HMM based autarkic reconstruction of motorcycle behavior from low-cost inertial measurements

Abstract

Based on autarkic data from a low-cost, 6-axes inertial measurement unit (IMU), which is fixed onto and power-supplied by the motorcycles battery, we reconstruct forward velocity and elementary driving behavior of a motorcycle using a Hidden Markov Model (HMM). The notorious drift problem of integrated IMU data is mastered by using the voltage fluctuations of the motorcycle's battery as a stabilizing external signal. Despite the structural simplicity of the algorithm and the relatively low performance of the IMU, the proposed off-line estimator is, after a short learning phase, accurate for a large class of motorcycles. © Springer-Verlag Berlin Heidelberg 2011.