Sensor Calibration and Hysteresis Compensation With Heteroscedastic Gaussian Processes
- 13 July 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 15 (11) , 6498-6506
Abstract
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.Keywords
Funding Information
- German Research Foundation (SPP 1527)
- European Commission Seventh Framework Program through the TACMAN Project (610967)
This publication has 17 references indexed in Scilit:
- The DLR artificial skin step II: Scalability as a prerequisite for whole-body covers2013
- The DLR artificial skin step I: Uniting sensitivity and collision tolerance2013
- Analytic moment-based Gaussian process filtering2009
- GP-BayesFilters: Bayesian filtering using Gaussian process prediction and observation modelsAutonomous Robots, 2009
- Hysteresis modelling and compensation for smart sensors and actuatorsJournal of Physics: Conference Series, 2008
- Most likely heteroscedastic Gaussian process regression2007
- Gaussian Processes and Reinforcement Learning for Identification and Control of an Autonomous BlimpProceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164), 2007
- The unscented Kalman filter for nonlinear estimation2002
- On the theory of rubber frictionSurface Science, 1998
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960