Dissertations / Theses on the topic 'Contrôleur robotique'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Contrôleur robotique.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Bonnet, Vincent. "Modélisation des coordinations posturales chez l'humain." Montpellier 2, 2009. http://www.theses.fr/2009MON20251.
Full textThe work of this thesis contributes to the modelization of human postural coordinations. First, we per- formed a biomechanical analysis of a human supra-postural task. This analysis has shown that human postural coordination modes are governed by mechanical constraints, such as those resulting from main- tening balance or minimizing energy. Based on this analysis, two closed-loop models, with different levels of description in actuator dynamics and sensory feedback, have been developed to capture the complex postural behaviors observed in a head tracking task. Comparison with experimental results on humans shows the relevance of this modeling, since our musculoskeletal models are able to exhibit reasonably well the behavioral invariants observed in human postures. Finally, a biomechanical model is presented to capture the specific invariant observed with stroke patients and compared with real data
Crossman, Tristan. "Téléopération d'un robot collaboratif par outil haptique." Mémoire, Université de Sherbrooke, 2016. http://hdl.handle.net/11143/9571.
Full textDillen, Arnau. "Interface neuronale directe pour applications réelles." Electronic Thesis or Diss., CY Cergy Paris Université, 2024. http://www.theses.fr/2024CYUN1295.
Full textSince the inception of digital computers, creating intuitive user interfaces has been crucial. Effective and efficient user interfaces ensure usability, significantly influenced by the deployment environment and target demographic. Diverse interaction modalities are essential for inclusive device usability.Brain-computer interfaces (BCIs) enable interaction with devices through neural signals, promising enhanced interaction for individuals with paralysis and improving their autonomy and quality of life. This research project develops a proof-of-concept software using off-the-shelf hardware to control a robotic arm with BCI. The BCI system decodes user intentions from EEG signals to execute commands, focusing on the optimal design of a BCI control system for practical human-robot collaboration.The research established the following key objectives: developing a real-time motor imagery (MI) decoding strategy with fast decoding, minimal computational cost, and low calibration time; designing a control system to address low MI decoding accuracy while enhancing user experience; and developing an evaluation procedure to quantify system performance and inform improvements.The literature review identified issues like the prevalence of offline decoding and lack of standardized evaluation procedures for BCIs, and highlighted the limitations of using deep learning for MI decoding. This prompted a focus on off-the-shelf machine learning methods for EEG decoding.Initial development benchmarked various EEG decoding pipelines for neuroprostheses control, finding that standard common spatial patterns and linear discriminant analysis were practical despite user customization yielding optimal results. Another investigation reduced the number of sensors for MI decoding, using a 64-channel EEG device and demonstrating that reliable MI decoding can be achieved with just eight well-placed sensors. This feasibility of using low-density EEG devices with fewer than 32 electrodes reduces costs.A comprehensive evaluation framework for BCI control systems was developed, ensuring iterative software improvements and participant training. An augmented reality (AR) control system design was also described, integrating visual feedback with real-world overlays via a shared control approach using eye tracking for object selection and computer vision for spatial awareness.A user study compared the developed BCI control system to an eye-tracking-only control system. While eye tracking outperformed the BCI system, the study confirmed the feasibility of the BCI design for real-world applications with potential enhancements.Key findings include:- Eight well-placed EEG sensors are sufficient for adequate decoding performance, with a non-significant decrease in accuracy from 0.67 to 0.65 when reducing from 64 sensors to 8.- A shared control design informed by real-world contexts simplifies BCI decoding, and AR integration enhances the user interface. Only 2 MI classes are needed to achieve a success rate of 0.83 on evaluation tasks.- Despite eye tracking outperforming current BCI systems, BCIs are feasible for real-world use, with significantly higher efficiency in task completion time for the eye-tracking system.- Consumer-grade EEG devices are viable for EEG acquisition in BCI control systems, with all participants using the commercial EEG device successfully completing evaluation tasks, indicating further cost reductions beyond sensor reduction.Future research should integrate advanced EEG decoding methods like deep learning, transfer learning, and continual learning. Gamifying the calibration procedure may yield better training data and make the control system more attractive to users. Closer hardware-software integration through embedded decoding and built-in sensors in AR headsets should lead to a consumer-ready BCI control system for diverse applications
Lezama, Morales Ruth. "Modélisation et programmation d’un robot anthropomorphe à 7 degrés de liberté actionné par muscles artificiels pneumatiques." Toulouse, INSA, 2008. http://eprint.insa-toulouse.fr/archive/00000218/.
Full textA service robot is a complex robotic system that accomplishes the tasks of service, interacts with its environment and guaranties an interaction sure and reliable with human beings. This thesis describes about an anthropomorphic robot arm of 7 degrees of freedom driven by pneumatic artificial muscles called McKibben. Robot actuation using pneumatic artificial muscles is suitable for service robot applications because they provide the robot with an articular flexibility, lightness and a natural compliance in close analogy with the human body. In general, the objective of this thesis is put in operation the anthropomorphic robot arm. More precisely, we examine the direct and inverse kinematic models of the robot. The implementation of these models is first analyzed by the development of a computerized graphic simulation tool. By applying the kinematic models, the execution of simple tasks in teleoperation mode such as, a trajectory tracking under soft contact and the manipulation of fragile objects is validated. However, the main contribution of this thesis is the automatic control of the pneumatic artificial muscle actuator. A PID, a feed-forward PID controller and a variable structure control system are studied. Corresponding experimental results show the effects of the gravity and the influence of the mechanical coupling between the articulations of the anthropomorphic robot arm. Finally, this work concludes with a discussion on the computer aspects of the platform as well as a consideration of the evolution of the robot control architecture
Forget, Florent. "Modélisation et contrôle d'actionneurs pour la robotique humanoïde." Thesis, Toulouse 3, 2018. http://www.theses.fr/2018TOU30342.
Full textHumanoid robotics actuation and control is complex as this field has specific needs. This involves the design of advanced mechatronic constructions. In this thesis, we focused on the humanoid robots actuation and paid particular attention to systems with good compliance capabilities. Compliance refers to the ability of the system to adapt to its environment by adopting a flexible behaviour. This feature is particularly sought after for human-robot interactions and to make contacts between the robot and its environment smoother. We studied two systems in detail : the first is a system based on Mckibben's artificial pneumatic muscles and the second is an electric cable driven actuator with flexibility. We have developed and implemented a control architecture for the control of both systems. The interest of this architecture lies in its generic nature and in its use within a model predictive control scheme. We then studied the thermal behaviour of an actuator in order to exploit the full potential of this system while ensuring its integrity. Finally, we have carried out developments to improve the joint torque control of the humanoid robot Talos
Godzik, Nicolas. "Approches évolutionnaires pour la robotique modulaire et anticipatoire." Paris 11, 2005. http://www.theses.fr/2005PA112200.
Full textIn this thesis, we propose some original approaches to autonomous robotics tha are somehow intermediate between Brooks'subsumption architecture and the pure black-box Evolutionary Robotics approach. Both those approaches badly scale up with the complexity of the task of the robot. The "symbolic controllers" approach uses some high level behaviors as output of the controller (e. G. Move forward, turn left,. . . ). The following step is that of the "supervisors", where the controller simply chooses between different possible behaviors from a library of behaviors that can themselves be the result of previous evolutions (e. G. Explore, go to the light,. . . ). This approach is then validate on a homing experiment with battery recharge. Finally, we studied the coupling between evolution and life-time learning for the robot. The "auto-teaching" architecture, proposed by Nolfi and Parisi, has been thoroughly tested, and some clear defects of its generalization properties have been shown. The AAA architecture (Action, Anticipation Adaptation) was designed to remedy those defects: it uses the errors made by the anticipatory part of the controller compared to its actual sensations to on-line modify the weights of the controller. Even though some long-term weaknesses still remain, this architecture showed some small adaptation capabilities, and some prmosing results were obtained after tuning some parameters of the model
Tran, Minh Tuan. "Approche neuro-robotique pour le contrôle des systèmes anthropomorphiques." Phd thesis, Université Paul Sabatier - Toulouse III, 2009. http://tel.archives-ouvertes.fr/tel-00446797.
Full textConstantin, Joseph. "Contrôle-Commande d'un bras robotique planaire par approches neuromimétiques." Amiens, 2001. http://www.theses.fr/2001AMIE0001.
Full textDubois, Michel. "MASL, langage de contrôle multi-agents robotiques." Phd thesis, Université de Bretagne Sud, 2008. http://tel.archives-ouvertes.fr/tel-00502455.
Full textBenon, Laurent. "Étude expérimentale du contrôle en force/position pour un manipulateur robotique." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape4/PQDD_0015/MQ57393.pdf.
Full textLavoie, Marc-André. "Développement et contrôle d'un bras robotique basé sur l'actionneur différentiel élastique." Mémoire, Université de Sherbrooke, 2009. http://savoirs.usherbrooke.ca/handle/11143/1494.
Full textZoppis, Bruno. "Outils pour l'intégration et le contrôle en vision et robotique mobile." Grenoble INPG, 1997. http://www.theses.fr/1997INPG0075.
Full textLasbouygues, Adrien. "Exploration robotique de l’environnement aquatique : les modèles au coeur du contrôle." Thesis, Montpellier, 2015. http://www.theses.fr/2015MONTS078/document.
Full textUnderwater robots can nowadays operate in complex environments in a broad scope of missions where the use of human divers is difficult for cost or safety reasons. However the complexity of aquatic environments requires to give the robotic vector an autonomy sufficient to perform its mission while preserving its integrity. This requires to design control laws according to application requirements. They are built on knowledge from several scientific fields, underlining the interdisciplinarity inherent to robotics. Once the control law designed, it must be implemented as a control Software working on a real-time Software architecture.Nonetheless the current conception of control laws, as "monolithic" blocks, makes difficult the adaptation of a control from an application to another and the integration of knowledge from various scientific fields which are often not fully understood by control engineers. It also penalizes the implementation of control on Software architectures, at least its modularity and evolution. To solve those problems we seek a proper separation of knowledge so that each knowledge item can be easily used, its role precisely defined and we want to reify the interactions between them. Moreover this will allow us a more efficient projection on the Software architecture. We thus propose a new formalism for control laws description as a modular composition of basic entities named Atoms used to encapsulate the knowledge items.We also aim at building a better synergy between control and software engineering based on shared concerns such as temporal constraints and stability. Hence we extend the definition of our Atoms with constraints carrying information related to their temporal behaviour. We propose as well a methodology relying on our formalism to guide the implementation of control on a real-time Middleware. We will focus on the ContrACT Middleware developed at LIRMM.Finally we illustrate our approach on several robotic functionalities that can be used during aquatic environments exploration and especially for wall avoidance during the exploration of a karst aquifer
Rosendo, Juan luis. "Techniques robustes pour le contrôle automatique des systèmes robotiques." Thesis, Brest, École nationale supérieure de techniques avancées Bretagne, 2019. http://www.theses.fr/2019ENTA0004.
Full textThis work seeks to mitigate the effects of constraints on mobile robotic systems. To this end, auxiliary control loops and robust tuning techniques are proposed. The former are proposed to mitigate the effects of constraints on the input and output of the systems through the modification of the motion parameter in path following applications.Then, PID controllers are considered as a structural constraint, given its wide use in robotics particularly at low control level. A robust tuning methodology considering this constraint is proposed which achieves good performancelevels even when facing disturbances. Finally, to deal with robustness in presence of robots nonlinearity constraints, an analysis and tuning tool for sliding mode controllers is proposed. The particularity of this tuning method, based on global optimization and interval techniques,is that it allows generating tuning maps of the parameter regions where the desired performance criterion is fulfilled. All the proposed strategies are put into practice, through real experimentation or invalidated simulators, over the AUV Ciscrea available at ENSTA Bretagne
Xu, Song. "Impact du délai de transmission des informations en téléchirurgie & formation en chirurgie robotique : travaux réalisés sur les simulateurs robotiques en réalité virtuelle." Thesis, Université de Lorraine, 2015. http://www.theses.fr/2015LORR0098/document.
Full textThe objectives of our work were, on the one hand, to determine the impact of data-transmission latency in robotic telesurgey, and on the other hand, to validate the role of robotic simulator in robotic surgery training. Two studies were realized in the part concerning latency. It was proved that surgical performance deteriorates exponentially as latency increases. It is preferable to perform telesurgey with a delay less than 200 ms. The delay higher than 800 ms is not suitable for telesurgery. On the other hand, surgeons had demonstrated the capacity to adapt to delay through training. In the second part, we developed a curriculum on a robotic simulator for a urologic surgical procedure. Another study was realized to determine the validity of a new robotic simulator (the XTT) as an evaluation tool of robotic surgical assistance skills
Guernut, Rémi. "Etude du lien perception-action en robotique mobile." Compiègne, 1996. http://www.theses.fr/1996COMP919S.
Full textFauteux, Philippe. "Conception d'un actionneur adapté à l'interaction physique dans un contexte de robotique." Mémoire, Université de Sherbrooke, 2009. http://savoirs.usherbrooke.ca/handle/11143/1529.
Full textBouillant, Sébastien. "Etude de méthodes de classification et de combinaison de classifieurs pour le contrôle qualité par vision artificielle : application au contrôle de filaments." Dijon, 2003. http://www.theses.fr/2003DIJOS067.
Full textInfantes, Guillaume. "Apprentissage de modèles de comportement pour le contrôle d'exécution et la planification robotique." Phd thesis, Université Paul Sabatier - Toulouse III, 2006. http://tel.archives-ouvertes.fr/tel-00129505.
Full textSalomé, Jean-Christophe. "Gestion des contraintes temporelles pour le contrôle d'exécution d'un plan d'actions en robotique." Toulouse, ENSAE, 1985. http://www.theses.fr/1985ESAE0017.
Full textBreton, Stéphane. "Une approche neuronale du contrôle robotique utilisant la vision binoculaire par reconstruction tridimensionnelle." Mulhouse, 1999. http://www.theses.fr/1999MULH0532.
Full textOuanezar, Sofiane. "Contrôle moteur par le cervelet et interface Cerveau-Machine pour commander un doigt robotique." Phd thesis, Télécom ParisTech, 2010. http://pastel.archives-ouvertes.fr/pastel-00577959.
Full textPoiré, Vincent. "Migration de lois de contrôle d'un environnement de simulation vers un cadre d'application robotique." Mémoire, École de technologie supérieure, 2006. http://espace.etsmtl.ca/525/1/POIR%C3%89_Vincent.pdf.
Full textLessard, Joël. "Caractérisation, modélisation et contrôle vibratoire d’une articulation rotoïde flexible, dédiée à un système robotique." Mémoire, École de technologie supérieure, 2012. http://espace.etsmtl.ca/1019/1/LESSARD_Jo%C3%ABl.pdf.
Full textNadon, Félix. "Sélection de prise et contrôle d'une main robotique pour la manipulation d'objets non rigides." Thesis, Université d'Ottawa / University of Ottawa, 2019. http://hdl.handle.net/10393/39995.
Full textMeller, Alain. "Apsis : un système pour l'expression de connaissances décisionnelles en robotique." Paris 11, 1985. http://www.theses.fr/1985PA112153.
Full textMokhtari, Mohammed-Yacine. "Potentiel de la robotique pour l'inspection thermographique par chauffage inductif." Master's thesis, Université Laval, 2018. http://hdl.handle.net/20.500.11794/33042.
Full textEddy current thermography (ECT) is an active thermography method. The inductive excitation generates Eddy currents in electrically-conductive specimen. In a presence of defects, the eddy current flow is affected by these discontinuities leading to changes in the temperature distribution in the specimen around the defects. These changes are observed by an infrared camera. In this work, we present a robotic application of the method. A robotic interface is developed and all the sensors needed are integrated to the platform. Simulations are performed using COMSOL Multiphysics by varying different parameters. Experiments are realised on different specimens (made of different materials) with defects of different sizes. The linescan Eddy current thermography is studied and other modes are explored. The resulting images are reconstructed with a dedicated algorithm. Finally, the method’s results are compared to optical thermography to show the capability of the method.
Fontaine, Jean-Guy. "Commande directe assistée : principe et application au contrôle d'actionneurs électriques et pneumatiques pour la robotique." Paris 11, 1987. http://www.theses.fr/1987PA112101.
Full textDubois, Michel. "MASL, Langage de controle multi-agents robotiques." Lorient, 2008. http://www.theses.fr/2008LORIS133.
Full textThe classical approach for Multi-Agent System (MAS) Control, especially autonomous and robotic ones, deals first from a microscopic point of view: each agent embed a control program with communication/synchronization primitives that enable cooperation between agents. The emergence of a global behaviour from a macroscopic point of view can only be observed afterwards. In this context, MASL offers a macroscopic and unified approach with heterogeneous and distributed calculations over deliberative, reactive or hybrid agents. In this high level language, regardless of the runtime, each concurrent agent locally decides its participation in a collective execution block named an e-block. Each e-block is an anonymous collective program that runs over an agent network following local conditions. The orchestral mode (scalar, asynchronous, synchronous) is statically fixed by a shared block attribute. The communication use shared memory, events, synchronous messages passing, and asynchronous messages passing. Heterogeneous agents are managed with heritage and polymorphism. Permeability mechanism, dealing with agent autonomy, allows an agent to dynamically filter calls to its interface in respects to the sender position in the e-block hierarchy. In dynamic task allocation of agents, auto failover and recovery, agent replacement in a robot fleet (case of agent failure, loss of a mandatory functionality for the mission) an e-block is an entry point of a collaborative work. In the case of synchronous e-block, the programming paradigm is the data parallel model with iterative task for waves of agents. Finally, MASL offers advances in the field of MAS (dynamic belonging to groups, accuracy of the pace of actions to undertake to enable a desired cooperation) and for the management of errors
Coulot, Claudine. "Etude de l'éclairage de surfaces métalliques pour la vision artificielle : application au contrôle dimensionnel." Dijon, 1997. http://www.theses.fr/1997DIJOS026.
Full textNetter, Thomas. "De la vision naturelle à la vision artificielle : application du contrôle visuo-moteur de la mouche au pilotage d'un robot réactif volant." Nice, 2000. http://www.theses.fr/2000NICE5484.
Full textPrevious research on the visuo-motor system of the fly within the Neurocybernetics Group of the Laboratory of Neurobiolgy, CNRS, Marseilles, France, has led to the development of two mobile robots which feature an analogue electronic vision system based on Elementary Motion Detectors (EMD) derived from thoseof the fly. A tethered Unmanned Air Vehicle (UAV), called Fania, was developed to study Nap-ofthe-Eart (NOE)flight (terrain following) and obstacle avoidance using a motion sensing visual system. After an aerodynamic study, Fania was custom-built as a miniature (35 cm, 0. 840kg), electrically-powered, thrust-vectoring rotorcraft. It is constrained by a whirling-arm to 3 degrees of freedom with pitch and thrust control. The robotic aircraft's 20-photoreceptor onboard eye senses moving contrasts with 19 ground-based neuromorphic EMDs
Rolland, de Rengervé Antoine. "Apprentissage Interactif en Robotique Autonome : vers de nouveaux types d'IHM." Phd thesis, Université de Cergy Pontoise, 2013. http://tel.archives-ouvertes.fr/tel-00969519.
Full textOccello, Michel. "Blackboards distribués et parallèles : application au contrôle de systèmes dynamiques en robotique et en informatique musicale." Nice, 1993. http://www.theses.fr/1993NICE4627.
Full textThis thesis deals with the design of software tools for « intelligent » process control, i. E. Real time intelligent software. These tools need decision making and operator assistance capabilities. They involve many types of cooperating knowledge. In Distributed Artificial Intelligence, the blackboard concept can be viewed as a orgnisational framework for multi agent systems. The adaptation of the blackboard concept to the design of control tools is studied in order to show advantages and limits and to build a model according to the constraints of the domain. A synthesis of the studies on blackboard in existing control systems and on the use of parallelism in this system shows that the problem is the specification of an architecture able to meet real time constraints. Then, an original model of real time parallel blackboard is presented. A representation of the concept in this framework using mathematical sets is chosen. The specification of agents and shared data is sufficient to describe the system. A generic control unit is proposed. The components of the model are described using Petri nets. A development tool based on this model is presented. Finally, this thesis proposes a decomposition of the problem of process control based on specialized blackboards. Three applications valid the model and the decomposition. They deal with computer music robotics and teleoperation
Ady, Ragou. "Mobilité assistée à l'aide d'une canne robotisée." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066410/document.
Full textMobility assistance is major challenge since its importance in people autonomy enhancement.In this thesis, we focus on one of the most used assisting device which is the cane.Firstly, we have analyzed the supply provided by conventional canes during impaired gaits.This analyse is based on cane-assisted gait experimental characterizations and simulation.We have highlighted the weight-bearing, braking and propulsion assistance allowed by the additional contact point represented by the cane.Then, the development of a robotized cane is introduced. Unlike existing robotized canes, our prototype does not remain on a stable mobile platform.In order to reduce its volume and keep the shape of a conventional cane, the cane is composed of a telescopic shaft and a wheel at its tip, both motorized.The control of this cane is described. It allows to synchronize the cane motion with its user’s gait. The active cane follows the weakest leg during its swinging phase and offers a stable contact point during the stance phase
Rolland, de Rengerve Antoine. "Apprentissage Interactif en Robotique Autonome : vers de nouveaux types d'IHM." Thesis, Cergy-Pontoise, 2013. http://www.theses.fr/2013CERG0664/document.
Full textAn autonomous robot collaborating with humans should be able to learn how to navigate and manipulate objects in the same task. In a classical approach, independent functional modules are considered to manage the different aspects of the task (navigation, arm control,...) . To the contrary, the goal of this thesis is to show that learning tasks of different kinds can be tackled by learning sensorimotor attractors from a few task nonspecific structures. We thus proposed an architecture which can learn and encode attractors to perform navigation tasks as well as arm control.We started by considering a model inspired from place-cells for navigation of autonomous robots. On-line and interactive learning of place-action couples can let attraction basins emerge, allowing an autonomous robot to follow a trajectory. The robot behavior can be corrected and guided by interacting with it. The successive corrections and their sensorimotor coding enables to define the attraction basin of the trajectory. My first contribution was to adapt this principle of sensorimotor attractor building for the impedance control of a robot arm. While a proprioceptive posture is maintained, the arm movements can be corrected by modifying on-line the motor command expressed as muscular activations. The resulting motor attractors are simple associations between the proprioceptive information of the arm and these motor commands. I then showed that the robot could learn visuomotor attractors by combining the proprioceptive and visual information with the motor attractors. The visuomotor control corresponds to a homeostatic system trying to maintain an equilibrium between the two kinds of information. In the case of ambiguous visual information, the robot may perceive an external stimulus (e.g. a human hand) as its own hand. According to the principle of homeostasis, the robot will act to reduce the incoherence between this external information and its proprioceptive information. It then displays a behavior of immediately observed gestures imitation. This mechanism of homeostasis, completed by a memory of the observed sequences and action inhibition capability during the observation phase, enables a robot to perform deferred imitation and learn by observation. In the case of more complex tasks, we also showed that learning transitions can be the basis for learning sequences of gestures, like in the case of cognitive map learning in navigation. The use of motivational contexts then enables to choose between different learned sequences.We then addressed the issue of integrating in the same architecture behaviors involving visuomotor navigation and robotic arm control to grab objects. The difficulty is to be able to synchronize the different actions so the robot act coherently. Erroneous behaviors of the robot are detected by evaluating the actions predicted by the model with respect to corrections forced by the human teacher. These situations can be learned as multimodal contexts modulating the action selection process in order to adapt the behavior so the robot reproduces the desired task.Finally, we will present the perspectives of this work in terms of sensorimotor control, for both navigation and robotic arm control, and its link to human robot interface issues. We will also insist on the fact that different kinds of imitation behavior can result from the emergent properties of a sensorimotor control architecture
Hungr, Nikolai. "Conception et évaluation de systèmes robotiques de ponction d'aguilles percutanées sous contrôle d'imagerie médicale." Phd thesis, Université de Grenoble, 2014. http://tel.archives-ouvertes.fr/tel-00997017.
Full textDromnelle, Rémi. "Architecture cognitive générique pour la coordination de stratégies d'apprentissage en robotique." Electronic Thesis or Diss., Sorbonne université, 2021. http://www.theses.fr/2021SORUS039.
Full textThe main objective of this thesis is to propose a new method for online adaptation of robotic learning, allowing robots to dynamically and autonomously adapt their behavior according to variations in their own performance. The developed method is sufficiently general and task-independent that a robot using it can perform different dynamic tasks of various nature without any algorithm or parameter adjustment by the programmer. The algorithms underlying this method consist of a meta-control system that allows the robot to call upon two decision-making experts following a different behavioral strategy. The model-based expert builds a model of the effects of long-term actions and uses this model to decide; this strategy is computationally expensive, but quickly converges to the solution. The model-free expert is inexpensive in terms of computational resources, but takes time to converge to the optimal solution. In this work, we have developed a new criterion for the coordination of these two experts allowing the robot to dynamically change its strategy over time. We show in this work that our behavior coordination method allows the robot to maintain an optimal performance in terms of performance and computation time. We also show that the method can cope with abrupt changes in the environment, changes in goals or changes in the behavior of the human partner in the case of interaction tasks
Mariusse, Brigitte. "Vision industrielle et contrôle qualité." Lyon, INSA, 1988. http://www.theses.fr/1988ISAL0060.
Full textJalaoui, Abdellah El. "Gestion contextuelle de tâches pour le contrôle d'un véhicule sous-marin autonome." Montpellier 2, 2007. http://www.theses.fr/2007MON20145.
Full textJumeline, Alexandre. "Utilisation de signaux électromyographiques pour le contrôle d'un bras robotique pour les usagers de fauteuils roulants motorisés." Mémoire, École de technologie supérieure, 2013. http://espace.etsmtl.ca/1228/1/JUMELINE_Alexandre.pdf.
Full textLaboissière, Rafael. "Préliminaires pour une robotique de la communication parlée : inversion et contrôle d'un modèle articulatoire du conduit vocal." Grenoble INPG, 1992. http://www.theses.fr/1992INPG0092.
Full textLindig, León Cecilia. "Classification multilabels à partir de signaux EEG d'imaginations motrices combinées : application au contrôle 3D d'un bras robotique." Thesis, Université de Lorraine, 2017. http://www.theses.fr/2017LORR0016/document.
Full textBrain-Computer Interfaces (BCIs) replace the natural nervous system outputs by artificial ones that do not require the use of peripheral nerves, allowing people with severe motor impairments to interact, only by using their brain activity, with different types of applications, such as spellers, neuroprostheses, wheelchairs, or among others robotics devices. A very popular technique to record signals for BCI implementation purposes consists of electroencephalography (EEG), since in contrast with other alternatives, it is noninvasive and inexpensive. In addition, due to the potentiality of Motor Imagery (MI, i.e., brain oscillations that are generated when subjects imagine themselves performing a movement without actually accomplishing it) to generate suitable patterns for scheming self-paced paradigms, such combination has become a common solution for BCI neuroprostheses design. However, even though important progress has been made in the last years, full 3D control is an unaccomplished objective. In order to explore new solutions for overcoming the existing limitations, we present a multiclass approach that considers the detection of combined motor imageries, (i.e., two or more body parts used at the same time). The proposed paradigm includes the use of the left hand, right hand, and both feet together, from which eight commands are provided to direct a robotic arm comprising fourteen different movements that afford a full 3D control. To this end, an innovative switching-mode scheme that allows managing different actions by using the same command was designed and implemented on the OpenViBE platform. Furthermore, for feature extraction a novel signal processing scheme has been developed based on the specific location of the activity sources that are related to the considered body parts. This insight allows grouping together within a single class those conditions for which the same limb is engaged, in a manner that the original multiclass task is transformed into an equivalent problem involving a series of binary classification models. Such approach allows using the Common Spatial Pattern (CSP) algorithm; which has been shown to be powerful at discriminating sensorimotor rhythms, but has the drawback of being suitable only to differentiate between two classes. Based on this perspective we also have contributed with a new strategy that combines together the CSP algorithm and Riemannian geometry. In which the CSP projected trials are mapped into the Riemannian manifold, from where more discriminative features can be obtained as the distances separating the input data from the considered class means. These strategies were applied on three new classification approaches that have been compared to classical multiclass methods by using the EEG signals from a group of naive healthy subjects, showing that the proposed alternatives not only outperform the existing schema, but also reduce the complexity of the classification task
Lindig, León Cecilia. "Classification multilabels à partir de signaux EEG d'imaginations motrices combinées : application au contrôle 3D d'un bras robotique." Electronic Thesis or Diss., Université de Lorraine, 2017. http://www.theses.fr/2017LORR0016.
Full textBrain-Computer Interfaces (BCIs) replace the natural nervous system outputs by artificial ones that do not require the use of peripheral nerves, allowing people with severe motor impairments to interact, only by using their brain activity, with different types of applications, such as spellers, neuroprostheses, wheelchairs, or among others robotics devices. A very popular technique to record signals for BCI implementation purposes consists of electroencephalography (EEG), since in contrast with other alternatives, it is noninvasive and inexpensive. In addition, due to the potentiality of Motor Imagery (MI, i.e., brain oscillations that are generated when subjects imagine themselves performing a movement without actually accomplishing it) to generate suitable patterns for scheming self-paced paradigms, such combination has become a common solution for BCI neuroprostheses design. However, even though important progress has been made in the last years, full 3D control is an unaccomplished objective. In order to explore new solutions for overcoming the existing limitations, we present a multiclass approach that considers the detection of combined motor imageries, (i.e., two or more body parts used at the same time). The proposed paradigm includes the use of the left hand, right hand, and both feet together, from which eight commands are provided to direct a robotic arm comprising fourteen different movements that afford a full 3D control. To this end, an innovative switching-mode scheme that allows managing different actions by using the same command was designed and implemented on the OpenViBE platform. Furthermore, for feature extraction a novel signal processing scheme has been developed based on the specific location of the activity sources that are related to the considered body parts. This insight allows grouping together within a single class those conditions for which the same limb is engaged, in a manner that the original multiclass task is transformed into an equivalent problem involving a series of binary classification models. Such approach allows using the Common Spatial Pattern (CSP) algorithm; which has been shown to be powerful at discriminating sensorimotor rhythms, but has the drawback of being suitable only to differentiate between two classes. Based on this perspective we also have contributed with a new strategy that combines together the CSP algorithm and Riemannian geometry. In which the CSP projected trials are mapped into the Riemannian manifold, from where more discriminative features can be obtained as the distances separating the input data from the considered class means. These strategies were applied on three new classification approaches that have been compared to classical multiclass methods by using the EEG signals from a group of naive healthy subjects, showing that the proposed alternatives not only outperform the existing schema, but also reduce the complexity of the classification task
Laflaquière, Alban. "Approche sensorimotrice de la perception de l'espace pour la robotique autonome." Phd thesis, Université Pierre et Marie Curie - Paris VI, 2013. http://tel.archives-ouvertes.fr/tel-00865091.
Full textPrelle, Christine. "Contribution au contrôle de la compliance d'un bras de robot à actionnement électropneumatique." Lyon, INSA, 1997. http://theses.insa-lyon.fr/publication/1997ISAL0127/these.pdf.
Full textCompliance is a characteristic required in Robotics for many contact tasks. Several ways are possible to confer a compliant behaviour on the robot ; a bibliographical study takes stock of these different solutions. Among all these, we have chosen the one consisting in using the actuator compliance ; we propose to use electropneumatic actuators composed of metal bellows having the advantage of an inherent compliance due to bellows flexibility and air compressibility. Two actuators designs, respectively with one and two bellows, are compared in order to make appear advantages and drawbacks. We show that it is possible to control axis compliance, either with a classical state feedback, or with an explicit force feedback, without force sensor. In the two cases, a good stability is remained. However, explicit force feedback control presents advantages comparing to classical control : it allows to modify actuator compliance linearly acting on a single parameter, without influence on the static state ; it allows a greater tuning range too and to obtain a compliance more important than the bellows compliance. A lot of tests verify the models and the theoretical approach. To validate our global approach, experiments have been done on a one-arm prototype, driven by this kind of actuator, and standing for a third of a parallel DELTA robot. These tests show that, in accordance with the theoretical approach, the arm compliance is adjustable modifying the actuator compliance with
Ammounah, Anas. "Architecture de contrôle pour un robot humanoïde à actionnement hydraulique." Electronic Thesis or Diss., université Paris-Saclay, 2021. http://www.theses.fr/2021UPASG056.
Full textHYDROïD is the first humanoid robot with hydraulic control in Europe. This research platform was created to emulate the human body. The emulation of the human body is important because the objective of the humanoid robot in the future is to cooperate and interact with humans, and even to replace them in dangerous scenarios. This interaction requires safety aspects. Emulation and having an anthropomorphic robot like the human body simplifies the achievement of this goal. Many aspects of emulation have already been realized, the actuation of the robot emulates human muscles, the hybrid mechanisms emulate human kinematics and agonist-antagonist effect, the mechanical design of the robot emulates the thin morphology and mass distribution of the human body, and the hydraulic flow emulates the blood flow inside the body.In this thesis, we have sought to emulate the architecture of the human nervous system, i.e., the physical structure, transmission, and processing of information. We proposed a layered control architecture for HYDROïD. A distributed architecture with 12 local controllers has been designed to be placed on the body of the robot to control 36 hydraulically operated kinematic joints. A central PC with a real-time operating system manages the whole-body motion through real-time middleware and EtherCAT communication. Each local controller is a complete integrated computing unit to control the robot at the joint level. A custom driver was built to control the hydraulic actuation. We investigated two approaches at this level, using a single-loop approach and a multi-threading approach
Abi-Farraj, Firas. "Contributions aux architectures de contrôle partagé pour la télémanipulation avancée." Thesis, Rennes 1, 2018. http://www.theses.fr/2018REN1S120/document.
Full textWhile full autonomy in unknown environments is still in far reach, shared-control architectures where the human and an autonomous controller work together to achieve a common objective may be a pragmatic "middle-ground". In this thesis, we have tackled the different issues of shared-control architectures for grasping and sorting applications. In particular, the work is framed in the H2020 RoMaNS project whose goal is to automatize the sort and segregation of nuclear waste by developing shared control architectures allowing a human operator to easily manipulate the objects of interest. The thesis proposes several shared-control architectures for dual-arm manipulation with different operator/autonomy balance depending on the task at hand. While most of the approaches provide an instantaneous interface, we also propose architectures which automatically account for the pre-grasp and post-grasp trajectories allowing the operator to focus only on the task at hand (ex., grasping). The thesis also proposes a shared control architecture for controlling a force-controlled humanoid robot in which the user is informed about the stability of the humanoid through haptic feedback. A new balancing algorithm allowing for the optimal control of the humanoid under high interaction forces is also proposed
Aumont, Arnaud. "Contrôle d'impédance de bras interactifs à actionneurs différentiels élastiques." Mémoire, Université de Sherbrooke, 2014. http://hdl.handle.net/11143/5427.
Full textLapointe, Claude. "Développement, simulation et expérimentation d'un contrôle de force/position en robotique par l'approche parallèle dans un environnement incertain." Mémoire, École de technologie supérieure, 2004.
Find full textGavrilovich, Irina. "Développement d'un système robotique pour des essais au sol du système de contrôle d'attitude et d'orbite d'un CubeSat." Thesis, Montpellier, 2016. http://www.theses.fr/2016MONTT329/document.
Full textAfter the launch of the first artificial Earth satellite in 1957, the evolution of various technologies has fostered the miniaturization of satellites. In 1999, the development of standardized modular satellites with masses limited to a few kilograms, called CubeSats, was initiated by a joint effort of California Polytechnic State University and Stanford University. Since then, CubeSats became a widespread and significant trend, due to a number of available off-the-shelf low cost components.In last years, the number of launched CubeSats constantly grows, but less than half of all CubeSat missions achieved their goals (either partly or completely). The analysis of these failures shows that the most evident cause is a lack of proper component-level and system-level CubeSat testing. An especially challenging task is Hardware-In-the-Loop (HIL) tests of the Attitude Determination and Control System (ADCS). A system devoted to these tests shall offer reliable simulations of the space environment and allow realistic CubeSat motions. The most relevant approach to provide a satellite with such test conditions consists in using air bearing platforms. However, the possible satellite motions are strictly constrained because of geometrical limitations, which are inherent in the air bearing platforms. Despite 15 years of CubeSat history, the list of the air bearing platforms suitable for CubeSat ADCS test is very limited.This thesis is devoted to the design and development of an air bearing testbed for CubeSat ADCS HIL testing. The main novelty of the proposed testbed design consists in using four air bearings instead of one and in utilizing a robotic arm, which allows potentially unconstrained CubeSat motions. Besides the testbed design principle, this thesis deals with the related issues of the determination of the CubeSat orientation by means of contactless measurements, and of the behavior of the air bearings, as well as with the need of a mass balancing method.In order to verify the feasibility of the proposed design, a prototype of the testbed is developed and tested. Several modifications aimed at simplifying the structure and at shortening the fabrication timeline have been made. For this reason, the Adept Viper s650 robot is involved in place of a custom-designed 4DoF robotic arm. A control strategy is proposed in order to provide the robot with a proper motion to follow the CubeSat orientation. Finally, the obtained results are presented and the overall assessment of the proposed testbed is put into perspective