Probabilistic consolidation of grasp experience

We present a probabilistic model for joint representation of several sensory modalities and action parameters in a robotic grasping scenario. Our non-linear probabilistic latent variable model encodes relationships between grasp-related parameters, learns the importance of features, and expresses confidence in estimates. The model learns associations between stable and unstable grasps that it experiences during an exploration phase. We demonstrate the applicability of the model for estimating grasp stability, correcting grasps, identifying objects based on tactile imprints and predicting tactile imprints from object-relative gripper poses. We performed experiments on a real platform with both known and novel objects, i.e., objects the robot trained with, and previously unseen objects. Grasp correction had a 75% success rate on known objects, and 73% on new objects. We compared our model to a traditional regression model that succeeded in correcting grasps in only 38% of cases.

[1]  Peter K. Allen,et al.  Grasp adjustment on novel objects using tactile experience from similar local geometry , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  R S Johansson,et al.  Sensory input and control of grip. , 1998, Novartis Foundation symposium.

[3]  Aude Billard,et al.  Iterative learning of grasp adaptation through human corrections , 2012, Robotics Auton. Syst..

[4]  Erik B. Sudderth.  Graphical models for visual object recognition and tracking , 2006 .

[5]  Van-Duc Nguyen,et al.  Constructing Force- Closure Grasps , 1988, Int. J. Robotics Res..

[6]  Anis Sahbani,et al.  An overview of 3D object grasp synthesis algorithms , 2012, Robotics Auton. Syst..

[7]  M. Vincze,et al.  BLORT-The Blocks World Robotic Vision Toolbox , 2010 .

[8]  Tamim Asfour,et al.  Planning grasps for robotic hands using a novel object representation based on the medial axis transform , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Danica Kragic,et al.  Data-Driven Grasp Synthesis—A Survey , 2013, IEEE Transactions on Robotics.

[10]  Danica Kragic,et al.  Demonstration-based learning and control for automatic grasping , 2009, Intell. Serv. Robotics.

[11]  Esa Alhoniemi,et al.  SOM Toolbox for Matlab 5 , 2000 .

[12]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[13]  R. Fisher.  Dispersion on a sphere , 1953, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[14]  C. Ek.  Shared Gaussian Process Latent Variables Models , 2009 .

[15]  Danica Kragic,et al.  Learning of grasp adaptation through experience and tactile sensing , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Jan Wikander,et al.  A FRAMEWORK FOR GRASP SIMULATION AND CONTROL IN DOMESTIC ENVIRONMENTS , 2006 .

[17]  Sachin Chitta,et al.  Human-Inspired Robotic Grasp Control With Tactile Sensing , 2011, IEEE Transactions on Robotics.

[18]  Máximo A. Roa,et al.  Transferring functional grasps through contact warping and local replanning , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Neil D. Lawrence,et al.  Manifold Relevance Determination , 2012, ICML.

[20]  Vijay Kumar,et al.  Robotic grasping and contact: a review , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[21]  Danica Kragic,et al.  Learning tactile characterizations of object- and pose-specific grasps , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.