Multi-task Driver Steering Behaviour Modeling Using Time-Series Transformer

Abstract

Human intention prediction provides an augmented solution for the design of assistants and collaboration between the human driver and intelligent vehicles. In this study, a multi-task sequential learning framework is developed to predict future steering torques and steering postures based on the upper limb neuromuscular Electromyography (EMG) signals. A single-right-hand driving mode is particularly studied. For this driving mode, three different driving postures are also evaluated. Then, a multi-task time-series transformer network (MTS-Trans) is developed to predict the steering torques and driving postures. To evaluate the multi-task learning performance, four different frameworks are assessed. Twenty-one participants are involved in the driving simulator-based experiment. The proposed model achieved accurate prediction results on the future steering torque prediction and driving postures recognition for single-hand driving modes. The proposed system can contribute to the development of advanced driver steering assistant systems and ensure mutual understanding between human drivers and intelligent vehicles.