Papers by Juan Antonio Corrales Ramon
Advances in intelligent systems and computing, Nov 20, 2019
In the context of metal additive manufacturing, one of the most attractive tasks to be robotized ... more In the context of metal additive manufacturing, one of the most attractive tasks to be robotized is the cleaning process of metal powder after the printing operations. This task presents a challenging scenario for most of robot manipulation approaches in the literature. In this paper we present an approach, marker-less and real time affordable, which address the cleaning problem like a shape manipulation control problem. This control strategy is designed as an optimization problem. The error function is written as a lagrangian function using an objective function based on Gaussian Mixture Model (GMM). The local optimization is performed by a gradient descent and a global optimization process is used to avoid local minima.
HAL (Le Centre pour la Communication Scientifique Directe), Jun 7, 2018
Within the framework of the H2020 European Project 'Bots2ReC' (roBots to ReConstruction) ("Robots... more Within the framework of the H2020 European Project 'Bots2ReC' (roBots to ReConstruction) ("Robots to Re-Construction", 2017), an automated system for the removal of asbestos from a real world rehabilitation site will be developed. The system will consist of multiple robotic units, each one is composed of a mobile platform and a robotic arm with a rotative abrasive tool. In this paper, only the arm control is considered, and the smooth position-force controller presented in (Mohy El Dine, 2017) is validated on a Kuka LWR lightweight robotic arm. The arm is equipped with force/torque sensor, camera and spindle with a grinding tool. The mentioned controller reconsiders the position, force and impedance control strategies together from a practical point of view to achieve the real grinding task. The experimental validation shows the efficiency, advantages and drawbacks of the proposed controller and it draws conclusions about the main factors that affect the wall grinding operation and its quality.
The International Journal of Advanced Manufacturing Technology, Mar 18, 2009
This paper describes a multi-sensorial robotic system to automatically construct metallic structu... more This paper describes a multi-sensorial robotic system to automatically construct metallic structures. Two robots must work cooperatively in the same workspace to perform the task. The robots are automatically guided by using visual and force sensor information. A new time-independent visual-force control system which guarantees the adequate robot behaviour during the construction of the structure is described. During the construction of the structure, a human operator works cooperatively with the robots in order to perform some tasks which cannot be automatically developed by the robots. To do so, a new human-robot cooperation approach is described in order to guarantee the human safety. The correct behaviour of the different subsystems proposed in the paper is demonstrated in the results section by the construction of a real structure composed of several metallic tubes and different types of pieces to join them.
This paper presents a miniaturized active vision system for visual tracking. One of the main prob... more This paper presents a miniaturized active vision system for visual tracking. One of the main problems in visual tracking is the autonomy and manageability of the system to be mounted on robotic structures, such as mobile and manipulator robots. The proposed active vision system has been built using a motorized platform characterized by its low price, lightness, small dimensions and wireless control. It is interesting for visual tracking applications where constraints of size and weight must be considered. In our mini active vision system, a tracking method based on CamShift has been implemented. The novelty of our tracker, in comparison with CamShift, is its ability to automatically combine a hue distance component and a saturation component from the HSV colour model in order to track objects in dynamic backgrounds with similar hue values.
We address the monocular visual shape servoing problem. This pushes the challenging visual servoi... more We address the monocular visual shape servoing problem. This pushes the challenging visual servoing problem one step further from rigid object manipulation towards deformable object manipulation. Explicitly, it implies deforming the object towards a desired shape in 3D space by robots using monocular 2D vision. We specifically concentrate on a scheme capable of controlling large isometric deformations. Two important open subproblems arise for implementing such a scheme. (P1) Since it is concerned with large deformations, perception requires tracking the deformable object's 3D shape from monocular 2D images which is a severely underconstrained problem. (P2) Since rigid robots have fewer degrees of freedom than a deformable object, the shape control becomes underactuated. We propose a template-based shape servoing scheme in which we solve these two problems. The template allows us to both infer the object's shape using an improved Shape-from-Template algorithm and steer the object's deformation by means of the robots' movements. We validate the scheme via simulations and real experiments.
Sensors, May 27, 2022
This paper presents a novel design and development of a low-cost and multi-touch sensor based on ... more This paper presents a novel design and development of a low-cost and multi-touch sensor based on capacitive variations. This new sensor is very flexible and easy to fabricate, making it an appropriate choice for soft robot applications. Materials (conductive ink, silicone, and control boards) used in this sensor are inexpensive and easily found in the market. The proposed sensor is made of a wafer of different layers, silicone layers with electrically conductive ink, and a pressure-sensitive conductive paper sheet. Previous approaches like e-skin can measure the contact point or pressure of conductive objects like the human body or finger, while the proposed design enables the sensor to detect the object's contact point and the applied force without considering the material conductivity of the object. The sensor can detect five multi-touch points at the same time. A neural network architecture is used to calibrate the applied force with acceptable accuracy in the presence of noise, variation in gains, and non-linearity. The force measured in real time by a commercial precise force sensor (ATI) is mapped with the produced voltage obtained by changing the layers' capacitance between two electrode layers. Finally, the soft robot gripper embedding the suggested tactile sensor is utilized to grasp an object with position and force feedback signals.
Práctica 5: Automatización de una Célula de Fabricación Objetivos • Diseñar la automatización de ... more Práctica 5: Automatización de una Célula de Fabricación Objetivos • Diseñar la automatización de una célula de fabricación compuesta por un robot, una mesa giratoria y una cinta transportadora. • Emplear sensores y otros dispositivos de automatización. • Conocer cómo utilizar una pantalla LED con Arduino. • Emplear sistemas reales. Introducción En esta práctica se va a emplear un robot Scorbot ER-IX de Intelitek. El lenguaje de programación del robot se denomina ACL. Dicho lenguaje de programación está basado en comandos básicos, tal y como la mayoría de lenguajes de programación de robots. Las instrucciones básicas que debe tener todo lenguaje de programación de robots consisten en una serie de instrucciones para definir las posiciones del mismo, bien mediante coordenadas articulares o coordenadas cartesianas. Además deben permitir realizar el movimiento desde la posición actual hasta una nueva posición, realizando un movimiento coordinado de las articulaciones o siguiendo una determinada trayectoria por el extremo del robot. Otra característica deseable, que no poseen todos los robots comerciales consiste en el movimiento del mismo mediante las velocidades deseadas para cada articulación o para el extremo del brazo. En el caso de la presente práctica, el lenguaje de programación utilizado es bastante similar a un lenguaje "ensamblador". Teniendo todo lo expuesto en cuenta la práctica se plantea de manera que no es necesario disponer de un conocimiento exhaustivo del lenguaje de programación ACL, ya que las partes de programación del robot más complejas serán facilitadas. El lenguaje de programación ACL lo puedes consultar en el manual situado en la siguiente página web: ftp://ftp.robotec.co.il/Public/Translations/Carlos/Spn-pdf/100263-01%20ACL-Ctrlr-B_Span.pdf
Springer proceedings in advanced robotics, 2020
Robots executing force controlled tasks require accurate perception of the applied force in order... more Robots executing force controlled tasks require accurate perception of the applied force in order to guarantee precision. However, dynamic motions generate non-contact forces due to the inertia. These non-contact forces can be regarded as disturbances to be removed such that only the forces generated by contacts with the environment remain. This paper presents an observer based on a recurrent neural network that estimates the non-contact forces measured by a force-torque sensor attached at the end-effector of a robotic arm. The approach is proven to also work with an external load attached to the robotic arm. The recurrent neural network observer uses signals from the joint encoders of the robotic arm and a low-cost inertial measurement unit to estimate the wrenches (i.e. forces and torques) generated due to gravity, inertia, centrifugal and Coriolis forces. The accuracy of the proposed observer is experimentally evaluated by comparing the measurements of the attached force-torque sensor to the observer's non-contact forces estimation. Additionally, the pure contact force estimation is evaluated against an external force-torque sensor.
Revista Iberoamericana De Automatica E Informatica Industrial, Oct 1, 2013
La percepción de profundidad se hace imprescindible en muchas tareas de manipulación, control vis... more La percepción de profundidad se hace imprescindible en muchas tareas de manipulación, control visual y navegación de robots. Las cámaras de tiempo de vuelo (ToF: Time of Flight) generan imágenes de rango que proporcionan medidas de profundidad en tiempo real. No obstante, el parámetro distancia que calculan estas cámaras es fuertemente dependiente del tiempo de integración que se configura en el sensor y de la frecuencia de modulación empleada por el sistema de iluminación que integran. En este artículo, se presenta una metodología para el ajuste adaptativo del tiempo de integración y un análisis experimental del comportamiento de una cámara ToF cuando se modifica la frecuencia de modulación. Este método ha sido probado con éxito en algoritmos de control visual con arquitectura 'eye-in-hand' donde el sistema sensorial está compuesto por una cámara ToF. Además, la misma metodología puede ser aplicada en otros escenarios de trabajo.
Robotics and Autonomous Systems, 2020
We propose an approach that considers controlling contact between a robot and the environment dur... more We propose an approach that considers controlling contact between a robot and the environment during physical interactions. Current physical interaction control approaches are limited in terms of the range of tasks that can be performed. To allow robots to perform more tasks, we derive tactile features representing deformations of the mechanically compliant sensing surface of a tactile sensor and incorporate these features to a robot controller, akin to a visual servo, via touch-and task-dependent tactile feature mapping matrices. As a first contribution, we derive tactile features to localize a contact coordinate frame between an object and an array of pressure sensing elements, with a mechanically compliant surface, attached onto a robot arm end-effector interacting with the object. As a second contribution, we propose tactile projection matrices to design a tactile servoing controller that combines these tactile features with a Cartesian impedance controller of the robot arm. These matrices convert the proposed tactile features to balance not only normal forces but also torques about the sensor's axes. It allows the end-effector to steer the contact frame in a desired manner by regulating errors in the tactile features to address several common issues in robotics: exploration and co-manipulation.
Precise robot manipulation of deformable objects requires an accurate and fast estimation of thei... more Precise robot manipulation of deformable objects requires an accurate and fast estimation of their shape as they deform. So far, visual sensing has been mostly used to solve this issue, but vision sensors are sensitive to occlusions, which might be inevitable when manipulating an object with robot. To address this issue, we present a modular pipeline to track the shape of a soft object in an online manner by coupling tactile sensing with a deformation model. Using a model of a tactile sensor, we compute the magnitude and location of a contact force and apply it as an external force to the deformation model. The deformation model then updates the nodal positions of a mesh that describes the shape of the deformable object. The proposed sensor model and pipeline, are evaluated using a Shadow Dexterous Hand equipped with BioTac sensors on its fingertips and an RGB-D sensor.
Robotics and Autonomous Systems, Aug 1, 2017
The field of in-hand robot manipulation of deformable objects is an open and key issue for the ne... more The field of in-hand robot manipulation of deformable objects is an open and key issue for the next-coming robots. The complexity of physics in a soft object and the huge variety of the deformations of its deformable shape, which can be caused when a robot grasps and manipulates it, makes necessary to develop an adaptable and agile framework for these tasks. Many research works have been proposed to control the manipulation tasks using a model of the manipulated object. Despite these techniques are precise to model the deformations, they are time consuming and, using them in real environments is almost impossible because of the large amount of objects which the robot could find. In this paper, we propose a model-independent framework to control the movements of the fingers of the hands while the robot executes manipulation tasks with deformable objects. This technique is based on tactile images which are obtained as a common interface for different tactile sensors, and uses a servo-tactile control to stabilize the grasping points, avoid sliding and adapt the contacts' configuration regarding to position and magnitude of the applied force. Tactile images are obtained using a combination of dynamic Gaussians, which allows the creation of a common representation for tactile data given by different sensors with different technologies and resolutions. The framework was tested on different manipulation tasks which include complex deformations of the objects, and without using a model of them.
Robotics and Autonomous Systems, Dec 1, 2015
Tactile sensing is an essential element of autonomous dexterous robot hand manipulation. It provi... more Tactile sensing is an essential element of autonomous dexterous robot hand manipulation. It provides information about forces of interaction and surface properties at points of contact between the robot fingers and the objects. Recent advancements in robot tactile sensing led to development of many computational techniques that exploit this important sensory channel. This paper reviews current state-of-the-art of manipulation and grasping applications that involve artificial sense of touch and discusses pros and cons of each technique. The main issues of artificial tactile sensing are addressed. General requirements of a tactile sensor are briefly discussed and the main transduction technologies are analyzed. Twenty eight various tactile sensors, each integrated into a robot hand, are classified in accordance with their transduction types and applications. Previously issued reviews are focused on hardware part of tactile sensors, whereas we present an overview of algorithms and tactile feedback-based control systems that exploit signals from the sensors. The applications of these algorithms include grasp stability estimation, tactile object recognition, tactile servoing and force control. Drawing from advancements in tactile sensing technology and taking into consideration its drawbacks, this paper outlines possible new directions of research in dexterous manipulation.
Federación Internacional de Automatización. Comité Español de Automática eBooks, 2007
Frontiers in Robotics and AI, Apr 28, 2022
This paper addresses the general problem of deformable linear object manipulation. The main appli... more This paper addresses the general problem of deformable linear object manipulation. The main application we consider is in the field of agriculture, for plant grasping, but may have interests in other tasks such as human daily activities and industrial production. We specifically consider an elastic linear object where one of its endpoints is fixed, and another point can be grasped by a robotic arm. To deal with the mentioned problem, we propose a model-free method to control the state of an arbitrary point that can be at any place along the object's length. Our approach allows the robot to manipulate the object without knowing any model parameters or offline information of the object's deformation. An adaptive control strategy is proposed for regulating the state of any point automatically deforming the object into the desired location. A control law is developed to regulate the object's shape thanks to the adaptive estimation of the system parameters and its states. This method can track a desired manipulation trajectory to reach the target point, which leads to a smooth deformation without drastic changes. A Lyapunov-based argument is presented for the asymptotic convergence of the system that shows the process's stability and convergence to desired state values. To validate the controller, numerical simulations involving two different deformation models are conducted, and performances of the proposed algorithm are investigated through full-scale experiments.
In robotic grinding tasks, the robot controller must reactively adapt to sudden changes in the en... more In robotic grinding tasks, the robot controller must reactively adapt to sudden changes in the environment and be able to handle uncertainties in texture, change in materials, and disturbances caused by vibrations, impacts and friction of the grinding tool operating at high rotational speed. This requires managing sudden signal changes in sensor data. In this paper, we present a smooth hybrid force/position controller based on distance measurements from radars, enabling the robot to achieve a stable interaction with the environment while grinding an unknown three-dimensional surface. The control uses an actively compliant wrist that maintains a desired force centered on the disc and normal to the surface. Our controller is based on a smooth transition between free space and contact modes, significantly reducing the impact force. Additionally, the vibro-dynamic effects are suppressed and smooth environmental tracking is ensured by the impedance/admittance control of the wrist. This framework is validated on a 6-dof anthropomorphic arm through dynamic simulation. The controller is able to adapt reactively to abrupt disturbances in the environment (ex: sudden impacts on the disc) while ensuring good position and force tracking performance.
Uploads
Papers by Juan Antonio Corrales Ramon