Grasping known objects with humanoid robots: A box-based approach

Autonomous grasping of household objects is one of the major skills that an intelligent service robot necessarily has to provide in order to interact with the environment. In this paper, we propose a grasping strategy for known objects, comprising an off-line, box-based grasp generation technique on 3D shape representations. The complete system is able to robustly detect an object and estimate its pose, flexibly generate grasp hypotheses from the assigned model and perform such hypotheses using visual servoing. We will present experiments implemented on the humanoid platform ARMAR-III.

[1]  J. J. Gibson.  The theory of affordances , 1977 .

[2]  R. Shaw,et al.  Perceiving, Acting and Knowing : Toward an Ecological Psychology , 1978 .

[3]  Sariel Har-Peled,et al.  Efficiently approximating the minimum-volume bounding box of a point set in three dimensions , 1999, SODA '99.

[4]  Lars Petersson,et al.  Systems integration for real-world manipulation tasks , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[5]  Robert O. Ambrose,et al.  Tactile gloves for autonomous grasping with the NASA/DARPA Robonaut , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[6]  Albert Albers,et al.  Design and development process of a humanoid robot upper body through experimentation , 2004, 4th IEEE/RAS International Conference on Humanoid Robots, 2004..

[7]  Stefan Schulz,et al.  Progress in the development of anthropomorphic fluidic hands for a humanoid robot , 2004, 4th IEEE/RAS International Conference on Humanoid Robots, 2004..

[8]  Peter K. Allen,et al.  Graspit! A versatile simulator for robotic grasping , 2004, IEEE Robotics & Automation Magazine.

[9]  K. Okada,et al.  Humanoid motion generation system on HRP2-JSK for daily life environment , 2005, IEEE International Conference Mechatronics and Automation, 2005.

[10]  Robert Platt,et al.  Learning and generalizing control-based grasping and manipulation skills , 2006 .

[11]  Tamim Asfour,et al.  ARMAR-III: An Integrated Humanoid Platform for Sensory-Motor Control , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[12]  Christopher W. Geib,et al.  Object Action Complexes as an Interface for Planning and Robot Control , 2006 .

[13]  Masayuki Inaba,et al.  Vision based behavior verification system of humanoid robot for daily environment tasks , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[14]  Gerd Hirzinger,et al.  Impedance Behaviors for Two-handed Manipulation: Design and Experiments , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[15]  Rüdiger Dillmann,et al.  Developing and analyzing intuitive modes for interactive object modeling , 2007, ICMI '07.

[16]  Tamim Asfour,et al.  Stereo-based 6D object localization for grasping with humanoid robot systems , 2007, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Rüdiger Dillmann,et al.  Visual servoing for humanoid grasping and manipulation tasks , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.

[18]  Danica Kragic,et al.  Birth of the Object: Detection of Objectness and Extraction of Object Shape through Object-Action complexes , 2008, Int. J. Humanoid Robotics.

[19]  Danica Kragic,et al.  Selection of robot pre-grasps using box-based shape approximation , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Danica Kragic,et al.  Minimum volume bounding box decomposition for shape approximation in robot grasping , 2008, 2008 IEEE International Conference on Robotics and Automation.

[21]  Tamim Asfour,et al.  Toward humanoid manipulation in human-centred environments , 2008, Robotics Auton. Syst..

[22]  Danica Kragic,et al.  Learning of 2D grasping strategies from box-based 3D object approximations , 2009, Robotics: Science and Systems.

[23]  Florentin Wörgötter,et al.  Cognitive agents - a procedural perspective relying on the predictability of Object-Action-Complexes (OACs) , 2009, Robotics Auton. Syst..