Filters








195 Hits in 11.0 sec

Robot grasping in clutter: Using a hierarchy of supervisors for learning from demonstrations

Michael Laskey, Jonathan Lee, Caleb Chuck, David Gealy, Wesley Hsieh, Florian T. Pokorny, Anca D. Dragan, Ken Goldberg
2016 2016 IEEE International Conference on Automation Science and Engineering (CASE)  
Physical experiments suggest that with a fixed budget of 160 expert demonstrations, using the hierarchy of supervisors can increase the probability of a successful grasp (reliability) from 55% to 90%.  ...  To explore this idea, we introduce a version of the grasping in clutter problem where a yellow cylinder must be grasped by a planar robot arm amid extruded objects in a variety of shapes and positions.  ...  Furthermore, deep learning, which we use to learn policies directly from raw 1 1 : Three policy roll-outs on a Zymark 3-DOF Robot of a fully trained grasping in clutter policy (one per row, left to  ... 
doi:10.1109/coase.2016.7743488 dblp:conf/case/LaskeyLCGHPDG16 fatcat:u7bb7dlwrfdwnncrdnffnxmqbe

Visual Foresight Tree for Object Retrieval from Clutter with Nonprehensile Rearrangement [article]

Baichuan Huang, Shuai D. Han, Jingjin Yu, Abdeslam Boularias
2021 arXiv   pre-print
This paper considers the problem of retrieving an object from many tightly packed objects using a combination of robotic pushing and grasping actions.  ...  The tree search returns a sequence of consecutive push actions yielding the best arrangement of the clutter for grasping the target object.  ...  For example, a hierarchy of supervisors was used for learning to grasp objects in clutter from demonstrations [16] .  ... 
arXiv:2105.02857v2 fatcat:lfmfxh7e4navdnudnzak2oxt6i

Real-Time Online Re-Planning for Grasping Under Clutter and Uncertainty [article]

Wisdom C. Agboh, Mehmet R. Dogar
2018 arXiv   pre-print
We consider the problem of grasping in clutter. While there have been motion planners developed to address this problem in recent years, these planners are mostly tailored for open-loop execution.  ...  Therefore, we propose an online re-planning approach for grasping through clutter.  ...  [22] proposed the use of a hierarchy of supervisors for learning from demonstrations in order to grasp an object in clutter. Ratliff et al. [23] and Schulman et al.  ... 
arXiv:1807.09049v2 fatcat:j4vmvbjbpfaqbcutlwp23h75mu

Real-Time Online Re-Planning for Grasping Under Clutter and Uncertainty

Wisdom C. Agboh, Mehmet R. Dogar
2018 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)  
We consider the problem of grasping in clutter. While there have been motion planners developed to address this problem in recent years, these planners are mostly tailored for open-loop execution.  ...  Therefore, we propose an online re-planning approach for grasping through clutter.  ...  [21] proposed the use of a hierarchy of supervisors for learning from demonstrations in order to grasp an object in clutter. Ratliff et al. [22] and Schulman et al.  ... 
doi:10.1109/humanoids.2018.8625041 dblp:conf/humanoids/AgbohD18 fatcat:zw6ihatmpbbqbhsumbk6tdglki

Singulation of Objects in Cluttered Environment Using Dynamic Estimation of Physical Properties

Abid Imran, Sang-Hwa Kim, Young-Bin Park, Il Hong Suh, Byung-Ju Yi
2019 Applied Sciences  
In this paper, this limitation is overcome by introducing a technique to learn these parameters from unlabeled videos. For the analytical model, an impulse-based approach is used.  ...  This paper presents a scattering-based technique for object singulation in a cluttered environment.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app9173536 fatcat:77h3arybb5fdxfe5e22yx7a7mm

iCub World: Friendly Robots Help Building Good Vision Data-Sets [article]

Sean Ryan Fanello, Carlo Ciliberto, Matteo Santoro, Lorenzo Natale, Giorgio Metta, Lorenzo Rosasco, Francesca Odone
2013 arXiv   pre-print
In this paper we present and start analyzing the iCub World data-set, an object recognition data-set, we acquired using a Human-Robot Interaction (HRI) scheme and the iCub humanoid robot platform.  ...  While more constrained in its scopes -- the iCub world is essentially a robotics research lab -- we demonstrate how the proposed data-set poses challenges to current recognition systems.  ...  For this setting we used sequences of objects acquired in the Robot Mode (Sec. 3), letting the robot grasp the objects (see Fig. 4 , fourth row). One video for each category has been acquired.  ... 
arXiv:1306.3560v1 fatcat:zihvph7l5bfstonj5czwpnmsqy

iCub World: Friendly Robots Help Building Good Vision Data-Sets

Sean Ryan Fanello, Carlo Ciliberto, Matteo Santoro, Lorenzo Natale, Giorgio Metta, Lorenzo Rosasco, Francesca Odone
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
In this paper we present and start analyzing the iCub World data-set, an object recognition data-set, we acquired using a Human-Robot Interaction (HRI) scheme and the iCub humanoid robot platform.  ...  While more constrained in its scopesthe iCub world is essentially a robotics research lab -we demonstrate how the proposed data-set poses challenges to current recognition systems.  ...  For this setting we used sequences of objects acquired in the Robot Mode (Sec. 3), letting the robot grasp the objects (see Fig. 4 , fourth row). One video for each category has been acquired.  ... 
doi:10.1109/cvprw.2013.106 dblp:conf/cvpr/FanelloCSNMRO13 fatcat:plpbjhabxrc6hh2pxovksgrxvy

A FRAMEWORK FOR LEARNING AND CONTROL IN INTELLIGENT HUMANOID ROBOTS

OLIVER BROCK, ANDREW FAGG, RODERIC GRUPEN, ROBERT PLATT, MICHAEL ROSENSTEIN, JOHN SWEENEY
2005 International Journal of Humanoid Robotics  
We present several pieces of an overall framework in which a robot learns situated policies for control that exploit existing control knowledge and extend its scope.  ...  Several examples drawn from the research agenda at the Laboratory for Perceptual Robotics are used to illustrate the ideas.  ...  Any opinions, findings, conclusions, or recommendations expressed in this material are the authors' and do not necessarily reflect those of the sponsors.  ... 
doi:10.1142/s0219843605000491 fatcat:quucpz6uazfznfcgrr6ywkjltm

Leveraging on a virtual environment for robot programming by demonstration

J. Aleotti, S. Caselli, M. Reggiani
2004 Robotics and Autonomous Systems  
The Programming by Demonstration paradigm promises to reduce the complexity of robot programming. Its aim is to let robot systems learn new behaviors from a human operator demonstration.  ...  In this paper, we argue that while providing demonstrations in the real environment enables teaching of general tasks, for tasks whose essential features are known a priori demonstrating in a virtual environment  ...  The system recognizes, from the user's hand movements, a sequence of high level actions and translates them into a sequence of commands for a robot manipulator.  ... 
doi:10.1016/j.robot.2004.03.009 fatcat:kffzhkicn5fcnegwjc3gzvrtgq

Learning Category-Level Manipulation Tasks from Point Clouds with Dynamic Graph CNNs [article]

Junchi Liang, Abdeslam Boularias
2022 arXiv   pre-print
This paper presents a new technique for learning category-level manipulation from raw RGB-D videos of task demonstrations, with no manual labels or annotations.  ...  We address this problem by first viewing both grasping and manipulation as special cases of tool use, where a tool object is moved to a sequence of key-poses defined in a frame of reference of a target  ...  Recent proposed methods include training a hierarchy of supervisors from demonstrations to grasp objects in clutter [26] , and convolutional neural networks, such as Dex-net 4.0 [27] , that are trained  ... 
arXiv:2209.06331v1 fatcat:f5wyrfn2y5cgji5yyrfsbf6u7q

People helping robots helping people: Crowdsourcing for grasping novel objects

A Sorokin, D Berenson, S S Srinivasa, M Hebert
2010 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We demonstrate our approach on the task of grasping unknown objects.  ...  In this paper we present a framework for robot supervision through Amazon Mechanical Turk.  ...  David Forsyth provided us invaluable advice and support.  ... 
doi:10.1109/iros.2010.5650464 dblp:conf/iros/SorokinBSH10 fatcat:zhcuaklaybgihhc6fuu4rj3t5y

Manipulation in Human Environments

Aaron Edsinger, Charles Kemp
2006 2006 6th IEEE-RAS International Conference on Humanoid Robots  
We describe the design of a humanoid robot named Domo, develop methods that allow Domo to assist a person in everyday tasks, and discuss general strategies for building robots that work alongside people  ...  Thesis Supervisor: Rodney A. Brooks Title: Professor of Computer Science and Engineering Foremost, I want to thank Rod Brooks for his support over the years.  ...  In the long run, learning from demonstration could serve as an intuitive way for people to program the robots they work with.  ... 
doi:10.1109/ichr.2006.321370 dblp:conf/humanoids/EdsingerK06 fatcat:i5tunfqrrfdenh6k2vos5mhsby

A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms [article]

Oliver Kroemer, Scott Niekum, George Konidaris
2020 arXiv   pre-print
We aim to survey a representative subset of that research which uses machine learning for manipulation.  ...  Learning will be central to such autonomous systems, as the real world contains too much variation for a robot to expect to have an accurate model of its environment, the objects in it, or the skills required  ...  Acknowledgments The authors would like to thank Animesh Garg for all of his help and insightful discussions, and Ben Abbatematteo, Daniel Brown, Caleb Chuck, Matt Corsaro  ... 
arXiv:1907.03146v3 fatcat:2lmt6zpehfa3rj42a3k5kgd4ju

A Modular Software Framework for Eye–Hand Coordination in Humanoid Robots

Jürgen Leitner, Simon Harding, Alexander Förster, Peter Corke
2016 Frontiers in Robotics and AI  
A key capability of this system is reactive avoidance of obstacle objects detected from the video stream while carrying out reach-and-grasp tasks.  ...  The subsystems of our architecture can independently be improved and updated, for example, we show that by using machine learning techniques we can improve visual perception by collecting images during  ...  For example, Hart et al. (2006) showed that a developmental approach can be used for a robot to learn to reach and grasp.  ... 
doi:10.3389/frobt.2016.00026 fatcat:ufmfl7hdfnfj3ks7zjhrjil46q

Social Robotics and Societies of Robots

Antonio Bicchi, Guglielmo Tamburrini
2015 The Information Society  
Notably, suitable robotic hand design and control principles must be adopted to achieve proper robotic manipulation of objects designed for human hands that one finds in human habitats.  ...  there rich robot-robot social exchanges, and yet refraining from any physical contact with human beings.  ...  and social hierarchies all play a role in negotiating passages through a corridor or narrow space, in very much the same way -albeit far less explicitly codifiedas car drivers use rules of the road to  ... 
doi:10.1080/01972243.2015.1020196 fatcat:qhq6auuhtvamppiahmpkyuao6q
« Previous Showing results 1 — 15 out of 195 results