Contact state estimation using machine learning

In this paper we present an approach that uses machine learning to determine the location of a contact between a gripper and a T-bar valve based on force/torque sensor data. The robot performs an exploratory behaviour that produces distinct force/torque data for each contact location of interest: no contact, a contact aligned with the central axis of the valve, and an off-center contact. Probabilistic clustering is utilised to transform the multidimensional data into a one-dimensional sequence of symbols, which is then used to train a hidden Markov model classifier. We present the results of an experiment where the learned classifier can predict a contact location with an accuracy of 97% on an unseen dataset.

[1]  Antonella Ferrara,et al.  AMADEUS: advanced manipulation for deep underwater sampling , 1997, IEEE Robotics Autom. Mag..

[2]  Konstantinos Kyriakopoulos,et al.  Persistent Autonomy: the Challenges of the PANDORA Project , 2012 .

[3]  Yongji Wang,et al.  AMADEUS: advanced manipulator for deep underwater sampling , 1997, Proceedings of International Conference on Robotics and Automation.

[4]  Nawid Jamali,et al.  Slip prediction using Hidden Markov models: Multidimensional sensor data to symbolic temporal pattern learning , 2012, 2012 IEEE International Conference on Robotics and Automation.

[5]  Junku Yuh,et al.  Underwater autonomous manipulation for intervention missions AUVs , 2009 .

[6]  David L. Dowe,et al.  MML clustering of multi-state, Poisson, von Mises circular and Gaussian distributions , 2000, Stat. Comput..

[7]  David A. Anisi,et al.  Real-world demonstration of sensor-based robotic automation in oil & gas facilities , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Mongi A. Abidi,et al.  Autonomous robotic inspection and manipulation using multisensor feedback , 1991, Computer.

[9]  Darwin G. Caldwell,et al.  Autonomous robotic valve turning: A hierarchical learning approach , 2013, 2013 IEEE International Conference on Robotics and Automation.

[10]  Frank Kirchner,et al.  A small-scale actuator with passive-compliance for a fine-manipulation deep-sea manipulator , 2011, OCEANS'11 MTS/IEEE KONA.

[11]  C. S. Wallace,et al.  An Information Measure for Classification , 1968, Comput. J..

[12]  Pedro J. Sanz,et al.  Combining template tracking and laser peak detection for 3D reconstruction and grasping in underwater environments , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.