Active estimation of object dynamics parameters with tactile sensors

The estimation of parameters that affect the dynamics of objects—such as viscosity or internal degree of freedom—is an important step in autonomous and dexterous robotic manipulation of objects. However, accurate and efficient estimation of these object parameters may be challenging due to complex, highly nonlinear underlying physical processes. To improve on the quality of otherwise hand-crafted solutions, automatic generation of control strategies can be helpful. We present a framework that uses active learning to help with sequential gathering of data samples,using information-theoretic ciriteria to find the optimal actions to perform at each time step. We demonstrate the usefulness of our approach on a robotic hand-arm setup, where the task involves shaking bottles of different liquids in order to determine the liquid's viscosity from only tactile feedback. We optimize the shaking frequency and the rotation angle of shaking in an online manner in order to speed up convergence of estimates.

[1]  Sethu Vijayakumar,et al.  Active Sequential Learning with Tactile Feedback , 2010, AISTATS.

[2]  Hod Lipson,et al.  Resilient Machines Through Continuous Self-Modeling , 2006, Science.

[3]  C. Rasmussen,et al.  Gaussian Process Priors with Uncertain Inputs - Application to Multiple-Step Ahead Time Series Forecasting , 2002, NIPS.

[4]  Minoru Asada,et al.  Object Category Acquisition by Dynamic Touch , 2008, Adv. Robotics.

[5]  Nando de Freitas,et al.  A Bayesian exploration-exploitation approach for optimal online sensing and planning with a visually guided mobile robot , 2009, Auton. Robots.

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

[7]  Weifeng Liu,et al.  An Information Theoretic Approach of Designing Sparse Kernel Adaptive Filters , 2009, IEEE Transactions on Neural Networks.

[8]  Lucas Paletta,et al.  Active object recognition by view integration and reinforcement learning , 2000, Robotics Auton. Syst..

[9]  Yuki Suga,et al.  Dynamic perception after visually guided grasping by a human-like autonomous robot , 2006, Adv. Robotics.

[10]  Zoubin Ghahramani,et al.  Sparse Gaussian Processes using Pseudo-inputs , 2005, NIPS.

[11]  Uwe D. Hanebeck,et al.  Analytic moment-based Gaussian process filtering , 2009, ICML '09.

[12]  John Hollerbach,et al.  Rigid body load identification for manipulators , 1985, 1985 24th IEEE Conference on Decision and Control.

[13]  Carl E. Rasmussen,et al.  In Advances in Neural Information Processing Systems , 2011 .

[14]  Stefano Nolfi,et al.  Active categorical perception in an evolved anthropomorphic robotic arm , 2009, 2009 IEEE Congress on Evolutionary Computation.

[15]  S. Takamuku,et al.  Haptic discrimination of material properties by a robotic hand , 2007, 2007 IEEE 6th International Conference on Development and Learning.

[16]  Joachim Denzler,et al.  Information Theoretic Sensor Data Selection for Active Object Recognition and State Estimation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..