Kinematic Morphing Networks for Manipulation Skill Transfer

The transfer of a robot skill between different geometric environments is non-trivial since a wide variety of environments exists, sensor observations as well as robot motions are high-dimensional, and the environment might only be partially observed. We consider the problem of extracting a low-dimensional description of the manipulated environment in form of a kinematic model. This allows us to transfer a skill by defining a policy on a prototype model and morphing the observed environment to this prototype. A deep neural network is used to map depth image observations of the environment to morphing parameter, which include transformations and configurations of the prototype model. Using the concatenation property of affine transformations and the ability to convert point clouds to depth images allows to apply the network in an iterative manner. The network is trained on data generated in a simulator and on augmented data that is created with its own predictions. The algorithm is evaluated on different tasks, where it is shown that iterative predictions lead to a higher accuracy than one-step predictions.

[1]  Dumitru Erhan,et al.  Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yichen Wei,et al.  Model-Based Deep Hand Pose Estimation , 2016, IJCAI.

[3]  Alex Graves,et al.  Asynchronous Methods for Deep Reinforcement Learning , 2016, ICML.

[4]  Peter Englert,et al.  Learning manipulation skills from a single demonstration , 2018, Int. J. Robotics Res..

[5]  Kostas E. Bekris,et al.  A self-supervised learning system for object detection using physics simulation and multi-view pose estimation , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[6]  Sergey Levine,et al.  Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection , 2016, Int. J. Robotics Res..

[7]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[8]  Gérard G. Medioni,et al.  Object modelling by registration of multiple range images , 1992, Image Vis. Comput..

[9]  Max Jaderberg,et al.  Unsupervised Learning of 3D Structure from Images , 2016, NIPS.

[10]  François Laviolette,et al.  Domain-Adversarial Training of Neural Networks , 2015, J. Mach. Learn. Res..

[11]  Sergey Levine,et al.  Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Razvan Pascanu,et al.  Progressive Neural Networks , 2016, ArXiv.

[13]  Wolfram Burgard,et al.  A Probabilistic Framework for Learning Kinematic Models of Articulated Objects , 2011, J. Artif. Intell. Res..

[14]  Oliver Brock,et al.  Online interactive perception of articulated objects with multi-level recursive estimation based on task-specific priors , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Razvan Pascanu,et al.  Sim-to-Real Robot Learning from Pixels with Progressive Nets , 2016, CoRL.

[16]  Wolfram Burgard,et al.  Multimodal deep learning for robust RGB-D object recognition , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[17]  Marc Toussaint.  A Tutorial on Newton Methods for Constrained Trajectory Optimization and Relations to SLAM, Gaussian Process Smoothing, Optimal Control, and Probabilistic Inference , 2017, Geometric and Numerical Foundations of Movements.

[18]  Dieter Fox,et al.  SE3-nets: Learning rigid body motion using deep neural networks , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Eric Mjolsness,et al.  New Algorithms for 2D and 3D Point Matching: Pose Estimation and Correspondence , 1998, NIPS.

[20]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.