In der vorliegenden Arbeit werden rekurrente neuronale Netze im Hinblick auf ihre Eignung zur Bewegungssteuerung autonomer Roboter untersucht. Nacheinander werden Oszillatoren für Vierbeiner, homöostatische Ringmodule für segmentierte Roboter und monostabile Neuromodule für Roboter mit vielen Freiheitsgraden und komplexen Bewegungsabläufen besprochen. Neben dem mathematisch-theoretischen Hintergrund der Neuromodule steht in gleichberechtigter Weise deren praktische Implementierung auf realen Robotersystemen. Hierzu wird die funktionale Einbettung ins Gesamtsystem ebenso betrachtet, wie die konkreten Aspekte der zugrundeliegenden Hardware: Rechengenauigkeit, zeitliche Auflösung, Einfluss verwendeter Materialien und dergleichen mehr. Interessante elektronische Schaltungsprinzipien werden detailliert besprochen. Insgesamt enthält die vorliegende Arbeit alle notwendigen theoretischen und praktischen Informationen, um individuelle Robotersysteme mit einer angemessenen Bewegungssteuerung zu versehen. Ein weiteres Anliegen der Arbeit ist es, aus der Richtung der klassischen Ingenieurswissenschaften kommend, einen neuen Zugang zur Theorie rekurrenter neuronaler Netze zu schaffen. Gezielte Vergleiche der Neuromodule mit analogen elektronischen Schaltungen, physikalischen Modellen und Algorithmen aus der digitalen Signalverarbeitung können das Verständnis von Neurodynamiken erleichtern. / How recurrent neural networks can help to make autonomous robots move, will be investigated within this thesis. First, oscillators which are able to control four-legged robots will be dealt with, then homeostatic ring modules which control segmented robots, and finally monostable neural modules, which are able to drive complex motion sequences on robots with many degrees of freedom will be focused upon. The mathematical theory of neural modules will be addressed as well as their practical implementation on real robot platforms. This includes their embedding into a major framework and concrete aspects, like computational accuracy, timing and dependance on materials. Details on electronics will be given, so that individual robot systems can be built and equipped with an appropriate motion controller. It is another concern of this thesis, to shed a new light on the theory of recurrent neural networks, from the perspective of classical engineering science. Selective comparisons to analog electronic schematics, physical models, and digital signal processing algorithms can ease the understanding of neural dynamics.

L'objectif du travail proposé est de concevoir et commander un groupe des robots mobiles similaires et d'architecture simple appelés m-bots (mono-robots). Plusieurs m-bots ont la capacité de saisir ensemble un objet afin d'assurer sa co-manipulation et son transport quelle que soit sa forme et sa masse. Le robot résultant est appelé p-bot (poly-robot) et est capable d'effectuer des tâches de déménageur pour le transport d'objets génériques. La reconfigurabilité du p-bot par l'ajustement du nombre des m-bots utilisés permet de manipuler des objets lourds et des objets de formes quelconques (particulièrement s'ils sont plus larges qu'un seul m-bot). Sont considérés dans ce travail l'évitement d'obstacle ainsi que la stabilité du p-bot incluant la charge à transporter. Une cinématique pour un mécanisme de manipulation a été proposée et étudiée. Ce dernier assure le levage de la charge et son dépôt sur le corps des robots pour la transporter. Plusieurs variantes d'actionnement ont été étudiées : passif, avec compliance et actionné. Un algorithme de positionnement optimal des m-bots autour de l'objet à manipuler a été proposé afin d'assurer la réussite de la tâche à effectuer par les robots. Cet algorithme respecte le critère de "Force Closure Grasping" qui assure la stabilité de la charge durant la phase de manipulation. Il maintient aussi une marge de stabilité statique qui assure la stabilité de l'objet durant la phase de transport. Enfin, l'algorithme respecte le critère des zones inaccessibles qui ne peuvent pas être atteintes par les m-bots. Une loi de commande a été utilisée afin d'atteindre les positions désirées pour les m-bots et d'assurer la navigation en formation, durant la phase du transport, durant laquelle chaque robot élémentaire doit maintenir une position désirée par rapport à l'objet transporté. Des résultats de simulation pour un objet de forme quelconque, décrite par une courbe paramétrique, sont présentés. Des simulations 3D en dynamique multi-corps ainsi que des expériences menées sur les prototypes réalisés ont permis de valider nos propositions. / Our goal in the proposed work is to design and control a group of similar mobile robots with a simple architecture, called m-bot. Several m-bots can grip a payload, in order to co-manipulate and transport it, whatever its shape and mass. The resulting robot is called a p-bot andis capable to solve the so-called "removal-man task" to transport a payload. Reconfiguring the p-bot by adjusting the number of m-bots allows to manipulate heavy objects and to manage objects with anyshape, particularly if they are larger than a single m-bot. Obstacle avoidance is addressed and mechanical stability of the p-bot and its payload is permanently guaranteed. A proposed kinematic architecture for a manipulation mechanism is studied. This mechanism allows to lift a payload and put it on them-bot body in order to be transported. The mobile platform has a free steering motion allowing the system maneuver in any direction. An optimal positioning of the m-bots around the payload ensures a successful task achievement without loss of stability for the overall system. The positioning algorithm respects the Force Closure Grasping (FCG) criterion which ensures the payload stability during the manipulation phase. It respects also the Static Stability Margin (SSM) criterion which guarantees the payload stability during the transport. Finally, it considers also the Restricted Areas (RA) that could not be reached by the robots to grab the payload. A predefined control law is then used to ensure the Target Reaching (TR) phase of each m-bot to its desired position around the payload and to track a Virtual Structure (VS), during the transportation phase, in which each elementary robot has to keep the desired position relative to the payload. Simulation results for an object of any shape, described by aparametric curve, are presented. Additional 3D simulation results with a multi-body dynamic software and experiments by manufactured prototypes validate our proposal.

Este trabajo analiza la idoneidad de dos de los principales métodos de asignación de tareas en entornos con restricciones temporales. Se pondrá de manifiesto que ambos tipos de mecanismos presentan carencias para tratar tareas con deadlines, especialmente cuando los robots han de formar coaliciones. Uno de los aspectos a los que esta tesis dedica mayor atención es la predicción del tiempo de ejecución, que depende, entre otros factores, de la interferencia física entre robots. Este fenómeno no se ha tenido en cuenta en los mecanismos actuales de asignación basados en subastas. Así, esta tesis presenta el primer mecanismo de subastas para la creación de coaliciones que tiene en cuenta la interferencia entre robots. Para ello, se ha desarrollado un modelo de predicción del tiempo de ejecución y un nuevo paradigma llamado subasta doble. Además, se han propuesto nuevos mecanismos basados en swarm

This thesis investigates the problem of robot navigation using only landmark bearings. The proposed system allows a robot to move to a ground target location specified by the sensor values observed at this ground target posi- tion. The control actions are computed based on the difference between the current landmark bearings and the target landmark bearings. No Cartesian coordinates with respect to the ground are computed by the control system. The robot navigates using solely information from the bearing sensor space. Most existing robot navigation systems require a ground frame (2D Cartesian coordinate system) in order to navigate from a ground point A to a ground point B. The commonly used sensors such as laser range scanner, sonar, infrared, and vision do not directly provide the 2D ground coordi- nates of the robot. The existing systems use the sensor measurements to localise the robot with respect to a map, a set of 2D coordinates of the objects of interest. It is more natural to navigate between the points in the sensor space corresponding to A and B without requiring the Cartesian map and the localisation process. Research on animals has revealed how insects are able to exploit very limited computational and memory resources to successfully navigate to a desired destination without computing Cartesian positions. For example, a honeybee balances the left and right optical flows to navigate in a nar- row corridor. Unlike many other ants, Cataglyphis bicolor does not secrete pheromone trails in order to find its way home but instead uses the sun as a compass to keep track of its home direction vector. The home vector can be inaccurate, so the ant also uses landmark recognition. More precisely, it takes snapshots and compass headings of some landmarks. To return home, the ant tries to line up the landmarks exactly as they were before it started wandering. This thesis introduces a navigation method based on reflex actions in sensor space. The sensor vector is made of the bearings of some landmarks, and the reflex action is a gradient descent with respect to the distance in sensor space between the current sensor vector and the target sensor vec- tor. Our theoretical analysis shows that except for some fully characterized pathological cases, any point is reachable from any other point by reflex action in the bearing sensor space provided the environment contains three landmarks and is free of obstacles. The trajectories of a robot using reflex navigation, like other image- based visual control strategies, do not correspond necessarily to the shortest paths on the ground, because the sensor error is minimized, not the moving distance on the ground. However, we show that the use of a sequence of waypoints in sensor space can address this problem. In order to identify relevant waypoints, we train a Self Organising Map (SOM) from a set of observations uniformly distributed with respect to the ground. This SOM provides a sense of location to the robot, and allows a form of path planning in sensor space. The navigation proposed system is analysed theoretically, and evaluated both in simulation and with experiments on a real robot.

La thématique étudiée dans ce mémoire est axée sur la préservation de la stabilité dynamique de véhicules évoluant en environnement naturel. En effet, la mobilité en milieu tout-terrain est une activité particulièrement pénible et dangereuse en raison de la nature difficile de l'environnement de conduite et de la reconfigurabilité des machines. Le caractère changeant et incertain des interactions rencontrées entre des véhicules à dynamique complexe et variable et leur environnement entraîne régulièrement des risques accrus de renversement et/ou de perte de contrôle (dévalement, dérapage déclenché par une perte soudaine d'adhérence) pour le conducteur. Une forte accidentalité mortelle est, en effet, recensée dans ce secteur, en particulier, dans le milieu agricole ou le renversement de véhicule est classé comme étant la première cause de mortalité au travail. A l'heure actuelle, les approches existantes sur la stabilité d'engins agricoles sont qualifiées à juste titre de passives car elles ne permettent pas d'éviter que les accidents ne se produisent. Par ailleurs, la transposition directe des solutions de sécurité active du secteur de l'automobile (ABS, ESP) s'est révélée inadaptée aux véhicules tout-terrain a cause des hypothèses simplificatrices (routes plates et homogènes, conditions d'adhérence constantes, etc.) dont souffre la conception de ces dispositifs. Ainsi, le développement de systèmes actifs de sécurité prenant en compte les spécificités de la conduite en milieu tout-terrain se révèle être la meilleure voie d'amélioration à suivre. Eu égard à ces circonstances, ce projet se propose d'adresser cette problématique en étudiant des métriques de stabilité pertinentes permettant d'estimer et d'anticiper en temps réel les risques afin de permettre des actions correctives pour la préservation de l'intégrité des machines tout-terrain. Afin de faciliter l'industrialisation du dispositif actif de sécurité conçu, l'une des contraintes sociétales et commerciales de ce projet a été l'utilisation de capteurs compatibles avec le coût des machines visées. L'objectif ambitieux de cette étude a été atteint par différentes voies. En premier lieu, une approche de modélisation multi-échelle a permis de caractériser l'évolution dynamique de véhicules en milieu tout-terrain. Cette approche à dynamique partielle a offert l'avantage de développer des modèles suffisamment précis pour être représentatifs du comportement réel de l'engin mais tout en présentant une structure relativement simple permettant la synthèse d'asservissements performants. Puis, une étude comparative des avantages et des inconvénients des trois grandes familles de métriques répertoriées dans la littérature a permis de mettre en exergue l'intérêt des métriques analytiques à modèle dynamique par rapport aux catégories de critères de stabilité dits statiques et empiriques. Enfin, l'analyse approfondie des métriques dynamiques a facilité le choix de trois indicateurs (Lateral and Longitudinal Load Transfer (LLT), Force Angle Stability Measurement (FASM) et Dynamic Energy Stability Measurement (DESM)) qui sont représentatifs d'un risque imminent de renversement du véhicule. La suite du mémoire s'appuie sur la théorie d'observation pour l'estimation en ligne des variables non directement mesurables en milieu tout-terrain telles que les rigidités de glissement et dérive du pneumatique. Jumelée aux différents modèles dynamiques du véhicule, la synthèse d'observateurs a permis donc d'estimer en temps réel les efforts d'interaction pneumatiques-sol nécessaires à l'évaluation des indicateurs d'instabilité. Le couplage de ces modèles multi-échelles à la théorie d'observation a ainsi constitué un positionnement original à même de briser la complexité de la caractérisation de la stabilité de véhicules à dynamiques complexes et incertaines. (...) / This work is focused on the thematic of the maintenance of the dynamic stability of off-road vehicles. Indeed, driving vehicles in off-road environment remains a dangerous and harsh activity because of the variable and bad grip conditions associated to a large diversity of terrains. Driving difficulties may be also encountered when considering huge machines with possible reconfiguration of their mechanical properties (changes in mass and centre of gravity height for instance). As a consequence, for the sole agriculture sector, several fatal injuries are reported per year in particular due to rollover situations. Passive protections (ROllover Protective Structure - ROPS) are installed on tractors to reduce accident consequences. However, protection capabilities of these structures are very limited and the latter cannot be embedded on bigger machines due to mechanical design limitations. Furthermore, driving assistance systems (such as ESP or ABS) have been deeply studied for on-road vehicles and successfully improve safety. These systems usually assume that the vehicle Center of Gravity (CG) height is low and that the vehicles are operating on smooth and level terrain. Since these assumptions are not satisfied when considering off-road vehicles with a high CG, such devices cannot be applied directly. Consequently, this work proposes to address this research problem by studying relevant stability metrics able to evaluate in real time the rollover risk in order to develop active safety devices dedicated to off-road vehicles. In order to keep a feasible industrialization of the conceived active safety device, the use of compatible sensors with the cost of the machines was one of the major commercial and societal requirements of the project. The ambitious goal of this study was achieved by different routes. First, a multi-scale modeling approach allowed to characterize the dynamic evolution of off-road vehicles. This partial dynamic approach has offered the advantage of developing sufficiently accurate models to be representative of the actual behavior of the machine but having a relatively simple structure for high-performance control systems. Then, a comparative study of the advantages and drawbacks of the three main families of metrics found in the literature has helped to highlight the interest of dynamic stability metrics at the expense to categories of so-called static and empirical stability criteria. Finally, a thorough analysis of dynamic metrics has facilitated the choice of three indicators (Longitudinal and Lateral Load Transfer (LLT), Force Angle Stability Measurement (FASM) and Dynamic Energy Stability Measurement (DESM)) that are representative of an imminent rollover risk. The following of the document is based on the observation theory for estimating online of variables which are not directly measurable in off-road environment such as slip and cornering stiffnesses. Coupled to the dynamic models of the vehicle, the theory of observers has helped therefore to estimate in real time the tire-soil interaction forces which are necessaries for evaluating indicators of instability. The coupling of these multiscale models to the observation theory has formed an original positioning capable to break the complexity of the characterization of the stability of vehicles having complex and uncertain dynamics. (...)

[EN] Nowadays, there are many electronic products that incorporate elements and features coming from the research in the field of mobile robotics. For instance, the well-known vacuum cleaning robot Roomba by iRobot, which belongs to the field of service robotics, one of the most active within the sector. There are also numerous autonomous robotic systems in industrial warehouses and plants. It is the case of Autonomous Guided Vehicles (AGVs), which are able to drive completely autonomously in very structured environments. Apart from industry and consumer electronics, within the automotive field there are some devices that give intelligence to the vehicle, derived in most cases from advances in mobile robotics. In fact, more and more often vehicles incorporate Advanced Driver Assistance Systems (ADAS), such as navigation control with automatic speed regulation, lane change and overtaking assistant, automatic parking or collision warning, among other features. However, despite all the advances there are some problems that remain unresolved and can be improved. Collisions and rollovers stand out among the most common accidents of vehicles with manual or autonomous driving. In fact, it is almost impossible to guarantee driving without accidents in unstructured environments where vehicles share the space with other moving agents, such as other vehicles and pedestrians. That is why searching for techniques to improve safety in intelligent vehicles, either autonomous or manual-assisted driving, is still a trending topic within the robotics community. This thesis focuses on the design of tools and techniques for planning and control of intelligent vehicles in order to improve safety and comfort. The dissertation is divided into two parts, the first one on autonomous driving and the second one on manual-assisted driving. The main link between them is the use of clothoids as mathematical formulation for both trajectory generation and collision detection. Among the problems solved the following stand out: obstacle avoidance, rollover avoidance and advanced driver assistance to avoid collisions with pedestrians. / [ES] En la actualidad se comercializan infinidad de productos de electrónica de consumo que incorporan elementos y características procedentes de avances en el sector de la robótica móvil. Por ejemplo, el conocido robot aspirador Roomba de la empresa iRobot, el cual pertenece al campo de la robótica de servicio, uno de los más activos en el sector. También hay numerosos sistemas robóticos autónomos en almacenes y plantas industriales. Es el caso de los vehículos autoguiados (AGVs), capaces de conducir de forma totalmente autónoma en entornos muy estructurados. Además de en la industria y en electrónica de consumo, dentro del campo de la automoción también existen dispositivos que dotan de cierta inteligencia al vehículo, derivados la mayoría de las veces de avances en robótica móvil. De hecho, cada vez con mayor frecuencia los vehículos incorporan sistemas avanzados de asistencia al conductor (ADAS por sus siglas en inglés), tales como control de navegación con regulación automática de velocidad, asistente de cambio de carril y adelantamiento, aparcamiento automático o aviso de colisión, entre otras prestaciones. No obstante, pese a todos los avances siguen existiendo problemas sin resolver y que pueden mejorarse. La colisión y el vuelco destacan entre los accidentes más comunes en vehículos con conducción tanto manual como autónoma. De hecho, la dificultad de conducir en entornos desestructurados compartiendo el espacio con otros agentes móviles, tales como coches o personas, hace casi imposible garantizar la conducción sin accidentes. Es por ello que la búsqueda de técnicas para mejorar la seguridad en vehículos inteligentes, ya sean de conducción autónoma o manual asistida, es un tema que siempre está en auge en la comunidad robótica. La presente tesis se centra en el diseño de herramientas y técnicas de planificación y control de vehículos inteligentes, para la mejora de la seguridad y el confort. La disertación se ha dividido en dos partes, la primera sobre conducción autónoma y la segunda sobre conducción manual asistida. El principal nexo de unión es el uso de clotoides como elemento de generación de trayectorias y detección de colisiones. Entre los problemas que se resuelven destacan la evitación de obstáculos, la evitación de vuelcos y la asistencia avanzada al conductor para evitar colisiones con peatones. / [CAT] En l'actualitat es comercialitzen infinitat de productes d'electrònica de consum que incorporen elements i característiques procedents d'avanços en el sector de la robòtica mòbil. Per exemple, el conegut robot aspirador Roomba de l'empresa iRobot, el qual pertany al camp de la robòtica de servici, un dels més actius en el sector. També hi ha nombrosos sistemes robòtics autònoms en magatzems i plantes industrials. És el cas dels vehicles autoguiats (AGVs), els quals són capaços de conduir de forma totalment autònoma en entorns molt estructurats. A més de en la indústria i en l'electrònica de consum, dins el camp de l'automoció també existeixen dispositius que doten al vehicle de certa intel·ligència, la majoria de les vegades derivats d'avanços en robòtica mòbil. De fet, cada vegada amb més freqüència els vehicles incorporen sistemes avançats d'assistència al conductor (ADAS per les sigles en anglés), com ara control de navegació amb regulació automàtica de velocitat, assistent de canvi de carril i avançament, aparcament automàtic o avís de col·lisió, entre altres prestacions. No obstant això, malgrat tots els avanços segueixen existint problemes sense resoldre i que poden millorar-se. La col·lisió i la bolcada destaquen entre els accidents més comuns en vehicles amb conducció tant manual com autònoma. De fet, la dificultat de conduir en entorns desestructurats compartint l'espai amb altres agents mòbils, tals com cotxes o persones, fa quasi impossible garantitzar la conducció sense accidents. És per això que la recerca de tècniques per millorar la seguretat en vehicles intel·ligents, ja siguen de conducció autònoma o manual assistida, és un tema que sempre està en auge a la comunitat robòtica. La present tesi es centra en el disseny d'eines i tècniques de planificació i control de vehicles intel·ligents, per a la millora de la seguretat i el confort. La dissertació s'ha dividit en dues parts, la primera sobre conducció autònoma i la segona sobre conducció manual assistida. El principal nexe d'unió és l'ús de clotoides com a element de generació de trajectòries i detecció de col·lisions. Entre els problemes que es resolen destaquen l'evitació d'obstacles, l'evitació de bolcades i l'assistència avançada al conductor per evitar col·lisions amb vianants. / Girbés Juan, V. (2016). Clothoid-based Planning and Control in Intelligent Vehicles (Autonomous and Manual-Assisted Driving) [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/65072 / TESIS

<div>With more and more videos taken from dash cams on thousands of cars, retrieving these videos and searching for important information is a daunting task. The purpose of this work is to mine some key road and vehicle motion attributes in a large-scale driving video data set for traffic analysis, sensing algorithm development and autonomous driving test benchmarks. Current sensing and control of autonomous cars based on full-view identification makes it difficult to maintain a high-frequency with a fast-moving vehicle, since computation is increasingly used to cope with driving environment changes.</div><div><br></div><div>A big challenge in video data mining is how to deal with huge amounts of data. We use a compact representation called the road profile system to visualize the road environment in long 2D images. It reduces the data from each frame of image to one line, thereby compressing the video clip to the image. This data dimensionality reduction method has several advantages: First, the data size is greatly compressed. The data is compressed from a video to an image, and each frame in the video is compressed into a line. The data size is compressed hundreds of times. While the size and dimensionality of the data has been compressed greatly, the useful information in the driving video is still completely preserved, and motion information is even better represented more intuitively. Because of the data and dimensionality reduction, the identification algorithm computational efficiency is higher than the full-view identification method, and it makes the real-time identification on road is possible. Second, the data is easier to be visualized, because the data is reduced in dimensionality, and the three-dimensional video data is compressed into two-dimensional data, the reduction is more conducive to the visualization and mutual comparison of the data. Third, continuously changing attributes are easier to show and be captured. Due to the more convenient visualization of two-dimensional data, the position, color and size of the same object within a few frames will be easier to compare and capture. At the same time, in many cases, the trouble caused by tracking and matching can be eliminated. Based on the road profile system, there are three tasks in autonomous driving are achieved using the road profile images.</div><div><br></div><div>The first application is road edge detection under different weather and appearance for road following in autonomous driving to capture the road profile image and linearity profile image in the road profile system. This work uses naturalistic driving video data mining to study the appearance of roads, which covers large-scale road data and changes. This work excavated a large number of naturalistic driving video sets to sample the light-sensitive area for color feature distribution. The effective road contour image is extracted from the long-time driving video, thereby greatly reducing the amount of video data. Then, the weather and lighting type can be identified. For each weather and lighting condition obvious features are I identified at the edge of the road to distinguish the road edge. </div><div><br></div><div>The second application is detecting vehicle interactions in driving videos via motion profile images to capture the motion profile image in the road profile system. This work uses visual actions recorded in driving videos taken by a dashboard camera to identify this interaction. The motion profile images of the video are filtered at key locations, thereby reducing the complexity of object detection, depth sensing, target tracking and motion estimation. The purpose of this reduction is for decision making of vehicle actions such as lane changing, vehicle following, and cut-in handling.</div><div><br></div><div>The third application is motion planning based on vehicle interactions and driving video. Taking note of the fact that a car travels in a straight line, we simply identify a few sample lines in the view to constantly scan the road, vehicles, and environment, generating a portion of the entire video data. Without using redundant data processing, we performed semantic segmentation to streaming road profile images. We plan the vehicle's path/motion using the smallest data set possible that contains all necessary information for driving.</div><div><br></div><div>The results are obtained efficiently, and the accuracy is acceptable. The results can be used for driving video mining, traffic analysis, driver behavior understanding, etc.</div>

Mobile robots need to move in the real world for the majority of tasks. Their control is often intertwined with the tasks they have to solve. Unforeseen events must have an adequate and prompt reaction, in order to solve the corresponding task satisfactorily. A robust system must be able to respond to a variety of events with specific solutions and strategies to keep the system running. Robot navigation control systems are essential for this. In this thesis we present a robot navigation control system that fulfills these requirements: Move Base Flex. Furthermore, the map representation used to model the environment is essential for path planning. Depending on the representation of the map, path planners can solve problems like simple 2D indoor navigation, but also complex rough terrain outdoor navigation with multiple levels and varying slopes, if the corresponding representation can model them accurately. With Move Base Flex, we present a middle layer navigation framework for navigation control, that is map independent at its core. Based on this, we present the Mesh Navigation Stack to master path planning in complex outdoor environments using a developed mesh map to model surfaces in 3D. Finally, to solve path planning in complex outdoor environments, we have developed and integrated the Continuous Vector Field Planner with the aforementioned solutions and evaluated it on five challenging and complex outdoor datasets in simulation and in the real-world. Beyond that, the corresponding developed software packages are open source available and have been released to easily reproduce the provided scientific results.

An Automated Guided Vehicle (AGV) must follow protective regulations to avoidcrashing into people when autonomously driving in industries. These safety norms require AGVs to enable protective fields, which perform hard braking when objects enter aspecific area in front of the vehicle. Warning fields, or warning systems, are similar fieldsthat decrease the speed of the AGV before objects enter the protective fields to enable asteadier driving. Today at Toyota Material Handling Manufacturing Sweden (TMHMS),warning systems have been implemented but the systems are too sensitive to objects outside of the AGVs path.The purpose of this thesis is to develop a predictive warning system based on empiricaldata from previous driving scenarios. By storing previous positions, the warning systemcould estimate a trajectory based on simple statistics and deploy speed limiting decisionsif objects appear in the upcoming predicted path.The predictive warning system was compared to the current warning system and adeactivated warning system setup in driving performance and driving dynamics. Performance was measured by measuring time to finish an industry-like test track and dynamicswas subjectively rated from a group of experienced AGV developers from TMHMS. Results showed that a predictive warning system drove the test track faster and with betterdynamics than the current warning system and the no warning system setup.Key findings are that a predictive warning system based on empirical data performedbetter in most cases but has some extra requirements to function. Firstly, the method require the AGV to mostly drive on previously driven paths to produce good results. Secondly the warning system requires a somewhat powerful on board computer to handlethe computations. Finally, the warning system requires spatial awareness of pose for thevehicle, as well as structure and shape for deployed protective fields.

In recent years, mobile robots have gained tremendous attention from the entire society: the industry is aiming at selling more intelligent products while the academia is improving their performance from all perspectives. Real world examples include autnomous driving vehicles, multirotors, legged robots, etc. One of the challenging tasks commonly faced by all game players, and all robotics platforms, is to plan motion or locomotion of the robot, calculate an optimal trajectory according to certain criterion and control it accordingly. Difficulty of solving such task usually arises from high-dimensionality and complexity of the system dynamics, fast changing conditions imposed as constraints and necessity for real-time deployment. This work proposes a method over the aforementioned mission by solving an optimal control problem in a receding horizon fashion. Unlike the existing Sequential Linear Quadratic [1] algorithm which is a continuous-time variant of Differential Dynamic Programming [2], we tackle the problem in a discretized multiple shooting fashion. Sequential Quadratic Programming is employed as optimization technique to solve the constrained Nonlinear Programming iteratively. Moreover, we apply trust region method in the sub Quadratic Programming to handle potential indefiniteness of Hessian matrix as well as to improve robustness of the solver. Simulation and benchmark with previous method have been conducted on robotics platforms to show the effectiveness of our solution and superiority under certain circumstances. Experiments have demonstrated that our method is capable of generating trajectories under complicated scenarios where the Hessian matrix contains negative eigenvalues (e.g. obstacle avoidance). / De senaste åren har mobila robotar fått enorm uppmärksamhet från hela samhället: branschen siktar på att sälja mer intelligenta produkter samtidigt som akademin förbättrar sina prestationer ur alla perspektiv. Exempel på verkligheten inkluderar autonoma körande fordon, multirotorer, robotar med ben, etc. En av de utmanande uppgifterna som vanligtvis alla spelare och alla robotplattformar står inför är att planera robotens rörelse eller rörelse, beräkna en optimal bana enligt vissa kriterier och kontrollera det därefter. Svårigheter att lösa en sådan uppgift beror vanligtvis på hög dimensionalitet och komplexitet hos systemdynamiken, snabbt föränderliga villkor som åläggs som begränsningar och nödvändighet för realtidsdistribution. Detta arbete föreslår en metod över det tidigare nämnda uppdraget genom att lösa ett optimalt kontrollproblem på ett vikande horisont. Till skillnad från den befintliga Sequential Linear Quadratic [1] algoritmen som är en kontinuerlig tidsvariant av Differential Dynamic Programming [2], tar vi oss an problemet på ett diskretiserat multipelfotograferingssätt. Sekventiell kvadratisk programmering används som optimeringsteknik för att lösa den begränsade olinjära programmeringen iterativt. Dessutom tillämpar vi trust region-metoden i den sub-kvadratiska programmeringen för att hantera potentiell obestämdhet av hessisk matris samt för att förbättra lösarens robusthet. Simulering och benchmark med tidigare metod har utförts på robotplattformar för att visa effektiviteten hos vår lösning och överlägsenhet under vissa omständigheter. Experiment har visat att vår metod är kapabel att generera banor under komplicerade scenarier där den hessiska matrisen innehåller negativa egenvärden (t.ex. undvikande av hinder).