Search

The accurate information of sideslip angle (SA) and tire cornering stiffness (TCS) is essential for advanced chassis control systems. However, SA and TCS cannot be directly measured by in-vehicle sensors. Thus, it is a hot topic to estimate SA and TCS with only in-vehicle sensors by an effective estimation method. In this article, we propose a novel fuzzy adaptive robust cubature Kalman filter (FARCKF) to accurately estimate SA and TCS. The model parameters of the FARCKF are dynamically updated using recursive least squares. A Takagi–Sugeno fuzzy system is developed to dynamically adjust the process noise parameter in the FARCKF. Finally, the performance of FARCKF is demonstrated via both simulation and experimental tests. The test results indicate that the estimation accuracy of SA and TCS is higher than that of the existing methods. Specifically, the estimation accuracy of SA is at least improved by more than 48%, while the estimators of TCS are closer to the reference values. [ABSTRACT FROM AUTHOR]

This article establishes a novel electroencephalograph (EEG)-based brain–computer interface (BCI) system for ground vehicle control with potential application of mobility assistance to the disabled. To enable an intuitive motor imagery (MI) paradigm of “left,” “right,” “push,” and “pull,” a driving simulator based EEG data recording and automatic labeling platform is built for dataset making. In the preprocessing stage, a wavelet and canonical correlation analysis (CCA) combined method is used for artifact removal and improving signal-to-noise ratio. An ensemble learning based training and testing framework is proposed for MI EEG data classification. The average classification accuracy of proposed framework is about 91.75%. This approach essentially takes advantage of the common spatial pattern (CSP) with ability of extracting the feature of event-related potentials and the convolutional neural networks (CNNs) with powerful capacity of feature learning and classification. To convert the classification results of EEG data segments into motion control signals of ground vehicle, shared control strategy is used to realize the control command of “left-steering,” “right-steering,” “acceleration,” and “stop” considering collision avoidance with obstacles detected by a single-line LIDAR. The online experimental results on a model vehicle platform validate the significant performance of the established BCI system and reveal the application potential of BCI on the vehicle control and automation. [ABSTRACT FROM AUTHOR]

Accurate knowledge of the vehicle states is the foundation of vehicle motion control. However, in real implementations, sensory signals are always corrupted by delays and noises. Network induced time-varying delays and measurement noises can be a hazard in the active safety of over-actuated electric vehicles (EVs). In this paper, a brain-inspired proprioceptive system based on state-of-the-art deep learning and data fusion technique is proposed to solve this problem in autonomous four-wheel actuated EVs. A deep recurrent neural network (RNN) is trained by the noisy and delayed measurement signals to make accurate predictions of the vehicle motion states. Then unscented Kalman predictor, which is the adaption of unscented Kalman filter in time-varying-delay situations, combines the predictions of the RNN and corrupted sensory signals to provide better perceptions of the locomotion. Simulations with a high-fidelity, CarSim, full-vehicle model are carried out to show the effectiveness of our RNN framework and the entire proprioceptive system. [ABSTRACT FROM AUTHOR]