Identification of driver’s braking intention based on a hybrid model of GHMM and GGAP-RBFNN

Geodesic Basis Function Neural Network

In the learning of existing radial basis function neural networks-based methods, it is difficult to propagate errors back. This leads to an inconsistency between the learning and recognition task. This article proposes a geodesic basis function neural network with subclass extension learning (GBFNN-ScE). The geodesic basis function (GBF), which is defined here for the first time, uses the geodetic distance in the manifold as a measure to obtain the response of the sample with respect to the local center. To learn network parameters by back-propagating errors for the purpose of correct classification, a specific GBF based on a pruned gamma encoding cosine function is constructed. This function has a concise and explicit expression on the hyperspherical manifold, which is conducive to the realization of error back propagation. In the preprocessing layer, a sample unitization method with no loss of information, nonnegative unit hyperspherical crown (NUHC) mapping, is proposed. The sample can be mapped to the support set of the GBF. To alleviate the problem that one-hot encoding is not effective enough in the differential expression of data labels within a class, a subclass extension (ScE) learning strategy is proposed. The ScE learning strategy can help the learned network be more robust. For the working of GBFNN-ScE, the original sample is projected onto the support set of GBF through the NUHC mapping. Then the mapped samples are sent to the nonlinear computation units composed of GBFs in the hidden layer. Finally, the response obtained in the hidden layer is weighted by the learned weight to obtain the network output. This article theoretically proves that the separability of the data with ScE learning is stronger. The experimental results show that the proposed GBFNN-ScE has a better performance in recognition tasks than existing methods. The ablation experiments show that the ideas of the GBFNN-ScE contribute to the algorithm performance.

A Lateral Control Method of Intelligent Vehicles Based on Shared Control

This paper studies the lateral control problem for intelligent vehicles based on the concept of shared control. Considering the participation of drivers in the control loop, a shared control-based lateral controller is designed, which consists of two differed controllers: one is an LQR-based autonomous driving controller and the other is a driver’s intention-based fuzzy controller. For the vehicle dynamic model with two-degrees of freedom, an autonomous driving controller based on LQR and a driver’s intention-based fuzzy controller are designed. Then, the lateral controller based on shared control is constructed, which integrates the aforementioned two controllers. Finally, the co-simulation by MATLAB/Simulink and Carsim is presented. Furthermore, simulation results show that the designed lateral controller can track the desired path with better performance than the LQR-based autonomous driving controller.

Driver Response Time and Age Impact on the Reaction Time of Drivers: A Driving Simulator Study among Professional-Truck Drivers

Drivers’ response time means that drivers act after a judgment is made when an emergency action signal is needed. Drivers have different feelings while driving, and the response time to sudden situations differs. The main purpose of this study was to verify whether the mean reaction time of professional drivers is at the level of one second, which is the value usually used for practical purposes, and to verify the impact of age on the reaction times of drivers. Two different studies with a total of 120 participants—professional drivers—were conducted on the simulator, with 116 drivers participating in the first experiment and four drivers participating in the second experiment using eye-tracking technology. The determination of the mean reaction time was realized using statistical tests. The evaluation of the impact of age on the reaction time of professional drivers was carried out using statistical testing, a regression model, and clustering. The results of this study can be immediately used in practice for professional drivers, as the mean reaction time is usually used as a benchmark in several calculations in transport, for forensic and educational purposes, and for planning traffic and modelling different traffic situations.

Control Oriented Prediction of Driver Brake Intention and Intensity Using a Composite Machine Learning Approach

Driver perception, decision, and control behaviors are easily affected by traffic conditions and driving style, showing the tendency of randomness and personalization. Brake intention and intensity are integrated and control-oriented parameters that are crucial to the development of an intelligent braking system. In this paper, a composite machine learning approach was proposed to predict driver brake intention and intensity with a proper prediction horizon. Various driving data were collected from Controller Area Network (CAN) bus under a real driving condition, which mainly contained urban and rural road types. ReliefF and RReliefF (they don’t have abbreviations) algorithms were employed as feature subset selection methods and applied in a prepossessing step before the training. The rank importance of selected predictors exhibited different trends or even negative trends when predicting brake intention and intensity. A soft clustering algorithm, Fuzzy C-means, was adopted to label the brake intention into categories, namely slight, medium, intensive, and emergency braking. Data sets with misplaced labels were used for training of an ensemble machine learning method, random forest. It was validated that brake intention could be accurately predicted 0.5 s ahead. An open-loop nonlinear autoregressive with external input (NARX) network was capable of learning the long-term dependencies in comparison to the static neural network and was suggested for online recognition and prediction of brake intensity 1 s in advance. As system redundancy and fault tolerance, a close-loop NARX network could be adopted for brake intensity prediction in the case of possible sensor failure and loss of CAN message.