Interoperability development between Autonomous Mobile Mobots, Auto- mated Guided Vehicles and their fleet managers provided by different brands became a highly important topic in the factory and warehouse management industry. The compatibility between the providers would provide endless opportunities for the customers to build scalable, flexible, and dynamic systems. The thesis develops a program synthesis method that is capable of making conversions between data structures. The results provide the programmers with a tool that can be used to create function compositions by providing input-output pairs and can save a significant amount of time. The study solves the search problem using Context-free grammar and a beam search guided by a neural network. The work compares the performance of three different artificial intelligence structures recurrent neural networks, long short-term memory networks, and gated recurrent unit networks, and validates the solution on a test set that consists of lines from data structures that are used in the Autonomous Mobile Robot industry combined with some generated data to measure performance in regards of the generalization power. / Interoperabilitetsutveckling mellan Autonoma Mobila Robotar, Automatiserade Guidade Fordon och deras flottförvaltare från olika varumärken har blivit ett mycket viktigt ämne inom fabriks- och lagerhanteringsbranschen. Kompatibiliteten mellan leverantörerna skulle ge oändliga möjligheter för kunderna att bygga skalbara, flexibla och dynamiska system. Avhandlingen utvecklar en programssyntesmetod som kan göra omvandlingar mellan datastrukturer. Resultaten ger programmerare ett verktyg som kan användas för att skapa funktionskompositioner genom att tillhandahålla in- och utdata- par och kan spara betydande tid. Studien löser sökproblemet med hjälp av kontextfri grammatik och en strålsökning som styrs av ett neuralt nätverk. Arbetet jämför prestandan hos tre olika konstgjorda intelligensstrukturer: ”recurrent neural networks", ”long short-term memory networks", och ”gated recurrent unit networks", och validerar lösningen på en testuppsättning som består av rader från datastrukturer som används inom den autonoma mobila robotindustrin kombinerat med några genererade data för att mäta prestanda med avseende på generaliseringskraften.

Les robots industriels ont évolué fondamentalement ces dernières années pour répondre aux exigences industrielles de machines et mécanismes toujours plus performants. Ceci se traduit aujourd’hui par de nouveaux robots anthropomorphes plus adaptés laissant entrevoir la réalisation de tâches plus complexes comme la découpe d’objets déformables telle que la découpe de viande ou soumis à de fortes sollicitations comme l’usinage. L’étude du comportement des robots anthropomorphes, à structures parallèles ou hybrides montre une anisotropie aussi bien cinématique, que dynamique, impactant la précision attendue. Ces travaux de thèse étudient l’intégration des redondances cinématiques qui permettent de pallier en partie ce problème en positionnant au mieux la tâche à réaliser dans un espace de travail compatible avec les capacités attendues. Ces travaux ont suivi une démarche en trois étapes : la modélisation analytique de cellules robotiques par équivalent sériel basée sur la méthode TCS, la formalisation des contraintes des processus de découpe de viande et d’usinage et une résolution par optimisation multicritère. Une première originalité de ces travaux réside en le développement d’un modèle à 6 degrés de liberté permettant d’analyser les gestes de l’opérateur qui optimise naturellement le comportement de son bras pour garantir la tâche qu’il réalise. La seconde originalité concerne le placement optimisé des redondances structurales (cellules à 9 ddls) où les paramètres de positionnement sont incorporés comme des variables pilotables (cellule à 11 ddls). Ainsi, ces travaux de thèse apportent des contributions à : - la définition de critères adaptés à la réalisation de tâches complexes et sollicitantes pour la gestion des redondances cinématiques ; - l’identification du comportement des structures sous sollicitations par moyen métrologique (Laser tracker) et l’auto-adaptation des trajectoires par l’utilisation d’une commande en effort industrielle ; - l’optimisation du comportement permettant l’amélioration de la qualité de réalisation des différents processus de coupe (découpe de viande et usinage). / Industrial robots have evolved fundamentally in recent years to reach the industrial requirements. We now find more suitable anthropomorphic robots leading to the realization of more complex tasks like deformable objects cutting such as meat cutting or constrained to high stresses as machining. The behavior study of anthropomorphic robots, parallel or hybrid one highlights a kinematic and dynamic anisotropy, which impacts the expected accuracy. This thesis studied the integration of the kinematic redundancy that can partially overcome this problem by well setting the task to achieve it in a space compatible with the expected capacity. This work followed a three-step approach: analytical modeling of robotic cells by serial equivalent based on the TCS method, formalizing the constraints of meat cutting process and machining process and a multicriteria optimization.The first originality of this work focuses on the development of a 6 DoFs model to analyze the operator actions who naturally optimizes his arm behavior to ensure the task it performs. The second originality concerns the optimized placement of structural redundancy (9 DoFs robotic cell) where positioning parameters are incorporated as controllable variables (11 DoFs robotic cell). Thus, the thesis makes contributions to : - the definition of criteria adapted to the realization of complex and under high stress task for the management of the kinematic redundancy; - the structural behavior identification, under stress, by metrology tools (Laser tracker ) and the self- adaptation paths by using an industrial force control; - the behavior optimization to improve the cutting process quality (meat cutting and machining).

Industrial robot manipulators are general-purpose machines used for industrial automation in order to increase productivity, flexibility, and quality. Other reasons for using industrial robots are cost saving, and elimination of heavy and health-hazardous work. Robot motion control is a key competence for robot manufacturers, and the current development is focused on increasing the robot performance, reducing the robot cost, improving safety, and introducing new functionalities. Therefore, there is a need to continuously improve the models and control methods in order to fulfil all conflicting requirements, such as increased performance for a robot with lower weight, and thus lower mechanical stiffness and more complicated vibration modes. One reason for this development of the robot mechanical structure is of course cost-reduction, but other benefits are lower power consumption, improved dexterity, safety issues, and low environmental impact. This thesis deals with three different aspects of modeling and control of flexible, i.e., elastic, manipulators. For an accurate description of a modern industrial manipulator, the traditional flexible joint model, described in literature, is not sufficient. An improved model where the elasticity is described by a number of localized multidimensional spring-damper pairs is therefore proposed. This model is called the extended flexible joint model. This work describes identification, feedforward control, and feedback control, using this model. The proposed identification method is a frequency-domain non-linear gray-box method, which is evaluated by the identification of a modern six-axes robot manipulator. The identified model gives a good description of the global behavior of this robot. The inverse dynamics control problem is discussed, and a solution methodology is proposed. This methodology is based on a differential algebraic equation (DAE) formulation of the problem. Feedforward control of a two-axes manipulator is then studied using this DAE approach. Finally, a benchmark problem for robust feedback control of a single-axis extended flexible joint model is presented and some proposed solutions are analyzed.

<p>Industrial robot manipulators are general-purpose machines used for industrial automation in order to increase productivity, flexibility, and quality. Other reasons for using industrial robots are cost saving, and elimination of heavy and health-hazardous work. Robot motion control is a key competence for robot manufacturers, and the current development is focused on increasing the robot performance, reducing the robot cost, improving safety, and introducing new functionalities. Therefore, there is a need to continuously improve the models and control methods in order to fulfil all conflicting requirements, such as increased performance for a robot with lower weight, and thus lower mechanical stiffness and more complicated vibration modes. One reason for this development of the robot mechanical structure is of course cost-reduction, but other benefits are lower power consumption, improved dexterity, safety issues, and low environmental impact.</p><p>This thesis deals with three different aspects of modeling and control of flexible, i.e., elastic, manipulators. For an accurate description of a modern industrial manipulator, the traditional flexible joint model, described in literature, is not sufficient. An improved model where the elasticity is described by a number of localized multidimensional spring-damper pairs is therefore proposed. This model is called the extended flexible joint model. This work describes identification, feedforward control, and feedback control, using this model.</p><p>The proposed identification method is a frequency-domain non-linear gray-box method, which is evaluated by the identification of a modern six-axes robot manipulator. The identified model gives a good description of the global behavior of this robot.</p><p>The inverse dynamics control problem is discussed, and a solution methodology is proposed. This methodology is based on a differential algebraic equation (DAE) formulation of the problem. Feedforward control of a two-axes manipulator is then studied using this DAE approach.</p><p>Finally, a benchmark problem for robust feedback control of a single-axis extended flexible joint model is presented and some proposed solutions are analyzed.</p>

Les robots industriels ont évolué fondamentalement ces dernières années pour répondre aux exigences industrielles de machines et mécanismes toujours plus performants. Ceci se traduit aujourd’hui par de nouveaux robots anthropomorphes plus adaptés laissant entrevoir la réalisation de tâches plus complexes et soumis à de fortes sollicitations comme durant l’usinage. L’étude du comportement des robots anthropomorphes, à structures parallèles ou hybrides montre une anisotropie aussi bien cinématique, que dynamique, impactant la précision attendue. Ces travaux de thèse étudient l’intégration des redondances cinématiques qui permettent de pallier en partie ce problème en positionnant au mieux la tâche à réaliser dans un espace de travail compatible avec les capacités attendues. Ces travaux ont permis d’améliorer notre outil d’optimisation et de le tester à la fois sur un modèle Eléments Finis du robot et sur le robot réel. Ainsi, ces travaux de thèse apportent des contributions à : - la définition de critères adaptés à la réalisation de tâches complexes et sollicitantes pour la gestion des redondances cinématiques ; - l’identification du comportement des structures sous sollicitations par moyen métrologique (Laser tracker) ; - l’optimisation du comportement permettant l’amélioration de la qualité de réalisation des opérations d’usinage ; - la modélisation Eléments Finis des robots prenant en compte l’identification des rigidités des corps et articulaires. / Industrial robots have evolved fundamentally in recent years to reach the industrial requirements. We now find more suitable anthropomorphic robots leading to the realization of more complex tasks like deformable objects cutting such as meat cutting or constrained to high loading like during machining. The behavior study of anthropomorphic robots, parallel or hybrid one highlights a kinematic and dynamic anisotropy, which impacts the expected accuracy.This thesis studied the integration of the kinematic redundancy that can partially overcome this problem by well setting the task to achieve it in a space compatible with the expected capacity.This work helped us to improve our optimization tool and to try it on both FE model of the robot and real robot.Thus, the thesis makes contributions to: - the definition of criteria adapted to the realization of complex and under high loading task for the management of the kinematic redundancy; - the structural behavior identification, under loading, by metrology tools (Laser tracker) ; - the behavior optimization to improve the cutting process quality during machining ; - robots finite elements modeling using stiffness identification for both bodies and joints.

La thèse porte sur la sélection de poses optimales pour la calibration géométrique et élasto-statique de robots industriels utilisés pour l'usinage de pièces des grandes dimensions. Une attention particulière est accordée à l'amélioration de la précision de positionnement du robot après compensation des erreurs géométriques et élasto-statiques. Pour répondre aux exigences industrielles des opérations d’usinage, une nouvelle approche pour la définition d'essais pour la calibration de robots sériels et quasi-sériels est proposée. Cette approche est basée sur un nouveau critère de performance, orienté applications industrielles, qui évalue la qualité du plan d'essais pour la calibration via la précision de positionnement du manipulateur après compensation d'erreurs, et tient compte des spécificités de la tâche manufacturière à réaliser au moyen de configurations tests. Contrairement aux travaux précédents, l'approche développée requiert seulement une mesure des positions de points et non d’orientation de corps rigides à l’aide d’un système de mesure externe tel qu’un laser tracker. Cette méthode permet ainsi d'éviter les problèmes de non-homogénéité dans les équations d'identification. Par ailleurs, afin de prendre en compte l'impact du compensateur de gravité,qui induit une chaîne cinématique fermée, le modèle de raideur est étendu en y incluant certains paramètres élasto-statiques dont les valeurs dépendent de la configuration du robot. Une méthodologie pour la calibration des modèles de compensateurs de gravité est ainsi proposée. Les avantages des techniques développées pour la calibration de robots industriels dédiés à des opérations d’usinage sont validés et mis en évidence expérimentalement, à travers la calibration géométrique et élasto-statique du robot industriel KUKAKR-270. / The thesis deals with the optimal pose selection for geometric and elastostatic calibration for industrial robots employed in machining of large parts. Particular attention is paid to the improvement of robot positioning accuracy after compensation of the geometric and elastostatic errors. To meet the industrial requirements of machining operations, a new approach for calibration experiments design for serial and quasi-serial industrial robots is proposed. This approach is based on a new industry-oriented performance measure that evaluates the quality of calibration experiment plan via the manipulator positioning accuracy after error compensation, and takes into account the particularities of prescribed manufacturing task by introducing manipulator test-poses. Contrary to previous works, the developed approach employs an enhanced partial pose measurement method, which uses only direct position measurements from an external device and allows us to avoid the non-homogeneity of relevant identification equations. In order to consider the impact of gravity compensator that creates closed-loop chains, the conventional stiffness model is extended by including in it some configuration dependent elastostatic parameters, which are assumed to be constant for strictly serial robots. Corresponding methodology for calibration of the gravity compensator models is also proposed. The advantages of the developed calibration techniques are validated via experimental study, which deals with geometric and elastostatic calibration of a KUKA KR-270 industrial robot.

The industry is moving towards a higher degree of automation and connectivity, where previously manual operations are being adapted for interconnected industrial robots. This thesis focuses specifically on the automation of tightening applications with pre-tightened bolts and collaborative robots. The use of 3D computer vision is investigated for direct localization of bolts, to allow for flexible assembly solutions. A localization algorithm based on 3D data is developed with the intention to create a lightweight software to be run on edge devices. A restrictive use of deep learning classification is therefore included, to enable product flexibility while minimizing the computational load. The cloud-to-edge and cluster-to-edge trade-offs for the chosen application are investigated to identify smart offloading possibilities to cloud or cluster resources. To reduce operational delay, image partitioning to sub-image processing is also evaluated, to more quickly start the operation with a first coordinate and to enable processing in parallel with robot movement. Four different hardware architectures are tested, consisting of two different Single Board Computers (SBC), a cluster of SBCs and a high-end computer as an emulated local cloud solution. All systems but the cluster is seen to perform without operational delay for the application. The optimal hardware architecture is therefore found to be a consumer grade SBC, being optimized on energy efficiency, cost and size. If only the variance in communication time can be minimized, the cluster shows potential to reduce the total calculation time without causing an operational delay. Smart offloading to deep learning optimized cloud resources or a cluster of interconnected robot stations is found to enable increasing complexity and robustness of the algorithm. The SBC is also found to be able to switch between an edge and a cluster setup, to either optimize on the time to start the operation or the total calculation time. This offers a high flexibility in industrial settings, where product changes can be handled without the need for a change in visual processing hardware, further enabling its integration in factory devices. / Industrin rör sig mot en högre grad av automatisering och uppkoppling, där tidigare manuella operationer anpassas för sammankopplade industriella robotar. Denna masteruppsats fokuserar specifikt på automatiseringen av åtdragningsapplikationer med förmonterade bultar och kollaborativa robotar. Användningen av 3D-datorseende undersöks för direkt lokalisering av bultar, för att möjliggöra flexibla monteringslösningar. En lokaliseringsalgoritm baserad på 3Ddata utvecklas med intentionen att skapa en lätt mjukvara för att köras på Edge-enheter. En restriktiv användning av djupinlärningsklassificering är därmed inkluderad, för att möjliggöra produktflexibilitet tillsammans med en minimering av den behövda beräkningskraften. Avvägningarna mellan edge- och moln- eller klusterberäkning för den valda applikationen undersöks för att identifiera smarta avlastningsmöjligheter till moln- eller klusterresurser. För att minska operationell fördröjning utvärderas även bildpartitionering, för att snabbare kunna starta operationen med en första koordinat och möjliggöra beräkningar parallellt med robotrörelser. Fyra olika hårdvaruarkitekturer testas, bestående av två olika enkortsdatorer, ett kluster av enkortsdatorer och en marknadsledande dator som en efterliknad lokal molnlösning. Alla system utom klustret visar sig prestera utan operationell fördröjning för applikationen. Den optimala hårdvaruarkitekturen visar sig därmed vara en konsumentklassad enkortsdator, optimerad på energieffektivitet, kostnad och storlek. Om endast variansen i kommunikationstid kan minskas visar klustret potential för att kunna reducera den totala beräkningstiden utan att skapa operationell fördröjning. Smart avlastning till djupinlärningsoptimerade molnresurser eller kluster av sammankopplade robotstationer visar sig möjliggöra ökad komplexitet och tillförlitlighet av algoritmen. Enkortsdatorn visar sig även kunna växla mellan en edge- och en klusterkonfiguration, för att antingen optimera för tiden att starta operationen eller för den totala beräkningstiden. Detta medför en hög flexibilitet i industriella sammanhang, där produktändringar kan hanteras utan behovet av hårdvaruförändringar för visuella beräkningar, vilket ytterligare möjliggör dess integrering i fabriksenheter.

The first chapter describes the situation of the use of industrial robots in the market of machine-building production. The sales volumes of modern robots are considered depending on the industries where they are applied. Comparative statistics on the implementation of robots for performing various operations are also given. The level of robotization in Russia and in the world is analyzed. The advantages and disadvantages associated with the introduction of robots into enterprises are revealed. In the second chapter, the topic of flexible production systems is discussed. The existing systems for designing flexible machining modules are evaluated. It also provides a definition of risk, its evaluation. The types of risks were identified during the implementation of the robotic machine module at the enterprise of the machine-building complex. Methods for determining the magnitude of risks are presented. The third chapter presents the most commonly used tools for risk analysis. The main features of the expert assessment method are considered in details. The sequence of actions of the expert survey is presented. On the basis of the chosen method, an order of actions for assessing the risks of the robotic modules presented in the second chapter of the CAD algorithms was developed. Visual images based on summary tables of each CAD algorithm are constructed. Measures to eliminate intolerable risks are suggested. The master's thesis consists of an explanatory note of 80 pages, 18 figures, 11 tables and includes an introduction, three chapters, conclusion, a list of sources used, consisting of 35 titles, and three appendixes. / В 1-й главе описывается ситуация применения промышленных роботов на рынке машиностроительного производства. Рассмотрены объемы продаж современных роботов в зависимости от отраслей, где они применяются. Также была приведена сравнительная статистика по реализации роботов для выполнения различных операций. Проанализирован уровень роботизации в России и в мире. Выявлены преимущества и недостатки, связанные с внедрением роботов на предприятия. Во 2-й главе затрагивается тема гибких производственных систем. Осуществляется оценка существующих систем проектирования гибких модулей механообработки. Также дается определение риска, его оценки. Были выявлены виды рисков при внедрении роботизированного станочного модуля на предприятии машиностроительного комплекса. Приводятся методы для определения величины рисков. В 3-й главе представлены наиболее часто используемые инструменты для анализа рисков. Рассмотрены более подробно основные особенности метода экспертных оценок. Представлена последовательность действий экспертного опроса. На основе выбранного метода был разработан порядок действий оценки рисков приведенных во второй главе алгоритмов САПР роботизированных модулей. Построены наглядные изображения на основе сводных таблиц каждого алгоритма САПР. Предложены мероприятия по устранению непереносимых рисков. Магистерская диссертация состоит из пояснительной записки объемом 80 страниц, 18 рисунков, 11 таблиц и включает в себя введение, три главы, заключение, список использованных источников, состоящий из 35 наименований, а также три приложения.

Industrial robots are a key component for several industrial applications. Like all mechanical tools, they do not last forever. The solution to extend the life of the machine is to perform maintenance on the degraded components. The optimal approach is called predictive maintenance, which aims to forecast the best moment for performing maintenance on the robot. This minimizes maintenance costs as well as prevents mechanical failure that can lead to unplanned production stops. There already exist methods to perform predictive maintenance on industrial robots, but these methods require additional sensors. This research aims to predict the anomalies by only using data from the sensors that already are used to control the robot. A machine learning approach is proposed for implementing predictive maintenance of industrial robots, using the torque profiles as input data. The algorithms selected are tested on simulated data created using wear and temperature models. The torque profiles from the simulator are used to extract a health index for each joint, which in turn are used to detect anomalous states of the robot. The health index has a fast exponential growth trend which is difficult to predict in advance. A Gaussian process regressor, an Exponentron, and hybrid algorithms are applied for the prediction of the time series of the health state to implement the predictive maintenance. The predictions are evaluated considering the accuracy of the time series prediction and the precision of anomaly forecasting. The investigated methods are shown to be able to predict the development of the wear and to detect the anomalies in advance. The results reveal that the hybrid approach obtained by combining predictions from different algorithms outperforms the other solutions. Eventually, the analysis of the results shows that the algorithms are sensitive to the quality of the data and do not perform well when the data present a low sampling rate or missing samples. / Industrirobotar är en nyckelkomponent för flera industriella applikationer. Likt alla mekaniska verktyg håller de inte för alltid. Lösningen för att förlänga maskinens livslängd är att utföra underhåll på de slitna komponenterna. Det optimala tillvägagångssättet kallas prediktivt underhåll, vilket innebär att förutsäga den bästa tidpunkten för att utföra underhåll på roboten. Detta minimerar både kostnaderna för underhåll samt förebygger mekaniska fel som kan leda till oplanerade produktionsstopp. Det finns redan metoder för att utföra prediktivt underhåll på industriella robotar, men dessa metoder kräver ytterligare sensorer. Denna forskning syftar till att förutsäga avvikelserna genom att endast använda data från de sensorer som redan används för att reglera roboten. En maskininlärningsmetod föreslås för implementering av prediktivt underhåll av industriella robotar, med hjälp av vridmomentprofiler som indata. Metoderna testas på simulerad data som skapats med hjälp av slitage- och temperaturmodeller. Vridmomenten används för att extrahera ett hälsoindex för varje axel, vilket i sin tur används för att upptäcka anomalier hos roboten. Hälsoindexet har en snabb exponentiell tillväxttrend som är svår att förutsäga i förväg. En Gaussisk processregressor, en Exponentron och hybridalgoritmer används för prediktion av tidsserien för hälsoindexet för att implementera det prediktiva underhållet. Förutsägelserna utvärderas baserat på träffsäkerheten av förutsägelsen för tidsserien samt precisionen för förutsagda avvikelser. De undersökta metoderna visar sig kunna förutsäga utvecklingen av slitage och upptäcka avvikelser i förväg. Resultaten uppvisar att hybridmetoden som erhålls genom att kombinera prediktioner från olika algoritmer överträffar de andra lösningarna. I analysen av prestandan visas att algoritmerna är känsliga för kvaliteten av datat och att de inte fungerar bra när datat har låg samplingsfrekvens eller då datapunkter saknas.