Skip to main content

ROBOTS AUTONOMOS DIESTROS COMO CO-TRABAJADORES CON OPERADORES HUMANOS

DPI2016-80077-R

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2016
State Plan 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Manipulación de objetos desconocidos analizando localmente su forma para optimizar las fuerzas de prensión

  • Montaño Sarria, Andrés Felipe
  • Suárez Feijóo, Raúl
Los enfoques propuestos para la manipulación de objetos se basan, generalmente, en el conocimiento de las características del objeto manipulado. En este trabajo se presenta un enfoque geométrico que permite manipular un objeto desconocido basándose únicamente en información cinemática y táctil. Los datos de los sensores táctiles y los valores articulares del robot, que se obtienen durante la manipulación, se usan para reconocer la forma del objeto (al menos la curvatura local de la superficie en contacto durante la manipulación), buscando optimizar las fuerzas de contacto. El enfoque propuesto ha sido implementado y probado usando la mano robótica Schunk Dexterous Hand (SDH2). Los resultados experimentales presentados muestran la validez del enfoque, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Neural cellular automata manifold

  • Hernández Ruiz, Alejandro José
  • Vilalta Arias, Armand
  • Moreno-Noguer, Francesc
Very recently, the Neural Cellular Automata (NCA) has been proposed to simulate the morphogenesis process with deep networks. NCA learns to grow an image starting from a fixed single pixel. In this work, we show that the neural network (NN) architecture of the NCA can be encapsulated in a larger NN. This allows us to propose a new model that encodes a manifold of NCA, each of them capable of generating a distinct image. Therefore, we are effectively learning an embedding space of CA, which shows generalization capabilities. We accomplish this by introducing dynamic convolutions inside an Auto-Encoder architecture, for the first time used to join two different sources of information, the encoding and cell's environment information. In biological terms, our approach would play the role of the transcription factors, modulating the mapping of genes into specific proteins that drive cellular differentiation, which occurs right before the morphogenesis. We thoroughly evaluate our approach in a dataset of synthetic emojis and also in real images of CIFAR-10. Our model introduces a general-purpose network, which can be used in a broad range of problems beyond image generation., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Knowledge-Oriented Physics-Based Motion Planning for Grasping Under Uncertainty

  • Ud Din, Muhayy
  • Akbari, Aliakbar
  • Rosell Gratacòs, Jan
Grasping an object in unstructured and uncertain environments is a challenging task, particularly when a collision-free trajectory does not exits. High-level knowledge and reasoning processes, as well as the allowing of interaction between objects, can enhance the planning efficiency in such environments. In this direction, this study proposes a knowledge-oriented physics-based motion planning approach for a hand-arm system that uses a high-level knowledge-based reasoning to partition the workspace into regions to both guide the planner and reason about the result of the dynamical interactions between rigid bodies. The proposed planner is a kinodynamic RRT that uses a region-biased state sampling strategy and a smart validity checker that takes into account uncertainty in the pose of the objects. Complex dynamical interactions along with possible physics-based constraints such as friction and gravity are handled by a physics engine that is used as the RRT state propagator. The proposal is validated for different scenarios in simulation and in a real environment using a 7-degree-of-freedom KUKA Lightweight robot equipped with a two-finger gripper. The results show a significant improvement in the success rate of the execution of the computed plan in the presence of object pose uncertainty., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Learning Action-oriented grasping for manipulation

  • Ud Din, Muhayy
  • Sarwar, M Usman
  • Zahoor, Imran
  • Qazi, Wajahat Mahmood
  • Rosell Gratacòs, Jan
Complex manipulation tasks require grasping strategies that simultaneously satisfy the stability and the semantic constraints that have to be satisfied for an action to be feasible, referred as action-oriented semantic grasp strategies. This study develops a framework using machine learning techniques to compute action-oriented semantic grasps. It takes a 3D model of the object and the action to be performed as input and provides a vector of action-oriented semantic grasps. We evaluate the performance of machine learning (particu- larly classification techniques) to determine which approaches perform better for this problem. Using the best approaches, a multi-model classification technique is developed. The proposed approach is evaluated in simulation to grasp different kitchenobjects using a parallel gripper. The results show that multi-model classification approach enhances the prediction accuracy. The implemented system can be used as to automate the data labeling process required for deep learning approaches., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Model-free in-hand manipulation based on commanded virtual contact points

  • Montaño Sarria, Andrés Felipe
  • Suárez Feijóo, Raúl
This paper presents a simple strategy to allow therotation of unknown objects using a robotic hand equipped withtactile sensors. The tactile and kinematic information, obtainedwhile that the object is manipulated, is used to determinethe hand configurations that change the object position. Theapproach was successfully tested using an anthropomorphicrobotic hand (Allegro Hand), with the fingertips modified toinclude tactile sensors (WTS-FT). Using three fingers of the hand,every-day objects were successfully rotated without using theirmodel for the determination of the hand movement, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Physics-based Motion Planning with Temporal Logic Specifications

  • Ud Din, Muhayy
  • Akbari, Aliakbar
  • Rosell Gratacòs, Jan
The final version of this work is available at https://doi.org/10.1016/j.ifacol.2017.08.1578 Copyright of all papers belongs to IFAC and must be referenced if derivative journal papers are produced from the conference papers., One of the main foci of robotics is nowadays centered in providing a great degree of autonomy to robots. A fundamental step in this direction is to give them the ability to plan in discrete and continuous spaces to find the required motions to complete a complex task. In this line, some recent approaches describe tasks with Linear Temporal Logic (LTL) and reason on discrete actions to guide sampling-based motion planning, with the aim of finding dynamically-feasible motions that satisfy the temporal-logic task specifications. The present paper proposes an LTL planning approach enhanced with the use of ontologies to describe and reason about the task, on the one hand, and that includes physics-based motion planning to allow the purposeful manipulation of objects, on the other hand. The proposal has been implemented and is illustrated with didactic examples with a mobile robot in simple scenarios where some of the goals are occupied with objects that must be removed in order to fulfill the task., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Simulation of virtual human hand evolution after stroke

  • Peña Pitarch, Esteve
  • Ticó Falguera, Neus
Different types of neurological deficits and sequels in the upper extremities that affect the activities of daily living (ADL) in patients who have undergone stroke have been analyzed from a subjective clinical point of view. The aim of this work is to show a novel environment to simulate the initial improvement of the upper limb functions a few days after stroke and simulate the functional recovery of patients under a rehabilitation program. Eighteen patients in the first seven days of stroke were selected. Five men and thirteen women participated in the experiments. After six months, six of them recovered all the functionality of the hand tested with the ARAT test and wearing a Ciberglobe system, five recovered part of the hand functionality, and seven did not show apparent recovery of the functionality of the hand., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Diseño de una prótesis de mano adaptable al crecimiento

  • Ayats, Marta
  • Suárez Feijóo, Raúl
En este artículo se presenta el diseño de una prótesis de mano que se adapta al crecimiento del usuario, desde los 4 años hasta la edad adulta. Se ha considerado en el diseño el estudio de las necesidades de los pacientes y el estudio de las medidas antropométricas de los usuarios en la edad de crecimiento. El diseño incluye únicamente la estructura externa y los mecanismos de movimiento, así pues no se ha incluido en este trabajo el diseño del control ni de la electrónica, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Grasp quality measures for transferring objects

  • Soler, Fernando
  • Rojas-de-Silva, Abiud
  • Suárez Feijóo, Raúl
There is a lack of quality indexes to evaluate grasps that are more likely to allow a hand-to-hand transfer of an object during a ma- nipulation task. In order to overcome it, this paper presents a proposal of grasp transfer quality measures to evaluate how easy or feasible is that an object grasped by one hand could be grasped by another hand to per- form a hand-to-hand transfer. Experiments were conducted to evaluate the proposed grasp transfer quality measures using different objects and the model of a real robotic hand, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

A lightweight perception module for planning purposes

  • Ud Din, Muhayy
  • Rosell Gratacòs, Jan
  • Bukhari, Sohail
  • Ahmad, Mansoor
  • Qazi, Wajahat Mahmood
© 2020 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, Sensing is an essential component for robots to perform the manipulation tasks in real environments. This study proposes a lightweight deep-learning-based sensing modules which allows the robots to automatically model the workspace for manipulation planning. This sensing module is developed as a part of our ongoing manipulation planning framework. It will be used to enhance the sensing accuracy and make it capable of planning the manipulation tasks in real environments. The retrained model is further trained over commonly used objects to enhance the prediction accuracy., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Modeling human-likeness in approaching motions of dual-arm autonomous robots

  • Rosell Gratacòs, Jan
  • Suárez Feijóo, Raúl
  • García Hidalgo, Néstor
© 2018 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, This paper addresses the problem of obtaining human-like motions with an anthropomorphic dual-arm torso assembled on a mobile platform. The focus is set on the coordinated movements of the robotic arms and the robot base while approaching a table to subsequently perform a bimanual manipulation task. For this, human movements are captured and mapped to the robot in order to compute the human dual-arm synergies. Since the demonstrated synergies change depending on the robot position, a recursive Cartesian-space discretization is presented based on these differences. Thereby, different movements of the arms are assigned to different regions of the Cartesian space. As an application example, a motion-planning algorithm exploiting this information is proposed and used., Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Bilateral telemanipulation of unknown objects using remote dexterous in-hand manipulation strategies

  • Montaño Sarria, Andrés Felipe
  • Suárez Feijóo, Raúl
  • Aldana López, Carlos Iván
  • Nuño, Emmanuel
This paper presents an approach to perform bilateral in-hand (dexterous) telemanipulation of unknown objects. The proposed approach addresses three of the main problems in telemanipulation: \eno{kinematic issues due to the physical differences between the robotic and the human hands;} obtaining coherent haptic feedback to provide information about the manipulation at any time; and time-delays that can affect the stability of the overall closed-loop system. The novelty of the approach lays on the shared control scheme, where the robotic hand uses the tactile and \eno{the} kinematic information to manipulate an unknown object while the operator commands \eno{a} desired orientation of the object without caring about the relation between her/his commands and the actual hand movements. The viability of the proposed approach has been tested through transatlantic telemanipulation experiments between Mexico and Spain., Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

An Ontology Framework for Physics-Based Manipulation Planning

  • Diab, Mohammed
  • Ud Din, Muhayy
  • Akbari, Aliakbar
  • Rosell Gratacòs, Jan
In manipulation planning, dynamic interactions between the objects and the robots play a significant role. In this scope, dynamic engines allow to consider them within motion planners, giving rise to physics-based motion planners that consider the purposeful manipulation of objects. In this context, the representation of knowledge regarding how the objects have to be manipulated eases a semantic-based reasoning that reduces the computational cost of physics-based planners. In this work, an ontology framework is proposed to organize the knowledge needed for physics-based manipulation planning, allowing to derive manipulation regions and behaviors. A semantic map is constructed to categorize and assign the manipulation constraints based on the robot, the objects and the type of actions. The ontology framework can be queried using Description Language to obtain the necessary knowledge for the robot to manipulate the objects in its environment., Peer Reviewed, Postprint (author's final draft)