https://hdl.handle.net/11000/418 2026-04-21T17:26:19Z https://hdl.handle.net/11000/39741 Título : Design of a Mobile Binary Parallel Robot that Exploits Nonsingular Transitions Autor : Peidró, Adrián; García-Martínez, Alberto; Marín, José María; Payá, Luis; Gil, Arturo; Reinoso, Óscar Resumen : Sliding-frame mobile robots used for autonomously inspecting metallic structures consist of two bodies connected by few joints. They move by alternately adhering one body to the structure while moving the other body to the next position. Slidingframe robots are simpler and offer safer adhesion than legged and wheeled robots, and their control can be simplified using binary actuators that adopt only two stable states. However, most existing sliding-frame robots require continuous actuators to reach targets with precision, since binary actuators impose steps of fixed length. To solve this, this paper presents a new sliding-frame robot consisting of two bodies connected through a 2RPR-PR kinematic chain driven by two binary actuators. The 2RPR-PR chain can perform nonsingular transitions, which is the ability of many parallel robots to switch between different poses corresponding to the same state of its actuators, without crossing singularities. Thanks to this, the poses reachable by the proposed robot are doubled, granting it a denser workspace and more accuracy than similar robots, using only two binary actuators. The feasibility of the proposed robot is shown through a prototype. 2026-04-15T07:13:33Z https://hdl.handle.net/11000/39740 Título : Redundant Manipulator Kinematics and Dynamics on Differentiable Manifolds Autor : Haug, Edward J.; Peidró, Adrián Resumen : A recently published treatment of nonredundant manipulator kinematics and dynamics on differentiable manifolds is extended to kinematically redundant manipulators. Analysis at the configuration level shows that forward kinematics and dynamics of redundant manipulators are identical to that for nonredundant manipulators. The manifold-based inverse kinematics formulation that is presented for redundant manipulators, in contrast, yields parameterizations of set-valued inverse kinematic mappings at the configuration level, where sharper results are obtained than those presented in the literature using velocity formulations. Explicit expressions are derived for set-valued inverse kinematic mappings for both serial and non-serial (called compound) kinematically redundant manipulators, as functions of vectors of arbitrary parameters. Parameterizations are presented for both manipulator regular configuration manifolds and self-motion manifolds, the latter comprised of sets of inputs that map into the same output. It is shown that kinematically redundant configuration manifolds and self-motion differentiable manifolds are distinctly different and play complementary roles in redundant manipulator kinematics. Computational methods are presented for evaluation of set-valued inverse kinematic mappings, without problem dependent ad-hoc analytical manipulations. Redundant serial and compound manipulator examples are presented to illustrate computation of set-valued inverse kinematic mappings and use of self-motion manifold mappings in obstacle avoidance applications. Differentiation of configuration level inverse mappings yields inverse velocity and acceleration mappings as functions of time dependent arbitrary parameters that play a central role in manipulator dynamics and control. 2026-04-15T07:08:01Z https://hdl.handle.net/11000/39739 Título : Topological and spatial analysis of self-motion manifolds for global redundancy resolution in kinematically redundant robots Autor : Fabregat-Jaén, Marc; Peidró, Adrián; Colombo, Matteo; Rocco, Paolo; Reinoso, Óscar Resumen : This paper introduces a novel framework for global redundancy resolution in kinematically redundant robots, which have more degrees of freedom than the dimensions required to complete their task. The method is based on the concept of self-motion manifolds (SMMs), which are subsets of the joint space where the robot can move without affecting the task. Given a task trajectory, a sequence of SMMs is generated by building a graph where each node represents a c-bundle, which are sets of SMMs that share the same topology. The graph is then explored to establish feasible paths, from which preliminary joint trajectories are derived. The joint trajectories undergo an iterative optimization process that moves each joint trajectory point along the SMM of the associated task instant. The method is capable of handling kinematic constraints, such as joint limits and collisions, and it is designed to be adaptable to the kinematic complexity of the robot, real-time requirements, or optimality. The effectiveness and global optimality of the method in solving redundancy is validated through simulations with different robots and degrees of redundancy. 2026-04-15T07:05:17Z https://hdl.handle.net/11000/38844 Título : Study of Qu-Based Resonant Microwave Sensors and Design of 3-D-Printed Devices Dedicated to Glucose Monitoring Autor : Juan, Carlos G.; Potelon, Benjamin; Quendo, Cédric; García-Martínez, Héctor; Ávila-Navarro, Ernesto; Bronchalo, Enrique; Sabater-Navarro, José María Resumen : A low-cost, additively manufactured, biocompatible glucose sensor based on the changes in the unloaded quality factor (Qu) with a single split-ring resonator is presented. An exposition of the fundamentals for the use of the Qu as sensing parameter with microwave planar resonant sensors is shown. The convenience of this sensing parameter is analyzed from the theoretical point of view, and practical design and optimization guidelines are inferred with a special focus on the optimization of Qu sensitivity to glucose concentration. For practical demonstration and experimental assessment, a novel inverted microstrip configuration is considered, built upon a customized structure made with a certified biocompatible material thanks to 3-D printing techniques, which is aimed to provide for a stronger interaction between the electromagnetic fields and the sample. Two metallization solutions are investigated, yielding devices operating at 4.50 and 4.62 GHz, with operating Qu of 16.36 and 22.00, relative Qu sensitivities of 1.377 and 2.727, Qu sensitivities to glucose content within the physiological range of 0.3 × 10−3 per mg/dL and 0.6 × 10−3 per mg/dL, sensing areas of approximately 11.7 × 8.8 mm2 and total structure sizes of 950.0 × 35.0 × 3.5 mm3. The devices show good performance with water–glucose solutions covering a wide range of concentrations, involving physiological as well as industry-related ones. Notas: Los derechos de autor de este artículo pertenecen al IEEE. El artículo se encuentra publicado en: https://ieeexplore.ieee.org/abstract/document/9585096 2026-01-12T11:35:37Z https://hdl.handle.net/11000/38843 Título : Neural Tract Avoidance Path-Planning Optimization: Robotic Neurosurgery Autor : Manrique-Cordoba, Juliana; Martorell, Carlos; Romero-Ante, Juan D.; Sabater-Navarro, José María Resumen : Background: We propose a three-dimensional path-planning method to generate optimized surgical trajectories for steering flexible needles along curved paths while avoiding critical tracts in the context of surgical glioma resection. Methods: Our approach is based on an application of the rapidly exploring random tree algorithm for multi-trajectory generation and optimization, with a cost function that evaluates different entry points and uses the information of MRI images as segmented binary maps to compute a safety trajectory. As a novelty, an avoidance module of the critical neuronal tracts defined by the neurosurgeon is included in the optimization process. The proposed strategy was simulated in real-case 3D environments to reach a glioma and bypass the tracts of the forceps minor from the corpus callosum. Results: A formalism is presented that allows for the evaluation of different entry points and trajectories and the avoidance of selected critical tracts for the definition of new neurosurgical approaches. This methodology can be used for different clinical cases, allowing the constraints to be extended to the trajectory generator. We present a clinical case of glioma at the base of the skull and access it from the upper area while avoiding the minor forceps tracts. Conclusions: This path-planning method offers alternative curved paths with which to reach targets using flexible tools. The method potentially leads to safer paths, as it permits the definition of groups of critical tracts to be avoided and the use of segmented binary maps from the MRI images to generate new surgical approaches. 2026-01-12T11:29:50Z https://hdl.handle.net/11000/38842 Título : N-Dimensional Reduction Algorithm for Learning from Demonstration Path Planning Autor : Manrique-Cordoba, Juliana; Casa-Lillo, Miguel Ángel de la; Sabater-Navarro, José María Resumen : This paper presents an n-dimensional reduction algorithm for Learning from Demonstration (LfD) for robotic path planning, addressing the complexity of highdimensional data. The method extends the Douglas–Peucker algorithm by incorporating velocity and orientation alongside position, enabling more precise trajectory simplification. A magnitude-based normalization process preserves proportional relationships across dimensions, and the reduced dataset is used to train Hidden Markov Models (HMMs), where continuous trajectories are discretized into identifier sequences. The algorithm is evaluated in 2D and 3D environments with datasets combining position and velocity. The results show that incorporating additional dimensions significantly enhances trajectory simplification while preserving key information. Additionally, the study highlights the importance of selecting appropriate encoding parameters to achieve optimal resolution. The HMM-based models generated new trajectories that retained the patterns of the original demonstrations, demonstrating the algorithm’s capacity to generalize learned behaviors for trajectory learning in high-dimensional spaces. 2026-01-12T11:28:13Z https://hdl.handle.net/11000/36844 Título : Methods for the Segmentation of Reticular Structures Using çD LiDAR Data: A Comparative Evaluation Autor : Soler Mora, Francisco J.; Peidró Vidal, Adrián; Fabregat-Jaén, Marcos; Payá Castelló, Luis; Reinoso García, Oscar Resumen : Reticular structures are the basis of major infrastructure projects, including bridges, electrical pylons and airports. However, inspecting and maintaining these structures is both expensive and hazardous, traditionally requiring human involvement.While some research has been conducted in this eld of study,most e orts focus on faults identi cation through images or the design of robotic platforms, o en neglecting the autonomous navigation of robots through the structure. is study addresses this limitation by proposing methods to detect navigable surfaces in truss structures, thereby enhancing the autonomous capabilities of climbing robots to navigate through these environments. e paper proposesmultiple approaches for the binary segmentation between navigable surfaces and background from çD point clouds captured frommetallic trusses. Approaches can be classi ed into two paradigms: analytical algorithms and deep learning methods. Within the analytical approach, an ad hoc algorithm is developed for segmenting the structures, leveraging di erent techniques to evaluate the eigendecomposition of planar patches within the point cloud. In parallel, widely used and advanced deep learning models, including PointNet, PointNet++, MinkUNetç¥C, and PointTransformerVç, are trained and evaluated for the same task. A comparative analysis of these paradigms reveals some key insights. e analytical algorithm demonstrates easier parameter adjustment and comparable performance to that of the deep learning models, despite the latter’s higher computational demands. Nevertheless, the deep learning models stand out in segmentation accuracy, with PointTransformerVç achieving impressive results, such as a Mean Intersection Over Union (mIoU) of approximately ÀÞ%. is study highlights the potential of analytical and deep learning approaches to improve the autonomous navigation of climbing robots in complex truss structures. e ndings underscore the trade-o s between computational e ciency and segmentation performance, o ering valuable insights for future research and practical applications in autonomous infrastructure maintenance and inspection. 2025-07-11T11:59:17Z https://hdl.handle.net/11000/36843 Título : Static Early Fusion Techniques for Visible and Thermal Images to Enhance Convolutional Neural Network Detection: A Performance Analysis Autor : Heredia-Aguado, Enrique; Cabrera, Juan José; Jiménez, Luis Miguel; Valiente, David; Gil, Arturo Resumen : This paper presents a comparison of different image fusion methods for matching visible-spectrum images with thermal-spectrum (far-infrared) images, aimed at enhancing person detection using convolutional neural networks (CNNs). While object detection with RGB images is a well-developed area, it is still greatly limited by lighting conditions. This limitation poses a significant challenge in image detection playing a larger role in everyday technology, where illumination cannot always be controlled. Far-infrared images (which are partially invariant to lighting conditions) can serve as a valuable complement to RGB images in environments where illumination cannot be controlled and robust object detection is needed. In this work, various early and middle fusion techniques are presented and compared using different multispectral datasets, with the aim of addressing these limitations and improving detection performance. 2025-07-11T11:57:12Z https://hdl.handle.net/11000/36842 Título : Detection of UAVs on a collision course using optical flow Autor : Cabrera, Juan José; Gil, Arturo; Payá, Luis; Santo, Antonio; Reinoso, Oscar; Rodríguez, David Resumen : This paper presents a method to detect, track and predict a potential collision with UAVs using an aircraft equipped with a single camera. The method analyses the movement in the camera’s image plane by means of sparse optical flow. In this way, the camera’s own movement can be modelled and cancelled by estimating a homography matrix from a set of corresponding points. Once the movement caused by the camera is cancelled other moving objects can be isolated and the presence of other UAVs can be detected. Additionally, the method predicts potential collisions by examining the alignment between the position and velocity vectors of the UAV, which are estimated up to a scale factor. The proposed method is effective at detecting and predicting collisions with UAVs, regardless of their appearance, size, or movement, making it useful for applications related to airspace security. 2025-07-11T11:56:26Z https://hdl.handle.net/11000/36841 Título : Triplet Neural Networks for the Visual Localization of Mobile Robots Autor : Alfaro, Marcos; Cabrera, Juan José; Jiménez, Luis Miguel; Reinoso, Óscar; Payá, Luis Resumen : Triplet networks are composed of three identical convolutional neural networks that function in parallel and share their weights. These architectures receive three inputs simultaneously and provide three different outputs, and have demonstrated to have a great potential to tackle visual localization. Therefore, this paper presents an exhaustive study of the main factors that influence the training of a triplet network, which are the choice of the triplet loss function, the selection of samples to include in the training triplets and the batch size. To do that, we have adapted and retrained a network with omnidirectional images, which have been captured in an indoor environment with a catadioptric camera and have been converted into a panoramic format. The experiments conducted demonstrate that triplet networks improve substantially the performance in the visual localization task. However, the right choice of the studied factors is of great importance to fully exploit the potential of such architectures 2025-07-11T11:54:16Z