ACAna Calzada-Garcia

Ana Calzada-Garcia

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ana Calzada-Garcia has a total of 3 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Manipulación robótica mediante aprendizaje por refuerzo inverso con características basadas en trayectorias expertas

    by Francisco J. Naranjo-Campos, Juan G. Victores, Ana Calzada-García, Carlos Balaguer

    Los algoritmos de aprendizaje para manipulación robótica aún presentan desafíos en tareas con alta variabilidad y dimensionalidad. Entre ellos, el Aprendizaje por Refuerzo ha mostrado buenos resultados, pero está limitado por la definición de la función de recompensa. Por ello surgen los algoritmos de Aprendizaje por Refuerzo Inverso (IRL), que estiman la recompensa a partir de demostraciones de un experto. En este trabajo se propone y valida un enfoque de IRL basado en características extraídas de trayectorias expertas, aplicado a tareas de manipulación con el robot TIAGo++. Este método aprovecha las demostraciones para centrar la definición de las características en la zona del espacio de estados relevante para el experto, así como priorizar los estados finales cercanos al objetivo. Las tareas de manipulación seleccionadas fueron apilar bloques y abrir un armario. Se entrenaron en simulación y se transfirieron al robot real, demostrando la viabilidad y eficacia del enfoque tanto en la ejecución exitosa como en métricas de distancia respecto al experto.

  • Open Access

    Inverse Kinematics for Robotic Manipulators via Deep Neural Networks: Experiments and Results

    by Ana Calzada-Garcia, Juan G. Victores, Francisco J. Naranjo-Campos, Carlos Balaguer

    This paper explores the application of Deep Neural Networks (DNNs) to solve the Inverse Kinematics (IK) problem in robotic manipulators. The IK problem, crucial for ensuring precision in robotic movements, involves determining joint configurations for a manipulator to reach a desired position or orientation. Traditional methods, such as analytical and numerical approaches, have limitations, especially for redundant manipulators, or involve high computational costs. Recent advances in machine learning, particularly with DNNs, have shown promising results and seem fit for addressing these challenges. This study investigates several DNN architectures, namely Feed-Forward Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs), for solving the IK problem, using the TIAGo robotic arm with seven Degrees of Freedom (DOFs). Different training datasets, normalization techniques, and orientation representations are tested, and custom metrics are introduced to evaluate position and orientation errors. The performance of these models is compared, with a focus on curriculum learning to optimize training. The results demonstrate the potential of DNNs to efficiently solve the IK problem while avoiding issues such as singularities, competing with traditional methods in precision and speed.


  • Top Cited Papers
    Open Access

    A Review on Inverse Kinematics, Control and Planning for Robotic Manipulators With and Without Obstacles via Deep Neural Networks

    by Ana Calzada-Garcia, Juan G. Victores, Francisco J. Naranjo-Campos, Carlos Balaguer

    Robotic manipulators are highly valuable tools that have become widespread in the industry, as they can achieve great precision and velocity in pick and place as well as processing tasks. However, to unlock their complete potential, some problems such as inverse kinematics (IK) need to be solved: given a Cartesian target, a method is needed to find the right configuration for the robot to reach that point. Another issue that needs to be addressed when dealing with robotic manipulators is the obstacle avoidance problem. Workspaces are usually cluttered and the manipulator should be able to avoid colliding with objects that could damage it, as well as with itself. Two alternatives exist to do this: a controller can be designed that computes the best action for each moment given the manipulator’s state, or a sequence of movements can be planned to be executed by the robot. Classical approaches to all these problems, such as numeric or analytical methods, can produce precise results but take a high computation time and do not always converge. Learning-based methods have gained considerable attention in tackling the IK problem, as well as motion planning and control. These methods can reduce the computational cost and provide results for every situation avoiding singularities. This article presents a literature review of the advances made in the past five years in the use of Deep Neural Networks (DNN) for IK with regard to control and planning with and without obstacles for rigid robotic manipulators. The literature has been organized in several categories depending on the type of DNN used to solve the problem. The main contributions of each reference are reviewed and the best results are presented in summary tables.