Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 17
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A Virtual Reality Framework For Fast Dataset Creation Applied to Cloth Manipulation with Automatic Semantic Labelling

  • Borràs, Julia
  • Boix-Granell, Arnau
  • Foix, Sergi
  • Torras, Carme
Trabajo presentado en la IEEE International Conference on Robotics and Automation (ICRA), celebrada en Londres (UK), del 29 de mayo al 2 de junio de 2024, Teaching complex manipulation skills, such as folding garments, to a bi-manual robot is a very challenging task, which is often tackled through learning from demon-stration. The few datasets of garment-folding demonstrations available nowadays to the robotics research community have been either gathered from human demonstrations or generated through simulation. The former have the great difficulty of perceiving both cloth state and human action as well as transferring them to the dynamic control of the robot, while the latter require coding human motion into the simulator in open loop, i.e., without incorporating the visual feedback naturally used by people, resulting in far-from-realistic movements. In this article, we present an accurate dataset of human cloth folding demonstrations. The dataset is collected through our novel virtual reality (VR) framework, based on Unity's 3D platform and the use of an HTC Vive Pro system. The framework is capable of simulating realistic garments while allowing users to interact with them in real time through handheld controllers. By doing so, and thanks to the immersive experience, our framework permits exploiting human visual feedback in the demonstrations while at the same time getting rid of the difficulties of capturing the state of cloth, thus simplifying data acquisition and resulting in more realistic demonstrations. We create and make public a dataset of cloth manipulation sequences, whose cloth states are semantically labeled in an automatic way by using a novel low-dimensional cloth representation that yields a very good separation between different cloth configurations., The research leading to these results receives funding from the European Research Council (ERC) from the European Union Horizon 2020 Programme under grant agreement no. 741930 (CLOTHILDE: CLOTH manIpulation Learning from DEmonstrations) and project SoftEnable (HORIZONCL4- 2021-DIGITAL-EMERGING-01-101070600). Authors also received funding from project CHLOE-GRAPH (PID2020-118649RB-I00) funded by MCIN/ AEI /10.13039/501100011033 and COHERENT (PCI2020-120718- 2) funded by MCIN/ AEI /10.13039/501100011033 and cofunded by the ”European Union NextGenerationEU/PRTR”., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Placing by Touching: An Empirical Study on the Importance of Tactile Sensing for Precise Object Placing

  • Lach, Luca
  • Funk, Niklas
  • Haschke, Robert
  • Lemaignan, Severin
  • Ritter, Helge Joachim
  • Peters, Jan
  • Chalvatzaki, Georgia
Trabajo presentado en el IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), celebrado en Detroit, MI (Estados Unidos), del 1 al 5 de octubre de 2023, This work deals with a practical everyday problem: stable object placement on flat surfaces starting from unknown initial poses. Common object-placing approaches require either complete scene specifications or extrinsic sensor measurements, e.g., cameras, that occasionally suffer from occlusions. We propose a novel approach for stable object placing that combines tactile feedback and proprioceptive sensing. We devise a neural architecture called PlaceNet that estimates a rotation matrix, resulting in a corrective gripper movement that aligns the object with the placing surface for the subsequent object manipulation. We compare models with different sensing modalities, such as force-torque, an external motion capture system, and two classical baseline models in real-world object placing tasks with different objects. The experimental evaluation of our placing policies with a set of unseen everyday objects reveals significant generalization of our proposed pipeline, suggesting that tactile sensing plays a vital role in the intrinsic understanding of robotic dexterous object manipulation. Code, models, and supplementary videos are available on https://sites.google.com/view/placing-by-touching., This work was supported by the European Union’s Horizon 2020 Marie Curie Actions under grant no. 813713 NeuTouch, the Horizon Europe research and innovation program under grant no. 101070600 SoftEnable, the DFG Emmy Noether Programme (CH 2676/1-1), the BMBF Project Sim4Dexterity, the BMBF Project Aristotle, and the AICO grant by the Nexplore/Hochtief Collaboration with TU Darmstadt., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Benchmarking the Sim-to-Real Gap in Cloth Manipulation

  • Blanco-Mulero, David
  • Barbany, Oriol
  • Alcan, Gokhan
  • Colomé, Adrià
  • Torras, Carme
  • Kyrki, Ville
Realistic physics engines play a crucial role for learning to manipulate deformable objects such as garments in simulation. By doing so, researchers can circumvent challenges such as sensing the deformation of the object in the real-world. In spite of the extensive use of simulations for this task, few works have evaluated the reality gap between deformable object simulators and real-world data. We present a benchmark dataset to evaluate the sim-to-real gap in cloth manipulation. The dataset is collected by performing a dynamic as well as a quasi-static cloth manipulation task involving contact with a rigid table. We use the dataset to evaluate the reality gap, computational time, and simulation stability of four popular deformable object simulators: MuJoCo, Bullet, Flex, and SOFA. Additionally, we discuss the benefits and drawbacks of each simulator. The benchmark dataset is open-source. Supplementary material, videos, and code, can be found at https://sites.google.com/view/cloth-sim2real-benchmark., This work was supported in part by Academy of Finland under Grant 317020, in part by Business Finland (decision 9249/31/2021), in part by EU’s H2020 Programme through the CLOTHILDE Project under Grant ERC-2016-ADG-741930, in part by EU’s Horizon Europe Programme through the SoftEnable Project under Grant Agreement 101070600, and in part by MCIN/AEI/10.13039/501100011033 through CHLOE-GRAPH Project under Grant PID2020-118649RB-I00., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Ethics of Social Robotics: Individual and Societal Concerns and Opportunities

  • Torras, Carme
Focus on the ethics of a given technology tends to lag far behind its development. This lag has been particularly acute in the case of artificial intelligence, whose accelerated deployment in a wide range of domains has triggered unprecedented attention on the risks and consequences for society at large, leading to a myriad of ethics regulations, which are difficult to coordinate and integrate due to their late appearance. The very nature of social robots forces their deployment to occur at a much slower pace, providing an opportunity for a profound reflection on ethics, which is already happening in multidisciplinary teams. This article provides a personal view of the ethics landscape, centered on the particularities of social robotics, with the main issues being ordered along two axes (individual and societal) and grouped into eight categories (human dignity, human autonomy, robot transparency, emotional bonding, privacy and safety, justice, freedom, and responsibility). This structure stems from the experience of developing and teaching a university course on ethics in social robotics, whose pedagogical materials are freely available., This work was partly supported by the European Research Council through the project CLOTHILDE (Cloth Manipulation Learning from Demonstrations; advanced grant agreement 741930) and by the European Union’s Horizon Europe program through the project SoftEnable (HORIZON-CL4-2021-DIGITAL-EMERGING-01-101070600)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Dynamic Manipulation of Deformable Objects using Imitation Learning with Adaptation to Hardware Constraints

  • Hannus, Eric
  • Le, Tran Nguyen
  • Blanco-Mulero, David
  • Kyrki, Ville
Imitation Learning (IL) is a promising paradigm for learning dynamic manipulation of deformable objects since it does not depend on difficult-to-create accurate simulations of such objects. However, the translation of motions demonstrated by a human to a robot is a challenge for IL, due to differences in the embodiments and the robot's physical limits. These limits are especially relevant in dynamic manipulation where high velocities and accelerations are typical. To address this problem, we propose a framework that first maps a dynamic demonstration into a motion that respects the robot's constraints using a constrained Dynamic Movement Primitive. Second, the resulting object state is further optimized by quasi-static refinement motions to optimize task performance metrics. This allows both efficiently altering the object state by dynamic motions and stable small-scale refinements. We evaluate the framework in the challenging task of bag opening, designing the system BILBO: Bimanual dynamic manipulation using Imitation Learning for Bag Opening. Our results show that BILBO can successfully open a wide range of crumpled bags, using a demonstration with a single bag. See supplementary material at https://sites.google.com/view/bilbo-bag., This work was financially supported by Business Finland (decision 9249/31/2021) and European Union’s Horizon Europe programme project SoftEnable (grant agreement No. 101070600)., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Zero-Shot Transfer of a Tactile-based Continuous Force Control Policy from Simulation to Robot

  • Lach, Luca
  • Haschke, Robert
  • Tateo, Davide
  • Peters, Jan
  • Ritter, Helge
  • Borràs, Julia
  • Torras, Carme
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is grasp force control, which aims to manipulate objects safely by limiting the amount of force exerted on the object. While prior works have either hand-modeled their force controllers, employed model-based approaches, or not shown sim-to-real transfer, we propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning. We, therefore, present a simulation environment that produces realistic normal forces, which we use to train continuous force control policies. A detailed evaluation shows that the learned policy performs similarly or better than a hand-crafted baseline. Ablation studies prove that the proposed inductive bias and domain randomization facilitate sim-to-real transfer. Code, models, and supplementary videos are available on https://sites.google.com/view/rl-force-ctrl, This work was supported by the European Union’s Horizon 2020 Marie Curie Actions under grant no. 813713 NeuTouch and the Horizon Europe research and innovation program under grant no. 101070600 SoftEnable., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Unfolding the Literature: A Review of Robotic Cloth Manipulation

  • Longhini, Alberta
  • Wang, Yufei
  • Garcia-Camacho, Irene
  • Blanco-Mulero, David
  • Moletta, Marco
  • Welle, Michael
  • Alenyà, Guillem
  • Yin, Hang
  • Erickson, Zackory
  • Held, David
  • Borràs, Julia
  • Kragic, Danica
The realm of textiles spans clothing, households, healthcare, sports, and industrial applications. The deformable nature of these objects poses unique challenges that prior work on rigid objects cannot fully address. The increasing interest within the community in textile perception and manipulation has led to new methods that aim to address challenges in modeling, perception, and control, resulting in significant progress. However, this progress is often tailored to one specific textile or a subcategory of these textiles. To understand what restricts these methods and hinders current approaches from generalizing to a broader range of real-world textiles, this review provides an overview of the field, focusing specifically on how and to what extent textile variations are addressed in modeling, perception, benchmarking, and manipulation of textiles. We conclude by identifying key open problems and outlining grand challenges that will drive future advancements in the field., This work was supported by the European Research Council (ERC-BIRD); the European Union’s Horizon Europe program through projects SoftEnable (HORIZON-CL4-2021-DIGITALEMERGING-01-101070600) and IRE (HORIZON-CL4-2023-DIGITAL-EMERGING-01- 101135082); the Swedish Research Council, the Knut and Alice Wallenberg Foundation, and the National Science Foundation under NSF CAREER grant IIS-2046491; and the project ROBIN PLEC2021-007859 funded by MCIN/AEI/10.13039/501100011033 and by European Union NextGenerationEU/PRTR., Peer reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Ethics of social robotics: individual and societal concerns and opportunities

  • Torras, Carme|||0000-0002-2933-398X
© 2024 by the author(s). This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. See credit lines of images or other third-party material in this article for license information., Focus on the ethics of a given technology tends to lag far behind its development. This lag has been particularly acute in the case of artificial intelligence, whose accelerated deployment in a wide range of domains has triggered unprecedented attention on the risks and consequences for society at large, leading to a myriad of ethics regulations, which are difficult to coordinate and integrate due to their late appearance. The very nature of social robots forces their deployment to occur at a much slower pace, providing an opportunity for a profound reflection on ethics, which is already happening in multidisciplinary teams. This article provides a personal view of the ethics landscape, centered on the particularities of social robotics, with the main issues being ordered along two axes (individual and societal) and grouped into eight categories (human dignity, human autonomy, robot transparency, emotional bonding, privacy and safety, justice, freedom, and responsibility). This structure stems from the experience of developing and teaching a university course on ethics in social robotics, whose pedagogical materials are freely available., This work was partly supported by the European Research Council through the project CLOTHILDE (Cloth Manipulation Learning from Demonstrations; advanced grant agreement 741930) and by the European Union's Horizon Europe program through the project SoftEnable (HORIZON-CL4-2021-DIGITAL-EMERGING-01-101070600)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

A virtual reality framework for fast dataset creation applied to cloth manipulation with automatic semantic labelling

  • Borràs Sol, Júlia|||0000-0002-1662-2037
  • Boix Granell, Arnau
  • Foix Salmerón, Sergi|||0000-0001-9249-6696
  • Torras, Carme|||0000-0002-2933-398X
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Teaching complex manipulation skills, such as folding garments, to a bi-manual robot is a very challenging task, which is often tackled through learning from demonstration. The few datasets of garment-folding demonstrations available nowadays to the robotics research community have been either gathered from human demonstrations or generated through simulation. The former have the great difficulty of perceiving both cloth state and human action as well as transferring them to the dynamic control of the robot, while the latter require coding human motion into the simulator in open loop, i.e., without incorporating the visual feedback naturally used by people, resulting in far-from-realistic movements. In this article, we present an accurate dataset of human cloth folding demonstrations. The dataset is collected through our novel virtual reality (VR) framework, based on Unity’s 3D platform and the use of an HTC Vive Pro system. The framework is capable of simulating realistic garments while allowing users to interact with them in real time through handheld controllers. By doing so, and thanks to the immersive experience, our framework permits exploiting human visual feedback in the demonstrations while at the same time getting rid of the difficulties of capturing the state of cloth, thus simplifying data acquisition and resulting in more realistic demonstrations. We create and make public a dataset of cloth manipulation sequences, whose cloth states are semantically labeled in an automatic way by using a novel low-dimensional cloth representation that yields a very good separation between different cloth configurations., The research leading to these results receives funding from the European Research Council (ERC) from the European Union Horizon 2020 Programme under grant agreement no. 741930 (CLOTHILDE: CLOTH manIpulation Learning from DEmonstrations) and project SoftEnable (HORIZONCL4-2021-DIGITAL-EMERGING-01-101070600). Authors also received funding from project CHLOE-GRAPH (PID2020-118649RB-I00) funded by MCIN/ AEI /10.13039/501100011033 and COHERENT (PCI2020-120718-2) funded by MCIN/ AEI /10.13039/501100011033 and cofunded by the ”European Union NextGenerationEU/PRTR”., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

Unfolding the literature: a review of robotic cloth manipulation

  • Longhini, Alberta
  • Wang, Yufei
  • Garcia Camacho, Irene|||0000-0002-1210-7345
  • Blanco Mulero, David|||0000-0003-1866-2144
  • Moletta, Marco
  • Welle, Michael C.
  • Alenyà Ribas, Guillem|||0000-0002-6018-154X
  • Yin, Hang
  • Erickson, Zackory
  • Held, David
  • Borràs Sol, Júlia|||0000-0002-1662-2037
  • Kragic, Danica
The realm of textiles spans clothing, households, healthcare, sports, and industrial applications. The deformable nature of these objects poses unique challenges that prior work on rigid objects cannot fully address. The increasing interest within the community in textile perception and manipulation has led to new methods that aim to address challenges in modeling, perception, and control, resulting in significant progress. However, this progress is often tailored to one specific textile or a subcategory of these textiles. To understand what restricts these methods and hinders current approaches from generalizing to a broader range of real-world textiles, this review provides an overview of the field, focusing specifically on how and to what extent textile variations are addressed in modeling, perception, benchmarking, and manipulation of textiles. We conclude by identifying key open problems and outlining grand challenges that will drive future advancements in the field., This work was supported by the European Research Council (ERC-BIRD); the European Union’s Horizon Europe program through projects SoftEnable (HORIZON-CL4-2021-DIGITALEMERGING-01-101070600) and IRE (HORIZON-CL4-2023-DIGITAL-EMERGING-01- 101135082); the Swedish Research Council, the Knut and Alice Wallenberg Foundation, and the National Science Foundation under NSF CAREER grant IIS-2046491; and the project ROBIN PLEC2021-007859 funded by MCIN/AEI/10.13039/501100011033 and by European Union NextGenerationEU/PRTR., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Evaluating the pre-dressing step: unfolding medical garments via imitation learning

  • Blanco Mulero, David|||0000-0003-1866-2144
  • Borràs Sol, Júlia|||0000-0002-1662-2037
  • Torras, Carme|||0000-0002-2933-398X
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Robotic-assisted dressing has the potential to significantly aid both patients as well as healthcare personnel, reducing the workload and improving the efficiency in clinical settings. While substantial progress has been made in robotic dressing assistance, prior works typically assume that garments are already unfolded and ready for use. However, in medical applications gowns and aprons are often stored in a folded configuration, requiring an additional unfolding step. In this paper, we introduce the pre-dressing step, the process of unfolding garments prior to assisted dressing. We leverage imitation learning for learning three manipulation primitives, including both high and low acceleration motions. In addition, we employ a visual classifier to categorise the garment state as closed, partly opened, and fully opened. We conduct an empirical evaluation of the learned manipulation primitives as well as their combinations. Our results show that highly dynamic motions are not effective for unfolding freshly unpacked garments, where the combination of motions can efficiently enhance the opening configuration., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Towards transferring tactile-based continuous force control policies from simulation to robot

  • Lach, Luca Michael
  • Haschke, Robert
  • Tateo, Davide
  • Peters, Jan
  • Ritter, Helge
  • Borràs Sol, Júlia|||0000-0002-1662-2037
  • Torras, Carme|||0000-0002-2933-398X
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is that of grasp force control, which aims to manipulate objects safely by limiting the amount of force exerted on the object. While prior works have either hand-modeled their force controllers, employed model-based approaches, or have not shown sim- to-real transfer, we propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning. We therefore present a simulation environment that produces realistic normal forces, which we use to train continuous force control policies. An evaluation in which we compare against a baseline and perform an ablation study shows that our approach outperforms the hand-modeled baseline and that our proposed inductive bias and domain randomization facilitate sim-to-real transfer. Code, models, and supplementary videos are available on https://sites.google. com/view/rl-force-ctrl, This work was supported by the European Union’s Horizon 2020 Marie Curie Actions under grant no. 813713 NeuTouch, the Horizon Europe research and innovation program under grant no. 101070600 SoftEnable, the German Research Center for AI (DFKI), and Hessian.AI. Research presented in this paper has been supported by the German Federal Ministry of Education and Research (BMBF) within the collaborative KIARA project (grant no. 13N16274).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A virtual reality framework for fast dataset creation applied to cloth manipulation with automatic semantic labelling

  • Borràs Sol, Júlia
  • Boix Granell, Arnau
  • Foix Salmerón, Sergi
  • Torras, Carme
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Teaching complex manipulation skills, such as folding garments, to a bi-manual robot is a very challenging task, which is often tackled through learning from demonstration. The few datasets of garment-folding demonstrations available nowadays to the robotics research community have been either gathered from human demonstrations or generated through simulation. The former have the great difficulty of perceiving both cloth state and human action as well as transferring them to the dynamic control of the robot, while the latter require coding human motion into the simulator in open loop, i.e., without incorporating the visual feedback naturally used by people, resulting in far-from-realistic movements. In this article, we present an accurate dataset of human cloth folding demonstrations. The dataset is collected through our novel virtual reality (VR) framework, based on Unity’s 3D platform and the use of an HTC Vive Pro system. The framework is capable of simulating realistic garments while allowing users to interact with them in real time through handheld controllers. By doing so, and thanks to the immersive experience, our framework permits exploiting human visual feedback in the demonstrations while at the same time getting rid of the difficulties of capturing the state of cloth, thus simplifying data acquisition and resulting in more realistic demonstrations. We create and make public a dataset of cloth manipulation sequences, whose cloth states are semantically labeled in an automatic way by using a novel low-dimensional cloth representation that yields a very good separation between different cloth configurations., The research leading to these results receives funding from the European Research Council (ERC) from the European Union Horizon 2020 Programme under grant agreement no. 741930 (CLOTHILDE: CLOTH manIpulation Learning from DEmonstrations) and project SoftEnable (HORIZONCL4-2021-DIGITAL-EMERGING-01-101070600). Authors also received funding from project CHLOE-GRAPH (PID2020-118649RB-I00) funded by MCIN/ AEI /10.13039/501100011033 and COHERENT (PCI2020-120718-2) funded by MCIN/ AEI /10.13039/501100011033 and cofunded by the ”European Union NextGenerationEU/PRTR”., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Ethics of social robotics: individual and societal concerns and opportunities

  • Torras, Carme
© 2024 by the author(s). This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. See credit lines of images or other third-party material in this article for license information., Focus on the ethics of a given technology tends to lag far behind its development. This lag has been particularly acute in the case of artificial intelligence, whose accelerated deployment in a wide range of domains has triggered unprecedented attention on the risks and consequences for society at large, leading to a myriad of ethics regulations, which are difficult to coordinate and integrate due to their late appearance. The very nature of social robots forces their deployment to occur at a much slower pace, providing an opportunity for a profound reflection on ethics, which is already happening in multidisciplinary teams. This article provides a personal view of the ethics landscape, centered on the particularities of social robotics, with the main issues being ordered along two axes (individual and societal) and grouped into eight categories (human dignity, human autonomy, robot transparency, emotional bonding, privacy and safety, justice, freedom, and responsibility). This structure stems from the experience of developing and teaching a university course on ethics in social robotics, whose pedagogical materials are freely available., This work was partly supported by the European Research Council through the project CLOTHILDE (Cloth Manipulation Learning from Demonstrations; advanced grant agreement 741930) and by the European Union's Horizon Europe program through the project SoftEnable (HORIZON-CL4-2021-DIGITAL-EMERGING-01-101070600)., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Evaluating the pre-dressing step: unfolding medical garments via imitation learning

  • Blanco Mulero, David
  • Borràs Sol, Júlia
  • Torras, Carme
© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works., Robotic-assisted dressing has the potential to significantly aid both patients as well as healthcare personnel, reducing the workload and improving the efficiency in clinical settings. While substantial progress has been made in robotic dressing assistance, prior works typically assume that garments are already unfolded and ready for use. However, in medical applications gowns and aprons are often stored in a folded configuration, requiring an additional unfolding step. In this paper, we introduce the pre-dressing step, the process of unfolding garments prior to assisted dressing. We leverage imitation learning for learning three manipulation primitives, including both high and low acceleration motions. In addition, we employ a visual classifier to categorise the garment state as closed, partly opened, and fully opened. We conduct an empirical evaluation of the learned manipulation primitives as well as their combinations. Our results show that highly dynamic motions are not effective for unfolding freshly unpacked garments, where the combination of motions can efficiently enhance the opening configuration., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Unfolding the literature: a review of robotic cloth manipulation

  • Longhini, Alberta
  • Wang, Yufei
  • Garcia Camacho, Irene
  • Blanco Mulero, David
  • Moletta, Marco
  • Welle, Michael C.
  • Alenyà Ribas, Guillem
  • Yin, Hang
  • Erickson, Zackory
  • Held, David
  • Borràs Sol, Júlia
  • Kragic, Danica
The realm of textiles spans clothing, households, healthcare, sports, and industrial applications. The deformable nature of these objects poses unique challenges that prior work on rigid objects cannot fully address. The increasing interest within the community in textile perception and manipulation has led to new methods that aim to address challenges in modeling, perception, and control, resulting in significant progress. However, this progress is often tailored to one specific textile or a subcategory of these textiles. To understand what restricts these methods and hinders current approaches from generalizing to a broader range of real-world textiles, this review provides an overview of the field, focusing specifically on how and to what extent textile variations are addressed in modeling, perception, benchmarking, and manipulation of textiles. We conclude by identifying key open problems and outlining grand challenges that will drive future advancements in the field., This work was supported by the European Research Council (ERC-BIRD); the European Union’s Horizon Europe program through projects SoftEnable (HORIZON-CL4-2021-DIGITALEMERGING-01-101070600) and IRE (HORIZON-CL4-2023-DIGITAL-EMERGING-01- 101135082); the Swedish Research Council, the Knut and Alice Wallenberg Foundation, and the National Science Foundation under NSF CAREER grant IIS-2046491; and the project ROBIN PLEC2021-007859 funded by MCIN/AEI/10.13039/501100011033 and by European Union NextGenerationEU/PRTR., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Towards transferring tactile-based continuous force control policies from simulation to robot

  • Lach, Luca Michael
  • Haschke, Robert
  • Tateo, Davide
  • Peters, Jan
  • Ritter, Helge
  • Borràs Sol, Júlia
  • Torras, Carme
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is that of grasp force control, which aims to manipulate objects safely by limiting the amount of force exerted on the object. While prior works have either hand-modeled their force controllers, employed model-based approaches, or have not shown sim- to-real transfer, we propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning. We therefore present a simulation environment that produces realistic normal forces, which we use to train continuous force control policies. An evaluation in which we compare against a baseline and perform an ablation study shows that our approach outperforms the hand-modeled baseline and that our proposed inductive bias and domain randomization facilitate sim-to-real transfer. Code, models, and supplementary videos are available on https://sites.google. com/view/rl-force-ctrl, This work was supported by the European Union’s Horizon 2020 Marie Curie Actions under grant no. 813713 NeuTouch, the Horizon Europe research and innovation program under grant no. 101070600 SoftEnable, the German Research Center for AI (DFKI), and Hessian.AI. Research presented in this paper has been supported by the German Federal Ministry of Education and Research (BMBF) within the collaborative KIARA project (grant no. 13N16274)., Postprint (published version)