Exploring affordances in robot grasping through latent structure representation

An important challenge in robotic research is learning by imitation. The goal in such is to create a system whereby a robot can learn to perform a specific task by imitating a human instructor. In order to do so, the robot needs to determine the state of the scene through its sensory system. There is a huge range of possible sensory streams that the robot can make use of to reason and interact with its environment. Due to computational and algorithmic limitations we are interested in limiting the number of sensory inputs. Further, streams can be complementary both in general, but more importantly for specific tasks. Thereby, an intelligent and constrained limitation of the number of sensory inputs is motivated. We are interested in exploiting such structure in order to do what will be referred to as Goal-Directed-Perception (GDP). The goal of GDP is, given partial knowledge about the scene, to direct the robot’s modes of perception in order to maximally disambiguate the state space. In this paper, we present the application of two different probabilistic models in modeling the largely redundant and complementary observation space for the task of object grasping. We evaluate and discuss the results of both approaches.

[1]  Danica Kragic,et al.  Monocular real-time 3D articulated hand pose estimation , 2009, 2009 9th IEEE-RAS International Conference on Humanoid Robots.

[2]  Adnan Darwiche,et al.  Inference in belief networks: A procedural guide , 1996, Int. J. Approx. Reason..

[3]  Trevor Darrell,et al.  Factorized Orthogonal Latent Spaces , 2010, AISTATS.

[4]  Rajesh P. N. Rao,et al.  Learning Shared Latent Structure for Image Synthesis and Robotic Imitation , 2005, NIPS.

[5]  Michael I. Jordan,et al.  Probabilistic Networks and Expert Systems , 1999 .

[6]  David Heckerman,et al.  A Tutorial on Learning with Bayesian Networks , 1998, Learning in Graphical Models.

[7]  Katsushi Ikeuchi,et al.  Toward automatic robot instruction from perception-mapping human grasps to manipulator grasps , 1997, IEEE Trans. Robotics Autom..

[8]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[9]  Neil D. Lawrence,et al.  Probabilistic Non-linear Principal Component Analysis with Gaussian Process Latent Variable Models , 2005, J. Mach. Learn. Res..

[10]  A. Meltzoff.  Elements of a developmental theory of imitation , 2002 .

[11]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

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

[13]  Ryan P. Adams,et al.  Learning the Structure of Deep Sparse Graphical Models , 2009, AISTATS.

[14]  Danica Kragic,et al.  Learning task constraints for robot grasping using graphical models , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Andrew McCallum,et al.  Piecewise pseudolikelihood for efficient training of conditional random fields , 2007, ICML '07.

[16]  Chrystopher L. Nehaniv,et al.  Correspondence Mapping Induced State and Action Metrics for Robotic Imitation , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[17]  David J. Fleet,et al.  Topologically-constrained latent variable models , 2008, ICML '08.

[18]  K. Dautenhahn,et al.  Imitation and Social Learning in Robots, Humans and Animals: Behavioural, Social and Communicative Dimensions , 2009 .

[19]  Manuel Lopes,et al.  Learning Object Affordances: From Sensory--Motor Coordination to Imitation , 2008, IEEE Transactions on Robotics.

[20]  Trevor Darrell,et al.  FOLS : Factorized Orthogonal Latent Spaces , 2010 .

[21]  Trevor Darrell,et al.  Discriminative Gaussian process latent variable model for classification , 2007, ICML '07.

[22]  J. Greeno.  Gibson's affordances. , 1994, Psychological review.