TY - CONF T1 - Advanced grasping with the Pisa/IIT softHand T2 - Robotic Grasping and Manipulation Challenge Y1 - 2018 A1 - M. Bonilla A1 - C. Della Santina A1 - A. Rocchi A1 - E. Luberto A1 - G. Santaera A1 - E. Farnioli A1 - C. Piazza A1 - F. Bonomo A1 - A. Brando A1 - A. Raugi A1 - M. G. Catalano A1 - M. Bianchi A1 - M. Garabini A1 - G. Grioli A1 - A. Bicchi JF - Robotic Grasping and Manipulation Challenge ER - TY - JOUR T1 - Efficient Walking Gait Generation via Principal Component Representation of Optimal Trajectories: Application to a Planar Biped Robot With Elastic Joints JF - IEEE Robotics and Automation Letters Y1 - 2018 A1 - G M Gasparri A1 - S. Manara A1 - D. Caporale A1 - G. Averta A1 - M. Bonilla A1 - H. Marino A1 - M. G. Catalano A1 - G. Grioli A1 - M. Bianchi A1 - A. Bicchi A1 - M. Garabini AB -

Recently, the method of choice to exploit robot dynamics for efficient walking is numerical optimization (NO). The main drawback in NO is the computational complexity, which strongly affects the time demand of the solution. Several strategies can be used to make the optimization more treatable and to efficiently describe the solution set. In this letter, we present an algorithm to encode effective walking references, generated offline via numerical optimization, extracting a limited number of principal components and using them as a basis of optimal motions. By combining these components, a good approximation of the optimal gaits can be generated at run time. The advantages of the presented approach are discussed, and an extensive experimental validation is carried out on a planar legged robot with elastic joints. The biped thus controlled is able to start and stop walking on a treadmill, and to control its speed dynamically as the treadmill speed changes.

VL - 3 ER - TY - JOUR T1 - Incrementality and Hierarchies in the Enrollment of Multiple Synergies for Grasp Planning JF - IEEE Robotics and Automation Letters Y1 - 2018 A1 - G. Averta A1 - F. Angelini A1 - M. Bonilla A1 - M. Bianchi A1 - A. Bicchi KW - 19-DoF anthropomorphic hand KW - Biomechanics KW - common grasping tasks KW - compliant joint/mechanism KW - covariance matrices KW - experimental covariance matrix KW - Force KW - force distribution KW - grasp planning KW - Grasping KW - grippers KW - hand posture reconstruction KW - hand-object relative pose KW - incremental learning algorithm KW - Jacobian matrices KW - joint angle covariation patterns KW - learning (artificial intelligence) KW - minimisation KW - multifingered hands KW - pose estimation KW - postural hand synergies KW - postural synergies KW - posture description KW - principal component analysis KW - reduced complexity representation KW - relative statistical weight KW - Robots KW - Solid modeling KW - synergy vectors KW - Task analysis VL - 3 ER - TY - CONF T1 - Touch-Based Grasp Primitives for Soft Hands: Applications to Human-to-Robot Handover Tasks and Beyond T2 - 2018 IEEE International Conference on Robotics and Automation (ICRA) Y1 - 2018 A1 - M. Bianchi A1 - G. Averta A1 - E. Battaglia A1 - C. Rosales A1 - M. Bonilla A1 - A. Tondo A1 - M. Poggiani A1 - G. Santaera A1 - S. Ciotti A1 - M. G. Catalano A1 - A. Bicchi JF - 2018 IEEE International Conference on Robotics and Automation (ICRA) ER - TY - CONF T1 - Noninteracting Constrained Motion Planning and Control for Robot Manipulators T2 - IEEE International Conference of Robotics and Automation, ICRA2017 Y1 - 2017 A1 - M. Bonilla A1 - L. Pallottino A1 - A. Bicchi KW - Robotics AB -

In this paper we present a novel geometric approach
to motion planning for constrained robot systems.
This problem is notoriously hard, as classical sampling-based
methods do not easily apply when motion is constrained in
a zero-measure submanifold of the configuration space. Based
on results on the functional controllability theory of dynamical
systems, we obtain a description of the complementary spaces
where rigid body motions can occur, and where interaction
forces can be generated, respectively. Once this geometric setting
is established, the motion planning problem can be greatly
simplified. Indeed, we can relax the geometric constraint, i.e.,
replace the lower–dimensional constraint manifold with a fulldimensional
boundary layer. This in turn allows us to plan
motion using state-of-the-art methods, such as RRT*, on points
within the boundary layer, which can be efficiently sampled. On
the other hand, the same geometric approach enables the design
of a completely decoupled control scheme for interaction forces,
so that they can be regulated to zero (or any other desired
value) without interacting with the motion plan execution.
A distinguishing feature of our method is that it does not
use projection of sampled points on the constraint manifold,
thus largely saving in computational time, and guaranteeing
accurate execution of the motion plan. An explanatory example
is presented, along with an experimental implementation of the
method on a bimanual manipulation workstation.

JF - IEEE International Conference of Robotics and Automation, ICRA2017 PB - IEEE UR - http://ieeexplore.ieee.org/document/7989463/ ER - TY - JOUR T1 - The Quest for Natural Machine Motion: An Open Platform to Fast-Prototyping Articulated Soft Robots JF - IEEE Robotics and Automation Magazine Y1 - 2017 A1 - C. Della Santina A1 - C. Piazza A1 - Gasparri, G. M. A1 - M. Bonilla A1 - M. G. Catalano A1 - G. Grioli A1 - M. Garabini A1 - A. Bicchi KW - Robotics AB -
Soft robots are one of the most significant recent evolutions in robotics. They rely on compliant physical structures purposefully designed to embody desired characteristics. Since their introduction, they have shown remarkable applicability in overcoming their rigid counterparts in such areas as interaction with humans, adaptability, energy efficiency, and maximization of peak performance. Nonetheless, we believe
that research on novel soft robot applications is still slowed by the difficulty in obtaining or developing a working soft robot structure to explore novel applications.
In this article, we present the Natural Machine Motion Initiative (NMMI), a modular open platform that aims to provide the scientific community with tools for fast and easy prototyping of articulated soft robots. Such a platform is composed of three main open hardware modules: the Qbmoves variable-stiffness actuators (VSAs) to build the main robotic structure, soft end effectors (EEs) to interact with the world, and a pool of application-specific add-ons. We also discuss many novel uses of the platform to rapidly prototype (RP) and test new robotic structures with original soft capabilities, and we propose NMMI- based experiments.
VL - 24 UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=7857692 IS - 1 N1 -

Open access

e wish to thank Samuele Batazzi, Fabio Bonomo, Alberto
Brando, Andrea Di Basco, Tommaso Pardi, Riccardo Persichi-
ni, and Alessandro Raugi for their valuable support in the
development of the hardware prototype. This work was sup-
ported by SOFTPRO (grant 688857) and SOMA (grant
645599)—projects of the European Commission’s Horizon
2020 research program—and by Walk-Man grant 611832.
Support also came from the European Research Council
under an Advanced Grant for “SoftHands: A Theory of Soft
Synergies for a New Generation of Artificial Hands” (grant
ERC-291166).
ER - TY - CHAP T1 - From Soft to Adaptive Synergies: The Pisa/IIT SoftHand T2 - Human and Robot Hands Y1 - 2016 A1 - M. G. Catalano A1 - G. Grioli A1 - E. Farnioli A1 - A. Serio A1 - M. Bonilla A1 - M. Garabini A1 - C. Piazza A1 - M Gabiccini A1 - A. Bicchi AB -

Taking inspiration from the neuroscientific findings on hand synergies discussed in the first part of the book, in this chapter we present the Pisa/IIT SoftHand, a novel robot hand prototype. The design moves under the guidelines of making an hardware robust and easy to control, preserving an high level of grasping capabilities and an aspect as similar as possible to the human counterpart. First, the main theoretical tools used to enable such simplification are presented, as for example the notion of soft synergies. A discussion of some possible actuation schemes shows that a straightforward implementation of the soft synergy idea in an effective design is not trivial. The proposed approach, called adaptive synergy, rests on ideas coming from underactuated hand design, offering a design method to implement the desired set of soft synergies as demonstrated both with simulations and experiments. As a particular instance of application of the synthesis method of adaptive synergies, the Pisa/IIT SoftHand is described in detail. The hand has 19 joints, but only uses one actuator to activate its adaptive synergy. Of particular relevance in its design is the very soft and safe, yet powerful and extremely robust structure, obtained through the use of innovative articulations and ligaments replacing conventional joint design. Moreover, in this work, summarizing results presented in previous papers, a discussion is presented about how a new set of possibilities is open from paradigm shift in manipulation approaches, moving from manipulation with rigid to soft hands.

JF - Human and Robot Hands PB - Springer VL - Springer Series on Touch and Haptic Systems ER - TY - JOUR T1 - No More Heavy Lifting: Robotic Solutions to the Container Unloading Problem JF - IEEE Robotics and Automation Magazine Y1 - 2016 A1 - T. Stoyanov A1 - N. Vaskeviciusz A1 - C. A. Mueller A1 - T. Fromm A1 - R. Krug A1 - V. Tincani A1 - R. Mojtahedzadeh A1 - S. Kunaschk A1 - R. M. Ernits A1 - D. R. Canelhas A1 - M. Bonilla A1 - S. Schwertfeger A1 - M. Bonini A1 - H. Halfar A1 - K. Pathak A1 - M. Rohde A1 - G Fantoni A1 - A. Bicchi A1 - A. Birk A1 - A. Lilienthal A1 - W. Echelmeyer KW - Robotics VL - 23 UR - https://ieeexplore.ieee.org/document/7553531 IS - 4 ER - TY - CONF T1 - Grasp Planning with Soft Hands using Bounding Box Object Decomposition T2 - IEEE International Conference of Intelligent Robots and Systems (IROS2015) Y1 - 2015 A1 - M. Bonilla A1 - D. Resasco A1 - M Gabiccini A1 - A. Bicchi KW - Haptics KW - Robotics JF - IEEE International Conference of Intelligent Robots and Systems (IROS2015) PB - IEEE CY - Hamburg, Germany, September 28 - October 02, 2015 UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7353421&queryText=Grasp%20Planning%20with%20Soft%20Hands%20using%20Bounding%20Box%20Object%20Decomposition&newsearch=true N1 -

softhands pacman walkman

ER - TY - CONF T1 - Sample-Based Motion Planning for Robot Manipulators with Closed Kinematic Chains T2 - IEEE International Conference on Robotics and Automation (ICRA2015) Y1 - 2015 A1 - M. Bonilla A1 - E. Farnioli A1 - L. Pallottino A1 - A. Bicchi KW - Robotics JF - IEEE International Conference on Robotics and Automation (ICRA2015) PB - IEEE CY - Seattle, USA, 25 - 30 May N1 -

softhands pacman walkman

ER - TY - CONF T1 - Grasping with Soft Hands T2 - IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS 2014) Y1 - 2014 A1 - M. Bonilla A1 - E. Farnioli A1 - C. Piazza A1 - M. G. Catalano A1 - G. Grioli A1 - M. Garabini A1 - M Gabiccini A1 - A. Bicchi KW - Haptics KW - Robotics AB -

Despite some prematurely optimistic claims, the ability of robots to grasp general objects in unstructured environments still remains far behind that of humans. This is not solely caused by differences in the mechanics of hands: indeed, we show that human use of a simple robot hand (the Pisa/IIT SoftHand) can afford capabilities that are comparable to natural grasping. It is through the observation of such human-directed robot hand operations that we realized how fundamental in everyday grasping and manipulation is the role of hand compliance, which is used to adapt to the shape of surrounding objects. Objects and environmental constraints are in turn used to functionally shape the hand, going beyond its nominal kinematic limits by exploiting structural softness. In this paper, we set out to study grasp planning for hands that are simple — in the sense of low number of actuated degrees of freedom (one for the Pisa/IIT SoftHand) — but are soft, i.e. continuously deformable in an infinity of possible shapes through interaction with objects. After general considerations on the change of paradigm in grasp planning that this setting brings about with respect to classical rigid multi-dof grasp planning, we present a procedure to extract grasp affordances for the Pisa/IIT SoftHand through physically accurate numerical simulations. The selected grasps are then successfully tested in an experimental scenario.

JF - IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS 2014) CY - Madrid, Spain, November 18 - 20 UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=7041421&queryText%3DGrasping+with+Soft+Hands ER - TY - CONF T1 - Velvet Fingers: Grasp Planning and Execution for an Underactuated Gripper with Active Surfaces T2 - 2014 IEEE International Conference on Robotics and Automation Y1 - 2014 A1 - R. Krug A1 - T. Stoyanov A1 - M. Bonilla A1 - V. Tincani A1 - N. Vaskeviciusz A1 - G Fantoni A1 - A. Birkz A1 - A. Lilienthal A1 - A. Bicchi KW - Haptics KW - Robotics AB -

In this work we tackle the problem of planning grasps for an underactuated gripper which enable it to retrieve target objects from a cluttered environment. Furthermore, we investigate how additional manipulation capabilities of the gripping device, provided by active surfaces on the inside of the fingers, can lead to performance improvement in the grasp execution process. To this end, we employ a simple strategy, in which the target object is `pulled-in' towards the palm during grasping which results in firm enveloping grasps. We show the effectiveness of the suggested methods by means of experiments conducted in a real-world scenario.

JF - 2014 IEEE International Conference on Robotics and Automation PB - IEEE CY - Hong Kong, May 31 2014-June 7 2014 UR - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6907390 U1 -

Roblog

ER - TY - CONF T1 - Controlling the active surfaces of the Velvet Fingers: sticky to slippy fingers T2 - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2013 Y1 - 2013 A1 - V. Tincani A1 - G. Grioli A1 - M. G. Catalano A1 - M. Bonilla A1 - M. Garabini A1 - G Fantoni A1 - A. Bicchi KW - Robotics AB -

Industrial grippers are often used for grasping, while in-hand re-orientation and positioning are dealt with by other means. Contact surface engineering has been recently proposed as a possible mean to introduce dexterity in simple grippers, as in the Velvet Fingers smart gripper, a novel concept of end-effector combining simple under-actuated mechanics and high manipulation possibilities, thanks to conveyors which are built in the finger pads. This paper undergoes the modeling and control of the active conveyors of the Velvet Fingers gripper which are rendered able to emulate different levels of friction and to apply tangential thrusts to the contacted objects. Through the paper particular attention is dedicated to the mechanical implementation, sense drive and control electronics of the device. The capabilities of the prototype are showed in some grasping and manipulation experiments.

JF - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2013 CY - Tokyo, Japan UR - http://ieeexplore.ieee.org/xpl/login.jsp?tp=&arnumber=6697152&url=http%3A%2F%2Fieeexplore.ieee.org%2Fxpls%2Fabs_all.jsp%3Farnumber%3D6697152 ER - TY - CONF T1 - Grasp Compliance Regulation in Synergistically Controlled Robotic Hands with VSA T2 - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2013 Y1 - 2013 A1 - E. Farnioli A1 - M Gabiccini A1 - M. Bonilla A1 - A. Bicchi KW - Robotics JF - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2013 CY - Tokyo, Japan ER -