A Sensor Calibration Methodology for Evidence Theoretic Unmanned Ground Vehicle Localization

Abstract

We present a novel sensor calibration methodology that is suited to an evidence theoretic Unmanned Ground Vehicle (UGV) localization system. The proposed procedure for sensor calibration employs a series of designed experiments with the objective of creating parametric calibration models and forming a mass assignment table for a Dempster-Shafer belief system. Sensors calibrated include custom built magnetic encoders positioned at the rear wheels of the UGV, an accelerometer, a solid-state rate-gyro, a digital compass, and a Global Positioning System (GPS). The estimated parameters together with a mass assignment table are presented. This table is created for the GPS unit based on the factors that significantly impact the accuracy of the readings using an experimental procedure. We conclude with a brief summary of the main results.

¿-Filter: An Evidence Theoretic Approach to Unmanned Ground Vehicle Localization

“…As we employ the FHP-4WD-SMP platform for experimental validation, we use the calibration models presented in [26]. Low Pass Filters (LPFs) in the form of moving average filters are used to deal with vibration-induced noise.…”

“…Table II in [26]). The following computations are made using equation (2) for the latitude (x-axis) and the longitude (y-axis): ) ( (18) and (19).…”

“…1 in [26]), y v is the velocity along the y V -axis, z ω is the angular velocity about the z V -axis, and t is the time between updates. The input covariance matrix is given by ) , , (…”

“…The mass functions and the variances for the right hand side of equations (18), (19), and (20) are determined using values from Table I, Table II, and Table III in [26], and by combination as described in Section C. Further normalization is obviated by the following property [16]:…”

“…However, in the event of larger residuals due to low #Sat and high HDOP (see Fig. 6 in [26] for the variation of GPS error as a function of #Sat and HDOP), the -Filter performs better than the EKF with respect to GPS sensor goodness.…”