Bayesian Hybrid Model-State Estimation Applied to Simultaneous Contact Formation Recognition and Geometrical Parameter Estimation

In this paper we describe a Bayesian approach to model selection and state estimation for sensor-based robot tasks. The approach is illustrated with a hybrid model-state estimation example from force-controlled autonomous compliant motion: simultaneous (discrete) contact formation recognition and estimation of (continuous) geometrical parameters. Previous research in this area mostly tries to solve one of the two subproblems, or treats the contact formation recognition problem separately, avoiding integration between the solutions to the contact formation recognition and the geometrical parameter estimation problems. A more powerful hybrid model, explicitly modeling contact formation transitions, is developed to deal with larger uncertainties. This paper demonstrates that Kalman filter variants have limits: iterated extended Kalman filters can only handle small uncertainties on the geometrical parameters, while the non-minimal state Kalman filter cannot deal with model selection. Particle filters can handle the increased level of model complexity. Explicit measurement equations for the particle filter are derived from the implicit kinematic and energetic constraints. The experiments prove that the particle filter approach successfully estimates the hybrid joint posterior density of the discrete contact formation variable and the 12-dimensional, continuous geometrical parameter vector during the execution of an assembly task. The problem shows similarities with the well-known problems of data association in simultaneous localization and map-building (SLAM) and model selection in global localization.

[1]  Yasuyuki Funahashi,et al.  Parameter identification of contact conditions by active force sensing , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[2]  Joris De Schutter,et al.  Polyhedral contact formation identification for autonomous compliant motion: exact nonlinear bayesian filtering , 2005, IEEE Transactions on Robotics.

[3]  W. Gilks,et al.  Following a moving target—Monte Carlo inference for dynamic Bayesian models , 2001 .

[4]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[5]  P. Perona,et al.  Motion estimation via dynamic vision , 1996, IEEE Trans. Autom. Control..

[6]  Nando de Freitas,et al.  The Unscented Particle Filter , 2000, NIPS.

[7]  Jing Xiao,et al.  A divide-and-merge approach to automatic generation of contact states and planning of contact motion , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[8]  Jun S. Liu,et al.  Sequential importance sampling for nonparametric Bayes models: The next generation , 1999 .

[9]  Robert D. Howe,et al.  Contact State Estimation Using Multiple Model Estimation and Hidden Markov Models , 2004, Int. J. Robotics Res..

[10]  Herman Bruyninckx,et al.  Markov techniques for object localisation with force-controlled robots , 2001 .

[11]  Hendrik Van Brussel,et al.  Compliant Robot Motion II. A Control Approach Based on External Control Loops , 1988, Int. J. Robotics Res..

[12]  Wolfram Burgard,et al.  A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots , 1998, Auton. Robots.

[13]  A. Doucet,et al.  Parameter estimation in general state-space models using particle methods , 2003 .

[14]  Gerald J. Bierman,et al.  Numerical comparison of kalman filter algorithms: Orbit determination case study , 1977, Autom..

[15]  G. Kitagawa.  A self-organizing state-space model , 1998 .

[16]  Herman Bruyninckx,et al.  Contact Transitions Tracking During Force-Controlled Compliant Motion Using an Interacting Multiple Model Estimator , 2002 .

[17]  Michael O. Kolawole,et al.  Estimation and tracking , 2002 .

[18]  Joris De Schutter,et al.  Polyhedral contact formation modeling and identification for autonomous compliant motion , 2003, IEEE Trans. Robotics Autom..

[19]  Sebastian Thrun,et al.  Simultaneous localization and mapping with unknown data association using FastSLAM , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[20]  Jing Xiao,et al.  Automatic Generation of High-Level Contact State Space , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[21]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[22]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.

[23]  L. M. M.-T..  Theory of Probability , 1929, Nature.

[24]  Yaakov Bar-Shalom,et al.  Estimation and Tracking: Principles, Techniques, and Software , 1993 .

[25]  H. Harry Asada,et al.  Representation and learning of nonlinear compliance using neural nets , 1993, IEEE Trans. Robotics Autom..

[26]  Joris De Schutter,et al.  Exact non-linear Bayesian parameter estimation for autonomous compliant motion , 2004, Adv. Robotics.

[27]  Geir Hovland,et al.  Hidden Markov Models as a Process Monitor in Robotic Assembly , 1998, Int. J. Robotics Res..

[28]  Blake Hannaford,et al.  Hidden Markov Model Analysis of Force/ Torque Information in Telemanipulation , 1989, ISER.

[29]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[30]  Joris De Schutter,et al.  Estimating First-Order Geometric Parameters and Monitoring Contact Transitions during Force-Controlled Compliant Motion , 1999, Int. J. Robotics Res..

[31]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[32]  Tine Lefebvre,et al.  Contact modelling, parameter identification and task planning for autonomous compliant motion using elementary contacts , 2003 .

[33]  Y. Bar-Shalom.  Tracking and data association , 1988 .

[34]  Joris De Schutter,et al.  Construction of a geometric 3-D model from sensor measurements collected during compliant motion , 2006, ISER.

[35]  Michael A. West,et al.  Combined Parameter and State Estimation in Simulation-Based Filtering , 2001, Sequential Monte Carlo Methods in Practice.

[36]  Hendrik Van Brussel,et al.  Compliant Robot Motion I. A Formalism for Specifying Compliant Motion Tasks , 1988, Int. J. Robotics Res..

[37]  Brian S. Eberman.  A Model-Based Approach to Cartesian Manipulation Contact Sensing , 1997, Int. J. Robotics Res..

[38]  Hirohisa Hirukawa,et al.  A motion planning algorithm for convex polyhedra in contact under translation and rotation , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[39]  Herman Bruyninckx,et al.  An open software framework for Bayesian state and parameter estimation , 2002 .

[40]  Brian D. Ripley,et al.  Stochastic Simulation , 2005 .

[41]  M. Pitt,et al.  Filtering via Simulation: Auxiliary Particle Filters , 1999 .

[42]  Jun S. Liu,et al.  Sequential Monte Carlo methods for dynamic systems , 1997 .

[43]  Xuerong Ji,et al.  Automatic Generation of High-Level Contact State Space , 2001, Int. J. Robotics Res..

[44]  Herman Bruyninckx,et al.  Kalman filters for non-linear systems: a comparison of performance , 2004 .

[45]  Eduardo Mario Nebot,et al.  Real time data association for FastSLAM , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[46]  Richard A. Volz,et al.  Identifying single-ended contact formations from force sensor patterns , 2000, IEEE Trans. Robotics Autom..

[47]  Walter R. Gilks,et al.  RESAMPLE-MOVE Filtering with Cross-Model Jumps , 2001, Sequential Monte Carlo Methods in Practice.

[48]  BurgardWolfram,et al.  A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots , 1998 .