Soft Hands

Robust Proprioceptive Grasping with a Soft Robot Hand

Soft Robotic Hand

We developed a soft hand that is capable of robustly grasping and identifying objects based on internal state measurements along with a system that autonomously performs grasps. The highly compliant soft hand allows for intrinsic robustness to grasping uncertainties. The addition of internal sensing allows the configuration of the hand and object to be detected. The finger module includes resistive force sensors on the fingertips for contact detection and resistive bend sensors for measuring the curvature profile of the finger. The curvature sensors can be used to estimate the contact geometry. This capability allows to distinguish between a set of grasped objects. With one data point from each finger, the object can be identified by grasping it. A clustering algorithm finds the correspondence for each grasped object. We tested this for both enveloping grasps and pinch grasps. A closed loop system uses a camera to detect approximate object locations. Compliance in the soft hand handles that uncertainty in addition to geometric uncertainty in the shape of the object.

  • [PDF] [DOI] B. S. Homberg*, R. K. Katzschmann*, M. R. Dogar, and D. Rus, “Robust proprioceptive grasping with a soft robot hand,” Autonomous Robots, 2018.
    [Bibtex]
    @article{homberg2018robust,
    title = {Robust proprioceptive grasping with a soft robot hand},
    author = {Homberg*, Bianca S. and Katzschmann*, Robert K. and Dogar, Mehmet R. and Rus, Daniela},
    publisher = {Springer US},
    journal = {Autonomous Robots},
    keywords = {Soft Robotics, Soft Gripper, Proprioceptive soft robotic hand, Proprioceptive sensing, Online object identification, Learning new objects, Autonomously Grasping},
    month = {April},
    year = {2018},
    doi = {10.1007/s10514-018-9754-1},
    abstract = {This work presents a soft hand capable of robustly grasping and identifying objects based on internal state measurements along with a combined system which autonomously performs grasps. A highly compliant soft hand allows for intrinsic robustness to grasping uncertainties; the addition of internal sensing allows the configuration of the hand and object to be detected. The finger module includes resistive force sensors on the fingertips for contact detection and resistive bend sensors for measuring the curvature profile of the finger. The curvature sensors can be used to estimate the contact geometry and thus to distinguish between a set of grasped objects. With one data point from each finger, the object grasped by the hand can be identified. A clustering algorithm to find the correspondence for each grasped object is presented for both enveloping grasps and pinch grasps. A closed loop system uses a camera to detect approximate object locations. Compliance in the soft hand handles that uncertainty in addition to geometric uncertainty in the shape of the object.},
    }
  • [PDF] [DOI] B. S. Homberg, R. K. Katzschmann, M. R. Dogar, and D. Rus, “Haptic Identification of Objects using a Modular Soft Robotic Gripper,” in 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015, p. 1698–1705.
    [Bibtex]
    @inproceedings{homberg2015haptic,
    author = {Homberg, Bianca S. and Katzschmann, Robert K. and Dogar, Mehmet R. and Rus, Daniela},
    booktitle = {2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
    doi = {10.1109/IROS.2015.7353596},
    keywords = {Baxter robot,Grasping,Grippers,Object recognition,Robot sensing systems,Rubber,clustering algorithm,dexterous manipulators,enveloping grasps,grippers,highly compliant hand,internal state measurements,modular soft robotic gripper,object haptic identification,pattern clustering,pinch grasps,resistive bend sensors,robust proprioceptive soft grasping,three finger gripper},
    month = {sep},
    pages = {1698--1705},
    title = {Haptic Identification of Objects using a Modular Soft Robotic Gripper},
    year = {2015},
    abstract = {This work presents a soft hand capable of robustly grasping and identifying objects based on internal state measurements. A highly compliant hand allows for intrinsic robustness to grasping uncertainty, but the specific configuration of the hand and object is not known, leaving undetermined if a grasp was successful in picking up the right object. A soft finger was adapted and combined to form a three finger gripper that can easily be attached to existing robots, for example, to the wrist of the Baxter robot. Resistive bend sensors were added within each finger to provide a configuration estimate sufficient for distinguishing between a set of objects. With one data point from each finger, the object grasped by the gripper can be identified. A clustering algorithm to find the correspondence for each grasped object is presented for both enveloping grasps and pinch grasps. This hand is a first step towards robust proprioceptive soft grasping.},
    }

News Articles (Sept. 2015): Soft robotic gripper can pick up and identify wide array of objects” featured in
BBC, Scientific American, CNBC, VICE, Popular Science, Boston Globe, Bloomberg Radio, Washington Post, NBC News, Quartz, Christian Science Monitor, Gizmodo, Slashgear, BostInno, etc.

Link to Soft Robotic Hand Project at the Distributed Robotics Lab, CSAIL, MIT

Printable Hydraulics for Soft Grippers

Printed Hydraulics Gripper

This work introduces a novel technique for fabricating functional robots using 3D printers. Simultaneously depositing photopolymers and a non-curing liquid allows complex, pre-filled fluidic channels to be fabricated. This new printing capability enables complex hydraulically actuated robots and robotic components to be automatically built, with no assembly required. The technique is showcased by printing linear bellows actuators, gear pumps, soft grippers and a hexapod robot, using a commercially-available 3D printer. We detail the steps required to modify the printer and describe the design constraints imposed by this new fabrication approach.

  • [PDF] [DOI] R. MacCurdy, R. K. Katzschmann, Y. Kim, and D. Rus, “Printable hydraulics: A method for fabricating robots by 3D co-printing solids and liquids,” in 2016 IEEE International Conference on Robotics and Automation (ICRA), Stockholm, 2016, p. 3878–3885.
    [Bibtex]
    @inproceedings{maccurdy2016printable,
    author = {MacCurdy, Robert and Katzschmann, Robert K. and Kim, Youbin and Rus, Daniela},
    booktitle = {2016 IEEE International Conference on Robotics and Automation (ICRA)},
    doi = {10.1109/ICRA.2016.7487576},
    arxivId = {1512.03744},
    eprint = {1512.03744},
    keywords = {3D printers,Additive Manufacturing,Flexible Robots,Hydraulic Robots,Liquids,Printable Robotics,Printers,Robots,Soft Material Robotics,Solid modeling,Solids,additive manufacturing,commercially-available 3D printer,flexible robots,functional robots,gear pumps,grippers,hexapod robot,hydraulic systems,linear bellows actuators,noncuring liquid,optical polymers,photopolymers,prefilled fluidic channels,printable hydraulics,robot dynamics,soft grippers},
    month = {may},
    pages = {3878--3885},
    title = {Printable hydraulics: A method for fabricating robots by 3D co-printing solids and liquids},
    url = {http://arxiv.org/abs/1512.03744},
    year = {2016},
    abstract = {This paper introduces a novel technique for fabricating functional robots using 3D printers. Simultaneously depositing photopolymers and a non-curing liquid allows complex, pre-filled fluidic channels to be fabricated. This new printing capability enables complex hydraulically actuated robots and robotic components to be automatically built, with no assembly required. The technique is showcased by printing linear bellows actuators, gear pumps, soft grippers and a hexapod robot, using a commercially-available 3D printer. We detail the steps required to modify the printer and describe the design constraints imposed by this new fabrication approach.},
    address = {Stockholm},
    }

News Articles (July 2016): First-ever 3-D printed robots made of both solids and liquids“ featured in
CBS News, Wired, BBC News, The Verge, Washington Post, Popular Science, ZDNet, Quartz, PC Mag, CNET, Digital Trends, Daily Mail, Engadget, Fast Company, Mashable, Boston Magazine, Vice, Gizmodo, ABC News, Gizmag, Yahoo Finance, etc.

Link to the Printable Hydraulics Project at the Distributed Robotics Lab, CSAIL, MIT