Control framework for dexterous manipulation using dynamic visual servoing and tactile sensors’ feedback

Tactile sensors play an important role in robotics manipulation to perform dexterous and complex tasks. This paper presents a novel control framework to perform dexterous manipulation with multi-fingered robotic hands using feedback data from tactile and visual sensors. This control framework permits the definition of new visual controllers which allow the path tracking of the object motion taking into account both the dynamics model of the robot hand and the grasping force of the fingertips under a hybrid control scheme. In addition, the proposed general method employs optimal control to obtain the desired behaviour in the joint space of the fingers based on an indicated cost function which determines how the control effort is distributed over the joints of the robotic hand. Finally, authors show experimental verifications on a real robotic manipulation system for some of the controllers derived from the control framework.

Dynamic Visual Servoing With Chaos Control for Redundant Robots

This paper presents a new dynamic visual control system for redundant robots with chaos compensation. In order to implement the visual servoing system, a new architecture is proposed that improves the system maintainability and traceability. Furthermore, high performance is obtained as a result of parallel execution of the different tasks that compose the architecture. The control component of the architecture implements a new visual servoing technique for resolving the redundancy at the acceleration level in order to guarantee the correct motion of both end-effector and joints. The controller generates the required torques for the tracking of image trajectories. However, in order to guarantee the applicability of this technique, a repetitive path tracked by the robot-end must produce a periodic joint motion. A chaos controller is integrated in the visual servoing system and the correct performance is observed in low and high velocities. Furthermore, a method to adjust the chaos controller is proposed and validated using a real three-link robot.

Direct Visual Servoing Framework based on Optimal Control for Redundant Joint Structures

This paper presents a new framework based on optimal control to define new dynamic visual controllers to carry out the guidance of any serial link structure. The proposed general method employs optimal control to obtain the desired behaviour in the joint space based on an indicated cost function which determines how the control effort is distributed over the joints. The proposed approach allows the development of new direct visual controllers for any mechanical joint system with redundancy. Finally, authors show experimental results and verifications on a real robotic system for some derived controllers obtained from the control framework.

Aerial Object Following Using Visual Fuzzy Servoing

This article presents a visual servoing system to follow a 3D moving object by a Micro Unmanned Aerial Vehicle (MUAV). The presented control strategy is based only on the visual information given by an adaptive tracking method based on the colour information. A visual fuzzy system has been developed for servoing the camera situated on a rotary wing MAUV, that also considers its own dynamics. This system is focused on continuously following of an aerial moving target object, maintaining it with a fixed safe distance and centred on the image plane. The algorithm is validated on real flights on outdoors scenarios, showing the robustness of the proposed systems against winds perturbations, illumination and weather changes among others. The obtained results indicate that the proposed algorithms is suitable for complex controls task, such object following and pursuit, flying in formation, as well as their use for indoor navigation

Sistema de supervisão aérea baseado em navegação visual para detecção de anomalias em instalações de petróleo e gás

This work deals with the development of a prototype of a helicopter quadrotor for monitoring applications in oil facilities. Anomaly detection problems can be resolved through monitoringmissions performed by a suitably instrumented quadrotor, i.e. infrared thermosensors should be embedded. The proposed monitoring system aims to reduce accidents as well as to make possible the use of non-destructive techniques for detection and location of leaks caused by corrosion. To this end, the implementation of a prototype, its stabilization and a navigation strategy have been proposed. The control strategy is based on dividing the problem into two control hierarchical levels: the lower level stabilizes the angles and the altitude of the vehicle at the desired values, while the higher one provide appropriate references signals to the lower level in order the quadrotor performs the desired movements. The navigation strategy for helicopter quadrotor is made using information provided by a acquisition image system (monocular camera) embedded onto the helicopter. Considering that the low-level control has been solved, the proposed vision-based navigation technique treats the problem as high level control strategies, such as, relative position control, trajectory generation and trajectory tracking. For the position control we use a control technique for visual servoing based on image features. The trajectory generation is done in a offline step, which is a visual trajectory composed of a sequence of images. For the trajectory tracking problem is proposed a control strategy by continuous servovision, thus enabling a navigation strategy without metric maps. Simulation and experimental results are presented to validate the proposal

3D Object following based on visual information for Unmanned Aerial Vehicles

This article presents a novel system and a control strategy for visual following of a 3D moving object by an Unmanned Aerial Vehicle UAV. The presented strategy is based only on the visual information given by an adaptive tracking method based on the color information, which jointly with the dynamics of a camera fixed to a rotary wind UAV are used to develop an Image-based visual servoing IBVS system. This system is focused on continuously following a 3D moving target object, maintaining it with a fixed distance and centered on the image plane. The algorithm is validated on real flights on outdoors scenarios, showing the robustness of the proposed systems against winds perturbations, illumination and weather changes among others. The obtained results indicate that the proposed algorithms is suitable for complex controls task, such object following and pursuit, flying in formation, as well as their use for indoor navigation

Dynamically balanced and plausible trajectory planning for human-like characters

International audience

A formação de professores para o ensino da Matemática no ensino básico a alunos com deficiência visual

Resumo: Este estudo surge no âmbito do Mestrado em Reabilitação na Especialidade de Deficiência Visual ministrado em conjunto pelas Faculdades de Ciências Médicas e Motricidade Humana. Na dissertação intitulada Formação de Professores para o Ensino da Matemática no Ensino Básico a Alunos com DV foi desenvolvida uma investigação, incidindo sobre a temática atrás referida. Na primeira parte apresenta-se uma revisão de literatura, onde se exploram vários conceitos relevantes como a deficiência visual, o currículo de matemática no Ensino Básico, as adaptações curriculares dos alunos com DV, as tecnologias de apoio e a Formação dos Professores, entre outros. Na segunda parte apresentam-se as fundamentações teóricas que subjazem à escolha da metodologia de investigação e instrumentação bem como a descrição dos procedimentos de investigação. Participaram neste estudo 52 professores de Matemática dos três ciclos do ensino básico, que tinham alunos cegos ou com baixa visão nas suas turmas. Os dados foram recolhidos através de um questionário aplicados aos professores. Na terceira parte apresentam-se alguns resultados desta pesquisa. Relativamente à Formação de Professores, sendo N= 52, no que diz respeito à Deficiência Visual, a maioria dos professores (58%) diz não ter conhecimento da mesma e 40% dos professores diz ter algum conhecimento sobre a deficiência visual. Destes professores, grande parte referiu não considerar suficiente a informação recebida, pelo que concluímos ser pertinente a proposta de cursos versando a formação de professores em Deficiência Visual. Conclui-se também que os professores sentem dificuldades com os materiais e equipamentos disponíveis embora refiram que tivessem tido alguma informação sobre os mesmos.----------------------------------------- ABSTRACT: This study is the subject of the Master Course on the Specialty of Visual impaired given by both the Faculties of Ciências Médicas and Motricidade Humana. In the dissertation, the title of Which is Vocational Training of Teachers for the Mathematies teaching in the Basic Compulsory education to students with Visual impaired inside of the thematic behind referred. In the first part it is presented a literature revision, where some concepts are explored like the visual impaired, the curriculum of mathematics in the Basic Compulsory Education, the curriculum adaptations to the pupils with visual impaired, the technologies of support and the vocational training of the teachers, among others. In the second part we can recognize the theoretical recitals that support the choice of the research methodology and the whole instrumens meedes as well as the description of the research procedures. 52 professors of Mathematics from the three cycles of basic compulsory education participated in this study, they had blind pupils or with low vision in their classes. The data had been collected through a questionnaire applied to the teachers. In the third part, we come to some results of this research. In what concerns the vocational training of the teachers being N= 52, the majority of them (58%) says not to have knowledge of it and 40% of them says that they have some knowledge on the visual impaired. Among, a great part mentioned not having received sufficient information, as we conclude to be pertinent the proposal of courses makina the vocational training of teachers in visual impaired a reality. One also concludes that the teachers have difficulties with the materials and available equipment even though they mention to have had some information about them.

Manobras de condução assistida para veículos submarinos subactuados

A intervenção humana no manuseamento de veículos submarinos operados remotamente (ROVs) é um requisito necessário para garantir o sucesso da missão e a integridade do equipamento. Contudo, a sua teleoperação não é fácil, pelo que a condução assistida destes veículos torna-se relevante. Esta dissertação propõe uma solução para este problema para ROVs de 3DOF (surge, heave e yaw). São propostas duas abordagens distintas – numa primeira propõe-se um sistema de controlo Image Based Visual Servoing (IBVS) tendo em vista a utilização exclusiva de uma câmara (sensor existente neste tipo de sistemas) por forma a melhorar significativamente a teleoperação de um pequeno ROV; na segunda, propõe-se um sistema de controlo cinemático para o plano horizontal do veículo e um algoritmo de uma manobra capaz de dotar o ROV de movimento lateral através de uma trajectória dente-de-serra. Demonstrou-se em cenários de operação real que o sistema proposto na primeira abordagem permite ao operador de um ROV com 3DOF executar tarefas de alguma complexidade (estabilização) apenas através de comandos de alto nível, melhorando assim drasticamente a teleoperação e qualidade de inspecção do veículo em questão. Foi também desenvolvido um simulador do ROV em MATLAB para validação e avaliação das manobras, onde o sistema proposto na segunda abordagem foi validado com sucesso.

Nouvelle approche pour modifier le tropisme des vecteurs adénoviraux à l’aide de ligands bispécifiques

L’adénovirus a été étudié dans l’optique de développer de nouveaux traitements pour différentes maladies. Les vecteurs adénoviraux (AdV) sont des outils intéressants du fait qu’ils peuvent être produits en grandes quantités (1X1012 particules par millilitre) et de par leur capacité à infecter des cellules quiescentes ou en division rapide. Les AdVs ont subi bon nombre de modifications pour leur permettre de traiter des cellules tumorales ou pour transporter des séquences génétiques exogènes essentielles pour le traitement de maladies monogéniques. Toutefois, les faibles niveaux d’expression du récepteur primaire de l’adénovirus, le CAR (récepteur à l’adénovirus et au virus coxsackie), réduit grandement l’efficacité de transduction dans plusieurs tumeurs. De plus, certains tissus normaux comme les muscles n’expriment que très peu de CAR, rendant l’utilisation des AdVs moins significative. Pour pallier à cette limitation, plusieurs modifications ont été générées sur les capsides virales. L’objectif de ces modifications était d’augmenter l’affinité des AdVs pour des récepteurs cellulaires spécifiques surexprimés dans les tumeurs et qui seraient exempts dans les tissus sains avoisinant. On peut mentionner dans les approches étudiées: l’utilisation de ligands bispécifiques, l’incorporation de peptides dans différentes régions de la fibre ou la substitution par une fibre de sérotypes différents. Notre hypothèse était que les domaines d’interaction complémentaire (K-Coil et ECoil) permettraient aux ligands de s’associer aux particules virales et d’altérer le tropisme de l’AdV. Pour ce faire, nous avons inclus un domaine d’interaction synthétique, le K-Coil,dans différentes régions de la fibre virale en plus de générer des mutations spécifiques pour abolir le tropisme naturel. Pour permettre la liaison avec les récepteurs d’intérêt dont l’EGF-R, l’IGF-IR et le CEA6, nous avons fusionné le domaine d’interaction complémentaire, le E-Coil, soit dans les ligands des récepteurs ciblés dont l’EGF et l’IGF-I, soit sur un anticorps à un seul domaine reconnaissant la protéine membranaire CEA6, l’AFAI. Suite à la construction des différents ligands de même que des différentes fibres virales modifiées, nous avons determiné tout d’abord que les différents ligands de même que les virus modifiés pouvaient être produits et que les différentes composantes pouvaient interagir ensemble. Les productions virales ont été optimisées par l’utilisation d’un nouveau protocole utilisant l’iodixanol. Ensuite, nous avons démontré que l’association des ligands avec le virus arborant une fibre modifiée pouvait entraîner une augmentation de transduction de 2 à 21 fois dans différentes lignées cellulaires. À cause de la difficulté des adénovirus à infecter les fibres musculaires occasionnée par l’absence du CAR, nous avons cherché à savoir si le changement de tropisme pourrait accroître l’infectivité des AdVs. Nous avons démontré que l’association avec le ligand bispécifique IGF-E5 permettait d’accroître la transduction autant dans les myoblastes que dans les myotubes de souris. Nous avons finalement réussi à démontrer que notre système pouvait induire une augmentation de 1,6 fois de la transduction suite à l’infection des muscles de souriceaux MDX. Ces résultats nous amènent à la conclusion que le système est fonctionnel et qu’il pourrait être évalué dans des AdVs encodant pour différents gènes thérapeutiques.

Characterizing typographic expertise: do we process typefaces like faces?

Studies of face recognition and discrimination provide a rich source of data and debate on the nature of their processing, in particular through using inverted faces. This study draws parallels between the features of typefaces and faces, as letters share a basic configuration, regardless of typeface, that could be seen as similar to faces. Typeface discrimination is compared using paragraphs of upright letters and inverted letters at three viewing durations. Based on previously reported effects of expertise, the prediction that designers would be less accurate when letters are inverted, whereas nondesigners would have similar performance in both orientations, was confirmed. A proposal is made as to which spatial relations between typeface components constitute holistic and configural processing, posited as the basis for better discrimination of the typefaces of upright letters. Such processing may characterize designers’ perceptual abilities, acquired through training.

Desenvolvimento de esquema de controle com realimentação visual para um robô manipulador

This work proposes a kinematic control scheme, using visual feedback for a robot arm with five degrees of freedom. Using computational vision techniques, a method was developed to determine the cartesian 3d position and orientation of the robot arm (pose) using a robot image obtained through a camera. A colored triangular label is disposed on the robot manipulator tool and efficient heuristic rules are used to obtain the vertexes of that label in the image. The tool pose is obtained from those vertexes through numerical methods. A color calibration scheme based in the K-means algorithm was implemented to guarantee the robustness of the vision system in the presence of light variations. The extrinsic camera parameters are computed from the image of four coplanar points whose cartesian 3d coordinates, related to a fixed frame, are known. Two distinct poses of the tool, initial and final, obtained from image, are interpolated to generate a desired trajectory in cartesian space. The error signal in the proposed control scheme consists in the difference between the desired tool pose and the actual tool pose. Gains are applied at the error signal and the signal resulting is mapped in joint incrementals using the pseudoinverse of the manipulator jacobian matrix. These incrementals are applied to the manipulator joints moving the tool to the desired pose

Controle de Manipulador Redundante Utilizando Realimentação Visual

In conventional robot manipulator control, the desired path is specified in cartesian space and converted to joint space through inverse kinematics mapping. The joint references generated by this mapping are utilized for dynamic control in joint space. Thus, the end-effector position is, in fact, controlled indirectly, in open-loop, and the accuracy of grip position control directly depends on the accuracy of the available kinematic model. In this report, a new scheme for redundant manipulator kinematic control, based on visual servoing is proposed. In the proposed system, a robot image acquired through a CCD camera is processed in order to compute the position and orientation of each link of the robot arm. The robot task is specified as a temporal sequence of reference images of the robot arm. Thus, both the measured pose and the reference pose are specified in the same image space, and its difference is utilized to generate a cartesian space error for kinematic control purposes. The proposed control scheme was applied in a four degree-of-freedom planar redundant robot arm, experimental results are shown

Omnidirectional bearing-only see-and-avoid for small aerial robots:

Motivated by the growing interest in unmanned aerial system's applications in indoor and outdoor settings and the standardisation of visual sensors as vehicle payload. This work presents a collision avoidance approach based on omnidirectional cameras that does not require the estimation of range between two platforms to resolve a collision encounter. It will achieve a minimum separation between the two vehicles involved by maximising the view-angle given by the omnidirectional sensor. Only visual information is used to achieve avoidance under a bearing-only visual servoing approach. We provide theoretical problem formulation, as well as results from real flight using small quadrotors

Catadioptric panoramic stereovision for humanoid robots

This paper proposes a novel design of a reconfigurable humanoid robot head, based on biological likeness of human being so that the humanoid robot could agreeably interact with people in various everyday tasks. The proposed humanoid head has a modular and adaptive structural design and is equipped with three main components: frame, neck motion system and omnidirectional stereovision system modules. The omnidirectional stereovision system module being the last module, a motivating contribution with regard to other computer vision systems implemented in former humanoids, it opens new research possibilities for achieving human-like behaviour. A proposal for a real-time catadioptric stereovision system is presented, including stereo geometry for rectifying the system configuration and depth estimation. The methodology for an initial approach for visual servoing tasks is divided into two phases, first related to the robust detection of moving objects, their depth estimation and position calculation, and second the development of attention-based control strategies. Perception capabilities provided allow the extraction of 3D information from a wide range of visions from uncontrolled dynamic environments, and work results are illustrated through a number of experiments.