term memory intended for applications in conversational<br />robotic agents. The proposed model is symbolic, from the<br />methodological point of view, and cognitively-inspired by<br />selected cognitive mechanisms of the human memory system,<br />including integration of mental representations, semantic<br />categorization, associative learning, and context-dependent<br />information selection. In the core of the model there is a<br />symbolic approach to automatic modeling of domains of<br />human-robot interaction. The relevant functional aspect of the<br />proposed model concerns the problems of context-dependent<br />retrieval from long-term memory, in accordance with external<br />stimuli, the interaction history, and the current context of<br />interaction. The level of abstraction in the model is sufficient to<br />enable generalization of the model over a range of spatial,<br />uniform domains that are characterical for human-robot<br />interaction, while the level of detail contained in the<br />specification of the model is sufficient for a computational<br />implementation.</p>

In this master thesis are presented design and testing processes of communication between elderly and single-purpose robot. At the beginning design and architecture of the system for testing are described. Communication understandability was checked in interviews with nineteen people. Other opinions on usability or affordability of automatic device, which is used for picking and lifting objects from the ground, are presented in this thesis. Results from questionnaires and measurements showed that working with the robot is pleasant and understandable. Even senior is able to learn effective communication with this device. The main finding is that even robot communicates through nonverbal sounds, is easy to understand it. Choosing of sound set has no influence on communication understandability.

The diploma thesis deals with the construction of a walking mobile robot, which is intended for passing through a rugged or forest terrain, whose task is to collect the sample. The first part is devoted to the review of walking robots. Follow-up an analysis of two-legged and four-leg walking robot technologies and a brief overview of drives. The second part is devoted to problem analysis and design variant. The work contains 4 design variants in the form of schemes. Using the multi-criteria analysis, the variants were evaluated and the optimal variant was chosen taking into account the representative parameters. The third part is devoted to the construction of the chosen variant, it is divided into body and leg construction. The overall design is processed in the form of a virtual 3D model. In the leg construction, the design itself, but also the calculations of drives, shafts, gears and belt transmissions are solved. The end of the thesis is devoted to drawing documentation based on 3D model and economic evaluation. Follow-up and discussion with possible continuation and use in practice.

This diploma thesis deals with the problem of mobile robot localisation in the environment based on current 2D and 3D sensor data and previous records. Work is focused on detecting previously visited places by robot. The implemented system is suitable for loop detection, using the Gestalt 3D descriptors. The output of the system provides corresponding positions on which the robot was already located. The functionality of the system has been tested and evaluated on LiDAR data.

This paper addresses the problem of mobile robot localization based on current 2D and 3D data and previous records. Focusing on practical loop detection in the trajectory of a robot. The objective of this work was to evaluate current methods of image processing and depth data for issues of localization in environment. This work uses Bag of Words for 2D data and environment of point cloud with Viewpoint Feature Histogram for 3D data. Designed system was implemented and evaluated.

This document deals with an image points of interest detection possibilities, especially corner detectors. Many applications which are interested in computer vision needs these points as their necessary step in the image processing. It describes the reasons why it is so useful to find these points and shows some basic methods to find them. There are compared features of these methods at the end.

<p>У овој дисертацији се разматрају изабрани аспекти истраживачког проблема спецификације, дизајнирања и имплементације конверзационих робота као асистивних средстава у терапији деце са церебралном парализом. Доприноси ови тезе су следећи. (i) Предложена је архитектура конверзационог агента опште намене која омогућава флексибилно интегрисање модула различитих функционалности. (ii) Дефинисана је и имплементирана адаптивна бихевиористичка стратегија коју робот примењује у интеракцији са децом. (iii) Предложена дијалошка стратегија је спроведена и позитивно процењена у интеркацији између деце и робота у реалистичном терапеутском контексту. (iv) Коначно, предложен је приступ за аутоматско детектовање критичних промена у дијалогу, заснован на појму нормализоване дијалошке ентропије.</p> / <p>U ovoj disertaciji se razmatraju izabrani aspekti istraživačkog problema specifikacije, dizajniranja i implementacije konverzacionih robota kao asistivnih sredstava u terapiji dece sa cerebralnom paralizom. Doprinosi ovi teze su sledeći. (i) Predložena je arhitektura konverzacionog agenta opšte namene koja omogućava fleksibilno integrisanje modula različitih funkcionalnosti. (ii) Definisana je i implementirana adaptivna bihevioristička strategija koju robot primenjuje u interakciji sa decom. (iii) Predložena dijaloška strategija je sprovedena i pozitivno procenjena u interkaciji između dece i robota u realističnom terapeutskom kontekstu. (iv) Konačno, predložen je pristup za automatsko detektovanje kritičnih promena u dijalogu, zasnovan na pojmu normalizovane dijaloške entropije.</p> / <p>This doctoral dissertation considers selected aspects of the research problem of specification, design, and implementation of conversational robots as assistive tools in therapy for children with cerebral palsy. This dissertation has made the following contributions: (i) It proposes a general architecture for conversational agents that allows for flexible integration of software modules implementing different functionalities. (ii) It introduces and implements an adaptive behavioural strategy that is applied by the robot in interaction with children. (iii) The proposed dialogue strategy is applied and evaluated in interaction between children and the robot MARKO, in realistic therapeutic settings. (iv) Finally, the dissertation proposes an approach to automatic detection of critical changes in human-machine interaction, based on the notion of normalized interactional entropy.</p>

This paper deals with the topic of design of a navigation system for an autonomous mobile robot in a park-like environment. Precisely, designing methods for road detection using available sensoric system, designing a mathematical model for fusion of these data, and suggesting a representation of an environment suitable for planning and local navigation.