The effectiveness of driving simulator training on driving skills and safety in young novice drivers: A systematic review of interventions

Driver Steering Intention Prediction for Human-Machine Shared Systems of Intelligent Vehicles Based on CNN-GRU Network

In order to mitigate human-machine conflicts and optimize shared control strategy in advance, it is essential for the shared control system to understand and predict driver behavior. This paper proposes a method for predicting driver steering intention with a CNN-GRU hybrid machine learning model. The convolutional neural network (CNN) layer extracts features from the stochastic driver behavior, which is input to the gated-recurrent-unit (GRU) layer. And the driver's steering intention is forecasted based on the GRU model. Our study was conducted using a driving simulator to observe the lateral control behaviors of 18 participants in four different driving circumstances. Finally, the efficiency of the suggested prediction approach was evaluated employing long-short-term-memory, GRU, CNN, Transformer, and back propagation networks. Experimental results demonstrated that the proposed CNN-GRU model performs significantly better than baseline models. Compared with the GRU network, the CNN-GRU network reduced the RMSE, MAE, and MAPE of the driver's input torque by 33.22%, 32.33%, and 35.86%, respectively. The proposed prediction method also possesses adaptability to different driver behaviors.

An experimental comparison on the effectiveness of various levels of simulator fidelity on ab initio pilot training

Despite recent advances in technology use for education and training, the approach to pilot training over the past several decades has largely remained unchanged. Student pilots complete their training in actual aircraft, with very few flight hours conducted in flight training devices. This study aimed to investigate the effectiveness of various levels of simulator fidelity on ab initio pilot training. Thirty student pilots were invited to train using a virtual reality simulator, desktop simulator, or flight training device. Performance was evaluated using a modified Transport Canada Flight Test Guide alongside the NASA Task Load Index, Subjective Stress Scale, and Simulator Sickness Questionnaire, giving insight into mental workload, stress, and experience of simulator sickness, respectively. Findings show potential for virtual reality and desktop simulators regarding training procedural tasks; however, trainees must be aware of the limitations virtual reality and desktop simulators have concerning the training of aircraft handling tasks.