Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

AI-enabled digital twin framework for reconfigurable robotic palletizing of irregularly shaped products

  • Theodoropoulos, Nikolaos
  • Castro Torres, Andres Felipe
  • Tragianni, Stella Dimitra
  • Andronas, Dionisis
  • Zaplana Agut, Isiah|||0000-0002-0862-3240
  • Ayan, Bengisu
  • Suárez Feijóo, Raúl|||0000-0002-3853-7095
  • Suppa, Michael
  • Makris, Sotiris
Palletizing in intralogistics and manufacturing remains particularly challenging when dealing with irregularly shaped products, large variant sets, and frequently changing customer orders. This paper presents an AI-enabled digital twin framework for reconfigurable robotic palletizing of irregularly shaped products. At its core, the framework uses a digital twin that maintains a unified representation of the robotic cell, its resources, and the handled products, and exposes consistent information to all software modules, enabling their interoperation. The palletizing pipeline integrates key enabling technologies to answer how products should be handled, where they are located in the workspace, and how they should be stacked at the output station. First, geometry-based preprocessing and an analytical grasping procedure extract key attributes and grasp points for each product type and store them in a knowledge base. Second, a perception module combines deep learning–based instance segmentation with template matching to identify and localize aluminium profiles that arrive in mixed, colour-oriented stacks without explicit identifiers. Third, a pallet loading optimizer employs a deep reinforcement learning–assisted selector, a constraint satisfaction stage, and a multi-criteria placement evaluation to generate near-optimal stacking configurations that satisfy stability and handling constraints. The digital twin mediates the exchange of this information across the participating enabling technologies, serving as a single source of truth and dispatching the solution execution components responsible for materializing the generated palletizing plan. The framework is deployed and validated in an industrial aluminium extrusion packaging use case using a dual-arm robotic palletizing cell, illustrating a viable path toward reconfigurable automation of irregular product palletizing in intralogistics and manufacturing environments., Open access funding provided by HEAL-Link Greece. This manuscript has been partially supported by the Project “SMARTHANDLE – Resilient manufacturing lines based on smart handling systems,” funded by the European Commission under the Horizon Europe Research and Innovation Programme (HORIZON-CL4-2022-TWINTRANSITION-01-04) with grant agreement ID: 101091792., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Automated depth dataset generation with integrated quality metrics for robotic manipulation

  • Dalmases, Albert
  • Ruiz Celada, Oriol|||0000-0002-6171-7270
  • Rosell Gratacòs, Jan|||0000-0003-4854-2370
  • Zaplana Agut, Isiah|||0000-0002-0862-3240
This work introduces a fully automatic and adaptable pipeline for synthetic depth dataset generation that later on can be used for the training of deep learning algorithms for robotic manipulation. From any available set of 3D object model meshes, the pipeline outputs rendered depth image data with labeled grasp candidates represented as a set of grasping points relative to the camera with associated metrics. The proposed pipeline allows adaptability in various characteristics such as the input dataset of objects, the sampling method, the gripper type, or the grasp evaluation metrics to allow the generation of a more customized, task-oriented collection of labeled grasps relevant for different robotic applications. The implementation is done using Blender’s Python API workspace, avoiding the use of multiple software tools or libraries, reducing the pipeline complexity, facilitating the extensibility, and providing benefits in terms of visualization and debugging., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Capítulo o parte de un libro (BookPart)

Closed-form inverse kinematics solutions for a class of serial robots without spherical wrist using conformal geometric algebra

  • Marzabal Gatell, Arnau
  • Zaplana Agut, Isiah|||0000-0002-0862-3240
One of the most well-known applications of geometric algebra in engineering is providing a compact formulation of the kinematics of serial robotic manipulators. However, the use of geometric algebra in the field of robotics is still in its early stages, and there are still several open problems that can be addressed with this elegant and compact formulation. In this context, this work introduces a strategy based on conformal geometric algebra to solve the inverse kinematics problem for a class of 6DOF serial robots without a spherical wrist, for which it is known that the inverse kinematics problem generally does not have an analytical solution. To achieve this, a purely geometric strategy extending already existing contributions for the case where the robot has a spherical wrist is proposed. In particular, a point is assigned to each joint of the robot so that the problem reduces to computing the set of all possible joint positions for a given desired position and orientation of its end-effector. These points are found by defining and manipulating several geometric entities such as lines, planes, and spheres. Finally, validation with a real robot of the considered class is demonstrated both in simulation and experimentation., This work was partially supported by the European Commission’s Horizon Europe Framework Programme with the project Smarthandle (Resilient manufacturing lines based on smart handling systems) under Grant Agreement 101091792, and the Spanish Government through the project CaRo (Capacidades Intr´ınsecas para Robots Co-trabajadores) under Grant Agreement PID2020-114819GB-I00., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Automated depth dataset generation with integrated quality metrics for robotic manipulation

  • Dalmases, Albert
  • Ruiz Celada, Oriol
  • Rosell Gratacòs, Jan
  • Zaplana Agut, Isiah
This work introduces a fully automatic and adaptable pipeline for synthetic depth dataset generation that later on can be used for the training of deep learning algorithms for robotic manipulation. From any available set of 3D object model meshes, the pipeline outputs rendered depth image data with labeled grasp candidates represented as a set of grasping points relative to the camera with associated metrics. The proposed pipeline allows adaptability in various characteristics such as the input dataset of objects, the sampling method, the gripper type, or the grasp evaluation metrics to allow the generation of a more customized, task-oriented collection of labeled grasps relevant for different robotic applications. The implementation is done using Blender’s Python API workspace, avoiding the use of multiple software tools or libraries, reducing the pipeline complexity, facilitating the extensibility, and providing benefits in terms of visualization and debugging., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

AI-enabled digital twin framework for reconfigurable robotic palletizing of irregularly shaped products

  • Theodoropoulos, Nikolaos
  • Castro Torres, Andres Felipe
  • Tragianni, Stella Dimitra
  • Andronas, Dionisis
  • Zaplana Agut, Isiah
  • Ayan, Bengisu
  • Suárez Feijóo, Raúl
  • Suppa, Michael
  • Makris, Sotiris
Palletizing in intralogistics and manufacturing remains particularly challenging when dealing with irregularly shaped products, large variant sets, and frequently changing customer orders. This paper presents an AI-enabled digital twin framework for reconfigurable robotic palletizing of irregularly shaped products. At its core, the framework uses a digital twin that maintains a unified representation of the robotic cell, its resources, and the handled products, and exposes consistent information to all software modules, enabling their interoperation. The palletizing pipeline integrates key enabling technologies to answer how products should be handled, where they are located in the workspace, and how they should be stacked at the output station. First, geometry-based preprocessing and an analytical grasping procedure extract key attributes and grasp points for each product type and store them in a knowledge base. Second, a perception module combines deep learning–based instance segmentation with template matching to identify and localize aluminium profiles that arrive in mixed, colour-oriented stacks without explicit identifiers. Third, a pallet loading optimizer employs a deep reinforcement learning–assisted selector, a constraint satisfaction stage, and a multi-criteria placement evaluation to generate near-optimal stacking configurations that satisfy stability and handling constraints. The digital twin mediates the exchange of this information across the participating enabling technologies, serving as a single source of truth and dispatching the solution execution components responsible for materializing the generated palletizing plan. The framework is deployed and validated in an industrial aluminium extrusion packaging use case using a dual-arm robotic palletizing cell, illustrating a viable path toward reconfigurable automation of irregular product palletizing in intralogistics and manufacturing environments., Open access funding provided by HEAL-Link Greece. This manuscript has been partially supported by the Project “SMARTHANDLE – Resilient manufacturing lines based on smart handling systems,” funded by the European Commission under the Horizon Europe Research and Innovation Programme (HORIZON-CL4-2022-TWINTRANSITION-01-04) with grant agreement ID: 101091792., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication

Closed-form inverse kinematics solutions for a class of serial robots without spherical wrist using conformal geometric algebra

  • Marzabal Gatell, Arnau
  • Zaplana Agut, Isiah
One of the most well-known applications of geometric algebra in engineering is providing a compact formulation of the kinematics of serial robotic manipulators. However, the use of geometric algebra in the field of robotics is still in its early stages, and there are still several open problems that can be addressed with this elegant and compact formulation. In this context, this work introduces a strategy based on conformal geometric algebra to solve the inverse kinematics problem for a class of 6DOF serial robots without a spherical wrist, for which it is known that the inverse kinematics problem generally does not have an analytical solution. To achieve this, a purely geometric strategy extending already existing contributions for the case where the robot has a spherical wrist is proposed. In particular, a point is assigned to each joint of the robot so that the problem reduces to computing the set of all possible joint positions for a given desired position and orientation of its end-effector. These points are found by defining and manipulating several geometric entities such as lines, planes, and spheres. Finally, validation with a real robot of the considered class is demonstrated both in simulation and experimentation., This work was partially supported by the European Commission’s Horizon Europe Framework Programme with the project Smarthandle (Resilient manufacturing lines based on smart handling systems) under Grant Agreement 101091792, and the Spanish Government through the project CaRo (Capacidades Intr´ınsecas para Robots Co-trabajadores) under Grant Agreement PID2020-114819GB-I00., Peer Reviewed, Postprint (author's final draft)