Rigid Body Dynamics Estimation by Unscented Filtering Pose Estimation Neural Networks

In this paper, we consider the task of estimating the state of dynamic object by applying an unscented filter to pose estimates generated by a neural network. To incorporate the rotational state of the system into the filter, we use a parameterization of the tangent space of the group of rotation matrices SO(3). We then characterize the noise in the pose estimation neural network by considering simple motions of the object, as well as using a Monte Carlo approach. Finally, using synthetically generated images, we show in simulation how the unscented filter can improve the accuracy of the pose estimates from the neural network.

[1]  Nassir Navab,et al.  Long Short-Term Memory Kalman Filters: Recurrent Neural Estimators for Pose Regularization , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Pieter Abbeel,et al.  BigBIRD: A large-scale 3D database of object instances , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Pascal Fua,et al.  Real-Time Seamless Single Shot 6D Object Pose Prediction , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[4]  J. Junkins,et al.  Optimal Estimation of Dynamic Systems , 2004 .

[5]  Vincent Lepetit,et al.  BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[6]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[7]  D. Simon.  Optimal State Estimation: Kalman, H Infinity, and Nonlinear Approaches , 2006 .

[8]  Dieter Fox,et al.  Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects , 2018, CoRL.

[9]  Jean-Philippe Condomines,et al.  Unscented Kalman filtering on Lie groups , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[10]  Sergey Levine,et al.  Backprop KF: Learning Discriminative Deterministic State Estimators , 2016, NIPS.

[11]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[12]  Søren Hauberg,et al.  Unscented Kalman Filtering on Riemannian Manifolds , 2013, Journal of Mathematical Imaging and Vision.

[13]  Jeffrey K. Uhlmann,et al.  Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.

[14]  Dieter Fox,et al.  PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes , 2017, Robotics: Science and Systems.