Добірка наукової літератури з теми "Robotic Manipulation of Deformable Objects (RMDO)"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Robotic Manipulation of Deformable Objects (RMDO)".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Статті в журналах з теми "Robotic Manipulation of Deformable Objects (RMDO)"
1
Hou, Yew Cheong, Khairul Salleh Mohamed Sahari, and Dickson Neoh Tze How. "A review on modeling of flexible deformable object for dexterous robotic manipulation." International Journal of Advanced Robotic Systems 16, no. 3 (May 1, 2019): 172988141984889. http://dx.doi.org/10.1177/1729881419848894.
Повний текст джерелаАнотація:
In this article, we present a review on the recent advancement in flexible deformable object modeling for dexterous manipulation in robotic system. Flexible deformable object is one of the most research topics in computer graphic, computer vision, and robotic literature. The deformable models are known as the construction of object with material parameters in virtual environment to describe the deformation behavior. Existing modeling techniques and different types of deformable model are described. Various approaches of deformable object modeling have been used in robotic recognition and manipulation in order to reduce the time and cost to obtain more accurate result. In robotic manipulation, object detection, classification, and recognition of deformable objects are always a challenging problem and required as a first step to imbue the robot to able handle these deformable objects. Furthermore, the dexterity of robot control is also another essential key in handling of deformable object which its manipulation strategies need to plan intelligently for each sequence process. We also discuss some deserving direction for further research based on most current contribution.
2
Wang, Liman, and Jihong Zhu. "Deformable Object Manipulation in Caregiving Scenarios: A Review." Machines 11, no. 11 (November 7, 2023): 1013. http://dx.doi.org/10.3390/machines11111013.
Повний текст джерелаАнотація:
This paper reviews the robotic manipulation of deformable objects in caregiving scenarios. Deformable objects like clothing, food, and medical supplies are ubiquitous in care tasks, yet pose modeling, control, and sensing challenges. This paper categorises caregiving deformable objects and analyses their distinct properties influencing manipulation. Key sections examine progress in simulation, perception, planning, control, and system designs for deformable object manipulation, along with end-to-end deep learning’s potential. Hybrid analytical data-driven modeling shows promise. While laboratory successes have been achieved, real-world caregiving applications lag behind. Enhancing safety, speed, generalisation, and human compatibility is crucial for adoption. The review synthesises critical technologies, capabilities, and limitations, while also pointing to open challenges in deformable object manipulation for robotic caregiving. It provides a comprehensive reference for researchers tackling this socially valuable domain. In conclusion, multi-disciplinary innovations combining analytical and data-driven methods are needed to advance real-world robot performance and safety in deformable object manipulation for patient care.
3
Chatzilygeroudis, Konstantinos, Bernardo Fichera, Ilaria Lauzana, Fanjun Bu, Kunpeng Yao, Farshad Khadivar, and Aude Billard. "Benchmark for Bimanual Robotic Manipulation of Semi-Deformable Objects." IEEE Robotics and Automation Letters 5, no. 2 (April 2020): 2443–50. http://dx.doi.org/10.1109/lra.2020.2972837.
Повний текст джерела
4
Verleysen, Andreas, Thomas Holvoet, Remko Proesmans, Cedric Den Haese, and Francis wyffels. "Simpler Learning of Robotic Manipulation of Clothing by Utilizing DIY Smart Textile Technology." Applied Sciences 10, no. 12 (June 13, 2020): 4088. http://dx.doi.org/10.3390/app10124088.
Повний текст джерелаАнотація:
Deformable objects such as ropes, wires, and clothing are omnipresent in society and industry but are little researched in robotics research. This is due to the infinite amount of possible state configurations caused by the deformations of the deformable object. Engineered approaches try to cope with this by implementing highly complex operations in order to estimate the state of the deformable object. This complexity can be circumvented by utilizing learning-based approaches, such as reinforcement learning, which can deal with the intrinsic high-dimensional state space of deformable objects. However, the reward function in reinforcement learning needs to measure the state configuration of the highly deformable object. Vision-based reward functions are difficult to implement, given the high dimensionality of the state and complex dynamic behavior. In this work, we propose the consideration of concepts beyond vision and incorporate other modalities which can be extracted from deformable objects. By integrating tactile sensor cells into a textile piece, proprioceptive capabilities are gained that are valuable as they provide a reward function to a reinforcement learning agent. We demonstrate on a low-cost dual robotic arm setup that a physical agent can learn on a single CPU core to fold a rectangular patch of textile in the real world based on a learned reward function from tactile information.
5
Zhu, Jihong, Benjamin Navarro, Robin Passama, Philippe Fraisse, Andre Crosnier, and Andrea Cherubini. "Robotic Manipulation Planning for Shaping Deformable Linear Objects WithEnvironmental Contacts." IEEE Robotics and Automation Letters 5, no. 1 (January 2020): 16–23. http://dx.doi.org/10.1109/lra.2019.2944304.
Повний текст джерела
6
Aspragathos, Nikos A. "Intelligent Robot Systems for Manipulation of Non-Rigid Objects." Solid State Phenomena 260 (July 2017): 20–29. http://dx.doi.org/10.4028/www.scientific.net/ssp.260.20.
Повний текст джерелаАнотація:
In this paper, methodologies are presented for the development of intelligent robot systems for the manipulation of linear and sheet like objects with low and/or very low bending rigidity. In the introduction the non-rigid objects are defined and classified considering their shape, bending rigidity and extensibility. The industrial and service applications of these systems are presented and the state of the art approaches for the manipulation of various categories of the non-rigid objects are presented. A brief State-of the-Art on the manipulation of the deformable objects with relatively low bending rigidity and presenting elastic behavior like foam, sheet metal is presented as well.The main part of the paper is devoted to the robotic manipulation of the sheet-like objects with very low rigidity such as fabrics and leather. Laboratory demonstrators accompany the presentation of the developed intelligent robotic systems for manipulation of non-rigid objects and the paper concludes with hints for the future directions of the research and development in robotic systems for handling non-rigid objects.
7
Zaidi, Lazher, Juan Antonio Corrales Ramon, Laurent Sabourin, Belhassen Chedli Bouzgarrou, and Youcef Mezouar. "Grasp Planning Pipeline for Robust Manipulation of 3D Deformable Objects with Industrial Robotic Hand + Arm Systems." Applied Sciences 10, no. 23 (December 6, 2020): 8736. http://dx.doi.org/10.3390/app10238736.
Повний текст джерелаАнотація:
In the grasping and manipulation of 3D deformable objects by robotic hands, the physical contact constraints between the fingers and the object have to be considered in order to validate the robustness of the task. Nevertheless, previous works rarely establish contact interaction models based on these constraints that enable the precise control of forces and deformations during the grasping process. This paper considers all steps of the grasping process of deformable objects in order to implement a complete grasp planning pipeline by computing the initial contact points (pregrasp strategy), and later, the contact forces and local deformations of the contact regions while the fingers close over the grasped object (grasp strategy). The deformable object behavior is modeled using a nonlinear isotropic mass-spring system, which is able to produce potential deformation. By combining both models (the contact interaction and the object deformation) in a simulation process, a new grasp planning method is proposed in order to guarantee the stability of the 3D grasped deformable object. Experimental grasping experiments of several 3D deformable objects with a Barrett hand (3-fingered) and a 6-DOF industrial robotic arm are executed. Not only will the final stable grasp configuration of the hand + object system be obtained, but an arm + hand approaching strategy (pregrasp) will also be computed.
8
Ruggiero, Fabio, Antoine Petit, Diana Serra, Aykut C. Satici, Jonathan Cacace, Alejandro Donaire, Fanny Ficuciello, et al. "Nonprehensile Manipulation of Deformable Objects: Achievements and Perspectives from the Robotic Dynamic Manipulation Project." IEEE Robotics & Automation Magazine 25, no. 3 (September 2018): 83–92. http://dx.doi.org/10.1109/mra.2017.2781306.
Повний текст джерела
9
Sanchez, Jose, Juan-Antonio Corrales, Belhassen-Chedli Bouzgarrou, and Youcef Mezouar. "Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey." International Journal of Robotics Research 37, no. 7 (June 2018): 688–716. http://dx.doi.org/10.1177/0278364918779698.
Повний текст джерелаАнотація:
We present a survey of recent work on robot manipulation and sensing of deformable objects, a field with relevant applications in diverse industries such as medicine (e.g. surgical assistance), food handling, manufacturing, and domestic chores (e.g. folding clothes). We classify the reviewed approaches into four categories based on the type of object they manipulate. Furthermore, within this object classification, we divide the approaches based on the particular task they perform on the deformable object. Finally, we conclude this survey with a discussion of the current state-of-the-art approaches and propose future directions within the proposed classification.
10
Almaghout, K., and A. Klimchik. "Vision-Based Robotic Comanipulation for Deforming Cables." Nelineinaya Dinamika 18, no. 5 (2022): 0. http://dx.doi.org/10.20537/nd221213.
Повний текст джерелаАнотація:
Although deformable linear objects (DLOs), such as cables, are widely used in the majority of life fields and activities, the robotic manipulation of these objects is considerably more complex compared to the rigid-body manipulation and still an open challenge. In this paper, we introduce a new framework using two robotic arms cooperatively manipulating a DLO from an initial shape to a desired one. Based on visual servoing and computer vision techniques, a perception approach is proposed to detect and sample the DLO as a set of virtual feature points. Then a manipulation planning approach is introduced to map between the motion of the manipulators end effectors and the DLO points by a Jacobian matrix. To avoid excessive stretching of the DLO, the planning approach generates a path for each DLO point forming profiles between the initial and desired shapes. It is guaranteed that all these intershape profiles are reachable and maintain the cable length constraint. The framework and the aforementioned approaches are validated in real-life experiments.
Дисертації з теми "Robotic Manipulation of Deformable Objects (RMDO)"
1
Roca, Filella Nicolas. "Contributions à la robotisation de tâches entrant dans la fabrication de pneumatiques." Electronic Thesis or Diss., Université Clermont Auvergne (2021-...), 2023. http://www.theses.fr/2023UCFA0011.
Повний текст джерелаАнотація:
La recherche en robotique connait un intérêt croissant pour la manipulation des objets mous : des tissus, des mousses ou tout autre objet déformable comme le caoutchouc. La déformation d’un tel objet est généralement modélisée par l’introduction de nouveaux degrés de liberté, ce qui rend plus complexe son contrôle. Dans le contexte de l’industrie du futur, la Manufacture Française des Pneumatiques Michelin souhaite moderniser son procédé de fabrication de pneumatiques qui consiste à assembler, couche par couche, des bandes et des nappes de gomme. Ces tâches, qui n’ont jamais été robotisées avant cette thèse, entrent dans le domaine de la manipulation robotique d’objets déformables (MROD).Issue d’une convention CIFRE (Convention Industrielle de Formation par la Recherche) de l’ANRT (Association Nationale de la Recherche et de la Technologie), cette thèse s’intéresse à cette problématique dans un contexte applicatif industriel à travers la conception d’une cellule robotique en apportant des solutions technologiques innovantes, notamment en termes d’actionnement, de perception et d’architecture de commande. Cependant, nous montrons que l’intégration de ces solutions est limitée par des problématiques classiques de la MROD, telles que la modélisation des déformations de l’objet, la perception multimodale ou encore la commande et la génération dynamique de tâches.Une première contribution apportée est l’adaptation d’algorithmes de traitement d’image issus de bibliothèques libres dans un contexte industrielle. Ces algorithmes remplacent des solutions industrielles du commerce et permettent une plus grande liberté de paramétrage pour chaque fonction. Le résultat est donc un assemblage de briques algorithmiques flexibles et adaptées aux spécificités du procédé de fabrication de pneumatiques.Cette thèse explore également l’utilisation d’un modèle physique réduit pour contrôler la tension dans une bande de gomme en suspension dont une extrémité est enroulée autour d’une bobine et l’autre extrémité est manipulée par un robot. Nous distinguons alors trois contributions : l’estimation par vision de la tension, une loi de commande en boucle fermée pour réguler la vitesse de rotation de la bobine et ainsi varier la longueur de la partie suspendue de la bande, et un algorithme de planification de la tension désirée.Une dernière contribution concerne une commande par retour visuelle permettant de joindre bout à bout les deux extrémités d’une nappe enroulée autour d’une surface cylindrique. Cette opération complexe se base sur la perception par vision et la reconstruction en 3D du bord de nappe ainsi qu’une loi de commande prenant en compte une mesure pondérée de l’erreur.Nos développements ont permis la conception et la réalisation d’un démonstrateur industriel qui se veut prêt à un déploiement en usine. Cela impose donc de prendre en compte dès le début de la réflexion scientifique les contraintes industrielles telles que l’encombrement, le temps de cycle, la matériel et l’architecture logicielle à disposition, ou encore les tolérances de qualité. Des validations expérimentales ont été réalisées sur ce banc d’essaiRobotics research is increasingly interested in the manipulation of soft objects: fabrics, foams or any other deformable object like rubber. The deformation of such an object is usually modeled by introducing new degrees of freedom, which makes its control more complex. In the context of the industry of the future, the Manufacture Française des Pneumatiques Michelin wishes to modernize its tire manufacturing process which consists of assembling, layer by layer, strips and plies of rubber. These tasks, which have never been robotized before this thesis, fall within the domain of robotic manipulation of deformable objects (RMDO).Through the CIFRE plan (French Industrial Research Training Convention) of the ANRT (French National Association for Technological Research), this thesis addresses this issue in an industrial application context through the design of a robotic cell by providing innovative technological solutions, especially in terms of actuation, perception, and control. However, we show that the integration of these solutions is limited by classical problems of RMDO, such as the modeling of object deformations, multimodal perception or dynamic control and generation of tasks.A first contribution is the adaptation of image processing algorithms from open-source libraries to an industrial context. These algorithms replace commercial industrial solutions and allow a greater freedom of parameterization for each function. The result is an assembly of flexible algorithmic bricks adapted to the specificities of the tire manufacturing process.This thesis also explores the use of a reduced physical model to control the tension in a suspended gum strip, one end of which is wrapped around a spool while the other is manipulated by a robot. We distinguish three contributions: vision-based estimation of the tension, a closed-loop control law to regulate the rotation speed of the reel and thus vary the length of the suspended part of the strip, and a planning algorithm to achieve the desired tension.A last contribution concerns a visual feedback control allowing to join end to end the two ends of a web wrapped around a cylindrical surface. This complex operation is based on visual perception and 3D reconstruction of the edge of the ply as well as a control law considering a weighted measure of the error.Our developments have enabled the design and production of an industrial demonstrator that is ready for deployment in a factory. This means that industrial constraints such as sizing, cycle time, available hardware and software architecture, and quality tolerances have been considered from the beginning of the scientific reflection. Experimental validations were carried out on this test bench
2
Caporali, Alessio. "Robotic manipulation of cloth-like deformable objects." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Знайти повний текст джерелаАнотація:
The manipulation of cloth-like deformable objects represents a challenging problem. Clothes are characterized by having shape, appearance, and other mechanical and visual properties to vary due to previous manipulations or external effects. In this thesis the problem of grasping cloth-like objects is addressed. This dissertation is part of a project where a mobile robot is involved in the loading and unloading of clothes for the end-of-line tests of washing machines. In particular, the thesis focuses on estimating target poses that would result in reliable grasping operations for a robotic arm. The processing of input pointclouds coming from a 3D camera is performed in order to develop strategies and algorithms for grasping clothes both from a bin randomly placed nearby the robot but also for clothes placed inside a drum or across its opening door. The structure of the developed algorithms is organized into three layers. In addition, the problem of avoiding collisions is analyzed, in particular inside the drum where the plastic paddles are identified with this purpose. The PointCloud library along with the Eigen library are utilized to perform the processing of the pointclouds. Chapter 2 focuses on the grasping of clothes from an external bin while Chapter 3 describes how the paddles in the washing machine are localized. Chapter 4 provides solutions for the grasping of clothes placed inside the drum. Chapter 5 addresses the problem of detecting cloths along the drum opening. Chapter 6 shows a possible application of the algorithms described in Chapter 2 and 5 on a real robot employing tools like ROS, Moveit! and a behavior three as task manger.
3
Zhu, Jihong. "Vision-based robotic manipulation of deformable linear objects." Thesis, Montpellier, 2020. http://www.theses.fr/2020MONTS008.
Повний текст джерелаАнотація:
En robotique, la manipulation d'objets déformables reçoit moins d'attention que celle d'objets rigides. Pourtant, de nombreux objets dans la vie réelle sont déformables. La recherche sur la manipulation d'objets déformables est indispensable pour doter les robots d'une dextérité de manipulation totale. La difficulté majeure de ce problème est que déformation de l'objet a un espace de configurations de dimensions infinie, tandis que les entrées du robots sont limitées. Dans le cadre de VERSATILE, un projet H2020 axé sur l'automatisation industrielle à l'aide de robots, nous avons axé nos recherches sur la manipulation d'objets déformables linéaires (câbles) par retour visuel.Une caractéristique de la manipulation des objets déformables est que la forme de l'objet change pendant la manipulation. Par conséquent, un problème important consiste à contrôler la forme de l'objet pendant la manipulation. Nous avons abordé le problème du contrôle de forme en exploitant le retour visuel.Dans un premier temps, nous avons représenté la forme de l'objet avec une série de Fourier. Nous estimons et mettons à jour la matrice d'interaction en ligne, puis nous concevons le contrôleur pour contrôler la forme.Ensuite, au lieu d'utiliser une caractéristique définie par l'humain pour le paramétrage, nous avons laissé le robot apprendre automatiquement les vecteurs de caractéristiques à partir des données visuelles. Nous proposons une méthode qui permet au robot de générer simultanément - et à partir des mêmes données - un vecteur de caractéristiques ainsi que la matrice d'interaction. Cette méthode nécessite un minimum de données pour l'initialisation. L'apprentissage et le contrôle peuvent être effectués en ligne de manière adaptative. Nous pouvons appliquer la même méthode à la manipulation d'objets rigides, directement et sans modification.Ces deux travaux ne requièrent aucune calibration de la caméra et ont été validés avec des expérimentations de robotique réelle.Un autre domaine d'importance dans la manipulation d'objets déformables est l'utilisation de contacts externes pour contrôler la forme de l'objet. Les contacts externes peuvent et doivent être utilisés pour la manipulation d'objets déformables. Nous considérons un scénario fréquent dans l'industrie - l'acheminement de câbles avec des contacts externes comme processus à automatiser avec notre robot. Nous proposons un algorithme de planification qui permet au robot d'utiliser des contacts pour déformer le câble et pour obtenir la configuration souhaitée. Des expériences robotiques réelles avec différents scénarios de placement de contacts permettent de valider nos algorithmesIn robotics, the area of deformable object manipulation receives far less attention than that of rigid object manipulation. However, many objects in real life are deformable. Research on deformable object manipulation is indispensable to equip robots with full manipulation dexterity. Deformable linear object (DLO) is one type of deformable objects that commonly presents in the industry and households, for instance, electrical cables for power transfer, USB cables for data transfer, or ropes for dragging and lifting equipment. In the context of H2020 VERSATILE, a project focusing on industrial automation using robots, we focus our research on DLO manipulation via visual feedback.One characteristic of deformable object manipulation is that the object shape changes while being manipulated. Consequently, a research direction is to control the shape of the object during manipulation. We tackle the shape control problem by using vision. Initially, we parameterize the shape with Fourier series, estimate and update the interaction matrix online, and finally control the DLO shape.In the subsequent research, instead of using human-defined features for parameterization, we let the robot automatically learn feature vectors from visual data. We propose a method that allows the robot to simultaneously generate a feature vector and the interaction matrix from the same data. Our approach requires minimum data for initialization. Learning and control can be done online in an adaptive manner. We can also apply the method to rigid object manipulation directly without modification.Neither of the two frameworks requires camera calibration, and both are verified with simulation and real robotic experiments.Another area of importance in deformable object manipulation is the utilization of external contacts. The object deformation is defined in a configuration space of infinite dimension. Nonetheless, the inputs from robots are limited. External contacts can and should be used for manipulating deformable objects. We take a practical scenario in the industry -- cable routing with external contacts as the process to automate with our robot. We propose a planning algorithm that allows the robot to use contacts for shaping the cable and achieving the desired cable configuration. Real robotic experiments with different contact placement scenarios further validate the algorithms
4
Wang, Zhifeng. "Robotic Manipulation of Deformable Linear Objects: Modelling and Simulation." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Знайти повний текст джерелаАнотація:
With the development of materials science, deformable material objects are used in more andmore fields. Handling of deformable soft objects can be found in many industrial fields includingfood industry and recycle industry. But deformable objects are different from rigid objects. Thereis still room for development of material control, in which the use of computers to simulate controlplays an important role. In this thesis, a physical model of the cable is established based ongeometrically exact dynamic splines, and the simulink of matlab is used to develop the model ofthe cable to establish a control system. Under the action of this control system, the cable can reacha designated position and form the desired shape through a series of operations from the defaultposition and the straight starting state. In this process, the cable will contact the establishedobstacle model and will be affected by the interaction force provided by the obstacle model.At theend of the thesis, the simulation results are analyzed.
5
Rowlands, Stephen. "Robotic Control for the Manipulation of 3D Deformable Objects." Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/42554.
Повний текст джерелаАнотація:
Robotic grasping and manipulation of three-dimensional deformable objects is a complex task that currently does not have robust and flexible solutions. Deformable objects include a wide variety of elastic and inelastic objects that change size and shape during manipulation. The development of adaptable methods for grasping and autonomously controlling the shape of three-dimensional deformable objects will benefit many commercial applications, including shaping parts for assembly in manufacturing, manipulating food for packaging and controlling tissues during robotic surgery. Controlling a deformable object to a desired shape requires first choosing contact points on the object's surface. Next, the robotic hand is positioned in the correct position and orientation to grasp and deform the object. After deformation, the object is assessed to evaluate the quality of the shape control procedure. In many cases, this process is completed without knowing the object's properties or behaviour before deformation. This work proposes and implements the framework for a robotic arm and hand system to control the shape of a previously unseen deformable object autonomously. Significant original contributions are made in developing an original algorithm to plan contact points on a three-dimensional object for grasping and shape control. This research uses a novel object representation to reduce the dimensionality of the deformable object manipulation problem. A path planning algorithm guides the robot arm to the optimal valid grasp pose to deform the object at the determined contact points. Additional contributions include developing a multi-view assessment strategy to determine the quality of the deformation towards the desired shape. The system completes the objectives using depth and colour images captured from a single point of view to locate and identify a previously unseen three-dimensional object within a robotic workspace. After estimating the unknown object's geometry, initial grasp contact points are planned to control the object to the desired shape. The grasp points are used to plan and execute a collision-free trajectory for the robot manipulator to place the robotic hand in the optimal position and orientation to grasp and deform the object. After the deformation is complete, the object is moved to a variety of assessment positions to determine the success of the shape control procedure. The system is validated experimentally on a variety of deformable three-dimensional objects.
6
Zanella, Riccardo <1991>. "Robotic Sensing and Manipulation of Deformable Linear Objects with Learning-based methods." Doctoral thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amsdottorato.unibo.it/9704/1/phd_thesis_riccardo_zanella.pdf.
Повний текст джерелаАнотація:
Nowadays robotic applications are widespread and most of the manipulation tasks are efficiently solved. However, Deformable-Objects (DOs) still represent a huge limitation for robots. The main difficulty in DOs manipulation is dealing with the shape and dynamics uncertainties, which prevents the use of model-based approaches (since they are excessively computationally complex) and makes sensory data difficult to interpret. This thesis reports the research activities aimed to address some applications in robotic manipulation and sensing of Deformable-Linear-Objects (DLOs), with particular focus to electric wires. In all the works, a significant effort was made in the study of an effective strategy for analyzing sensory signals with various machine learning algorithms. In the former part of the document, the main focus concerns the wire terminals,
i.e. detection, grasping, and insertion. First, a pipeline that integrates vision and tactile sensing is developed, then further improvements are proposed for each module.
A novel procedure is proposed to gather and label massive amounts of training images for object detection with minimal human intervention. Together with this strategy, we extend a generic object detector based on Convolutional-Neural-Networks for orientation prediction.
The insertion task is also extended by developing a closed-loop control capable to guide the insertion of a longer and curved segment of wire through a hole, where the contact forces are estimated by means of a Recurrent-Neural-Network.
In the latter part of the thesis, the interest shifts to the DLO shape. Robotic reshaping of a DLO is addressed by means of a sequence of pick-and-place primitives, while a decision making process driven by visual data learns the optimal grasping locations exploiting Deep Q-learning and finds the best releasing point. The success of the solution leverages on a reliable interpretation of the DLO shape. For this reason, further developments are made on the visual segmentation.
7
Chandra, Rohit. "Application of Dual Quaternion for Bimanual Robotic Tasks." Thesis, Université Clermont Auvergne (2017-2020), 2019. http://www.theses.fr/2019CLFAC042.
Повний текст джерелаАнотація:
L'approche classique pour le contrôle coopératif dans l’espace de travail d’un manipulateur bi-bras a été revisitée. En particulier, une nouvelle approche pour la formulation symétrique de la coordination bi-bras à l'aide du concept "virtual sticks" a été proposée à l'aide d'un torseur cinématique en utilisant des quaternions duaux. Le contrôle couplé dans l'espace de travail coopératif qui est proposé, i.e. le contrôle simultané, en position et en orientation, des points de consigne de l'espace de travail relatif et absolu a été comparé à un contrôleur proportionnel découplé traitant séparément les erreurs de position et d'orientation. Le contrôleur couplé a démontré un meilleur suivi de la pose et de l'orientation en termes de précision et de stabilité comparé au contrôleur découplé pour les tâches exigeant un fonctionnement plus rapide dans l'espace de travail relatif des manipulateurs bi-bras.L'approche de modélisation et de contrôle de l'espace de travail d’une tâche coopérative, en exploitant les torseurs cinématiques et des quaternions duaux, a été étendue à la modélisation de la coopération des doigts d'une main robotique anthropomorphique. De plus, le couplage des articulations des doigts sous-actionnés de la main robotique a été représenté à l’aide de la "jacobienne couplée" du doigt. La "jacobienne couplée" du doigt robotique a été utilisée pour le contrôle cinématique inverse, tout en lui permettant une intégration facile avec un bras robotique.L'idée d'un traitement couplé des variables en position et en orientation a été capitalisée en utilisant la conception d'une trajectoire de second ordre utilisant des quaternions duaux. Le contrôleur de trajectoire ainsi conçu est capable de suivre les points de consigne en pose en vitesse et en accélération, de l'effecteur en utilisant le modèle dynamique inverse du robot. Le contrôleur couplé en taux d’accélération résolue ("resolved rate acceleration") s'est avéré capable d'un contrôle de trajectoire plus précis, particulièrement en termes d'erreurs liées à l'orientation, que le contrôleur découplé classique qui traitait séparément les points de consigne en position et en orientation et ignorait l'effet de la rotation sur le mouvement de translation. De plus, cela a également permis de réduire les oscillations de la commande du couple des articulations lorsque le contrôleur a été implémenté pour le contrôle de l'un des bras du robot bi-bras Baxter.Enfin, un cadre complet pour la coordination des systèmes robotiques bi-bras a été proposé avec l'ajout d'un planificateur de tâches coopératives. La simplicité du torseur cinématique a également été exploitée pour la génération de trajectoires généralisées du second ordre pour des tâches nécessitant un mouvement simplifié, comme la translation, la rotation et la torsion autour d'un axe hélicoïdale arbitraire donné dans un repère connu. La méthode de génération de trajectoires a été étendue pour représenter les contraintes liées aux tâches impliquant un contact entre les objets en utilisant le concept de mécanisme virtuelThe classical approach for dual-arm cooperative task space control was revisited and the symmetric formulation of dual arm coordination using virtual sticks was implemented using screw-based kinematics with dual quaternion representation. The proposed coupled control of cooperative task space, i.e. simultaneous control of both position and orientation setpoints of relative and absolute task space was compared against the performance of a proportional decoupled controller treating position and orientation error separately. The coupled controller demonstrated better tracking of pose and orientation in terms of accuracy and stability compared to the decoupled controller for tasks requiring faster operation in the relative task space of dual-arm manipulators.The cooperative task space modelling and control approach using screw-based kinematics and dual quaternions were extended for the cooperation modelling of the fingers of an anthropomorphic robotic hand. Additionally, the coupling of joints in the underactuated fingers of the robotic hand was represented with a coupled finger Jacobian. The coupled Jacobian of the robotic finger was used for inverse kinematic control, while allowing easy integration with a robotic arm.The idea of coupled treatment of position and orientation variables was capitalized further with the design of a second-order trajectory tracker using dual quaternions. The trajectory controller hence designed was capable of tracking pose, velocity and acceleration setpoints for the end-effector using inverse dynamic model of the robot. The coupled resolved rate acceleration controller was found to be capable of tighter trajectory control, specially for error terms related to orientation, compared to the conventional decoupled controller that treated the position and orientation setpoints separately and ignored the inherent effect of rotation on translational motion. Additionally, it also led to lower oscillations in the joint torque command when implemented for the control of one of the arms of Baxter dual-arm robot.Finally, a complete framework for the coordination of bi-arm robotic systems was proposed with the addition of a cooperative task planner. The simplicity of screw theory was exploited additionally for parametrized generation of generalized second order trajectories for tasks requiring simplified motion, like translation, rotation and screw motion around an arbitrary 6D screw-axis given in a known reference frame. The trajectory generation method was extended to represent the constraints related to tasks involving contact between objects using the concept of virtual mechanism
8
Phillips-Grafflin, Calder. "Enabling Motion Planning and Execution for Tasks Involving Deformation and Uncertainty." Digital WPI, 2017. https://digitalcommons.wpi.edu/etd-dissertations/307.
Повний текст джерелаАнотація:
"A number of outstanding problems in robotic motion and manipulation involve tasks where degrees of freedom (DoF), be they part of the robot, an object being manipulated, or the surrounding environment, cannot be accurately controlled by the actuators of the robot alone. Rather, they are also controlled by physical properties or interactions - contact, robot dynamics, actuator behavior - that are influenced by the actuators of the robot. In particular, we focus on two important areas of poorly controlled robotic manipulation: motion planning for deformable objects and in deformable environments; and manipulation with uncertainty. Many everyday tasks we wish robots to perform, such as cooking and cleaning, require the robot to manipulate deformable objects. The limitations of real robotic actuators and sensors result in uncertainty that we must address to reliably perform fine manipulation. Notably, both areas share a common principle: contact, which is usually prohibited in motion planners, is not only sometimes unavoidable, but often necessary to accurately complete the task at hand. We make four contributions that enable robot manipulation in these poorly controlled tasks: First, an efficient discretized representation of elastic deformable objects and cost function that assess a ``cost of deformation' for a specific configuration of a deformable object that enables deformable object manipulation tasks to be performed without physical simulation. Second, a method using active learning and inverse-optimal control to build these discretized representations from expert demonstrations. Third, a motion planner and policy-based execution approach to manipulation with uncertainty which incorporates contact with the environment and compliance of the robot to generate motion policies which are then adapted during execution to reflect actual robot behavior. Fourth, work towards the development of an efficient path quality metric for paths executed with actuation uncertainty that can be used inside a motion planner or trajectory optimizer."
Частини книг з теми "Robotic Manipulation of Deformable Objects (RMDO)"
1
Millard, David, James A. Preiss, Jernej Barbič, and Gaurav S. Sukhatme. "Parameter Estimation for Deformable Objects in Robotic Manipulation Tasks." In Springer Proceedings in Advanced Robotics, 239–51. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-25555-7_16.
Повний текст джерела
2
F., Fouad, and Pierre Payeur. "Dexterous Robotic Manipulation of Deformable Objects with Multi-Sensory Feedback - a Review." In Robot Manipulators Trends and Development. InTech, 2010. http://dx.doi.org/10.5772/9183.
Повний текст джерелаТези доповідей конференцій з теми "Robotic Manipulation of Deformable Objects (RMDO)"
1
Mira, D., A. Delgado, C. M. Mateo, S. T. Puente, F. A. Candelas, and F. Torres. "Study of dexterous robotic grasping for deformable objects manipulation." In 2015 23th Mediterranean Conference on Control and Automation (MED). IEEE, 2015. http://dx.doi.org/10.1109/med.2015.7158760.
Повний текст джерела
2
Li, Xiang, Zerui Wang, and Yun-Hui Liu. "Sequential Robotic Manipulation for Active Shape Control of Deformable Linear Objects." In 2019 IEEE International Conference on Real-time Computing and Robotics (RCAR). IEEE, 2019. http://dx.doi.org/10.1109/rcar47638.2019.9044123.
Повний текст джерела
3
Tang, Te, Changliu Liu, Wenjie Chen, and Masayoshi Tomizuka. "Robotic manipulation of deformable objects by tangent space mapping and non-rigid registration." In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2016. http://dx.doi.org/10.1109/iros.2016.7759418.
Повний текст джерела
4
Bednarek, Michal, and Krzysztof Walas. "Comparative Assessment of Reinforcement Learning Algorithms in the Taskof Robotic Manipulation of Deformable Linear Objects." In 2019 4th International Conference on Robotics and Automation Engineering (ICRAE). IEEE, 2019. http://dx.doi.org/10.1109/icrae48301.2019.9043790.
Повний текст джерела
5
Valencia, Angel J., Felix Nadon, and Pierre Payeur. "Toward Real-Time 3D Shape Tracking of Deformable Objects for Robotic Manipulation and Shape Control." In 2019 IEEE SENSORS. IEEE, 2019. http://dx.doi.org/10.1109/sensors43011.2019.8956623.
Повний текст джерела
6
Zürn, Manuel, Annika Kienzlen, Lars Klingel, Armin Lechler, Alexander Verl, Shiyi Ren, and Weiliang Xu. "Deep Learning-Based Instance Segmentation for Feature Extraction of Branched Deformable Linear Objects for Robotic Manipulation." In 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE). IEEE, 2023. http://dx.doi.org/10.1109/case56687.2023.10260646.
Повний текст джерела