Sensor Calibration and Hysteresis Compensation With Heteroscedastic Gaussian Processes

We deal with the problem of estimating the true measured scalar quantity from the output signal of a sensor that is afflicted with hysteresis and noise. We use a probabilistic, nonparametric sensor model based on heteroscedastic Gaussian processes (GPs), which is trained using a data set of sensor output and ground truth pairs. The inference problem is formulated as state estimation in a dynamical system. We exploit the low dimensionality of the latent state space of the sensor to perform exact probabilistic inference of the measured quantity from a time series of the sensor's output. Compared with the state-of-the-art assumed density filtering algorithm for GPs, which analytically approximates the posterior by a normal distribution during inference, our method reduces the prediction error by 33% on a data set obtained from a novel flexible tactile sensor based on carbon-black filled elastomers. The proposed model can be applied, but is not limited, to any sensor for which the Preisach model of hysteresis holds. The use of probabilistic modeling and inference not only provides a most likely estimate of the measured quantity but also the corresponding confidence interval.

[1]  Greg Welch,et al.  Welch & Bishop , An Introduction to the Kalman Filter 2 1 The Discrete Kalman Filter In 1960 , 1994 .

[2]  Bernhard G. Zagar,et al.  Smart hysteresis compensation of a magneto-elastic force sensor based on Terfenol-D , 2010, 2010 IEEE Instrumentation & Measurement Technology Conference Proceedings.

[3]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[4]  B. Persson On the theory of rubber friction , 1998 .

[5]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[6]  J Dargahi,et al.  Human tactile perception as a standard for artificial tactile sensing—a review , 2004, The international journal of medical robotics + computer assisted surgery : MRCAS.

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

[8]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[9]  D. Schneider,et al.  The DLR artificial skin step II: Scalability as a prerequisite for whole-body covers , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Dieter Fox,et al.  GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation models , 2008, IROS.

[11]  Rudolph van der Merwe,et al.  The unscented Kalman filter for nonlinear estimation , 2000, Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No.00EX373).

[12]  Ciro Visone,et al.  Hysteresis modelling and compensation for smart sensors and actuators , 2008 .

[13]  X. Jin Factor graphs and the Sum-Product Algorithm , 2002 .

[14]  Michael I. Jordan,et al.  Loopy Belief Propagation for Approximate Inference: An Empirical Study , 1999, UAI.

[15]  Robert A. Shanks,et al.  General Purpose Elastomers: Structure, Chemistry, Physics and Performance , 2013 .

[16]  Dieter Fox,et al.  Gaussian Processes and Reinforcement Learning for Identification and Control of an Autonomous Blimp , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[17]  Wolfram Burgard,et al.  Most likely heteroscedastic Gaussian process regression , 2007, ICML '07.

[18]  Gerd Hirzinger,et al.  The DLR artificial skin step I: Uniting sensitivity and collision tolerance , 2013, 2013 IEEE International Conference on Robotics and Automation.

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

[20]  Jung-Fu Cheng,et al.  Turbo Decoding as an Instance of Pearl's "Belief Propagation" Algorithm , 1998, IEEE J. Sel. Areas Commun..

[21]  Stefania Campopiano,et al.  Compensation of hysteresis in magnetic field sensors employing Fiber Bragg Grating and magneto-elastic materials , 2008 .

[22]  Paul W. Goldberg,et al.  Regression with Input-dependent Noise: A Gaussian Process Treatment , 1997, NIPS.

[23]  Brendan J. Frey,et al.  Factor graphs and the sum-product algorithm , 2001, IEEE Trans. Inf. Theory.

[24]  Giulio Sandini,et al.  Tactile Sensing—From Humans to Humanoids , 2010, IEEE Transactions on Robotics.