Estimation of driver´s steering direction about lane change maneuver at the preceding car avoidance by brain source current estimation method

Vehicle technology regarding the interaction between human and the machine has been called human-electronics in Japan. It is necessary to achieve a better relationship between human and vehicle. A driver´s information, which can be obtained from steering operation, pedal operation, camera images and physiological information, particularly is crucial to find a method to determine a driver´s operational intention. It is beneficial to find a method to determine a driver´s operational intention. Therefore, we have focused on the brain activities in the biological information. The time frequency analysis such as FFT has been used in the traditional decomposition of the electroencephalogram (EEG). However, these conventional methods can only use two-dimensional data. In this paper, we described that the driver´s EEG during car following was decomposed by parallel factor analysis (PARAFAC), and we investigated the feature factor of longitudinal behavior for recognize and judgment from that decomposition result. PARAFAC analysis has known as a multi-channel EEG analysis of multi-dimensional data. In previous research [1], we investigated the driver´s EEG of during lane change maneuver using the parallel factor (PARAFAC) analysis. Consequently, all subjects have two common factors of the frequency component which exist in the 5-7 Hz and 8-13 Hz region. Those factors were located at the right frontpolar cortex and the precuneus posterior cingulate cortex, and this factor was changed by the driver´s mental state during visual recognition and judgment. In this paper, we estimated the driver´s intention from a driver´s EEG using source current distribution estimation with Hierarchical Bayesian method and the sparse logistic regression. From the estimation results, the estimation accuracy of driver´s intention was higher than about 70 % of three subject´s in the lateral operation.