Trajectory Prediction for Powered Two Wheelers with Deep Learning

The development of active safety systems for powered two wheelers (PTW) plays an important role to reduce the number of accidents involving PTW. Future Advanced Rider Assistance Systems (ARAS) will require information about the riding intention. The calculation of a trajectory in the upcoming seconds of the ride is one way to describe this intention. The presented work pursues the prediction of the PTW lateral dynamic state by means of a roll angle trajectory over the upcoming 4 s of riding. Inputs for the prediction model are PTW internal signals only, that are measurements of vehicle dynamics, rider inputs, and rider behavior. A deep learning model that is based on long short-term memory layers is used and tuned using hyperparameter optimization. The importance of non-common rider input & behavior features is shown in an ablation study. The comparison with a basic prediction assumption reveals that the deep learning based roll angle trajectory prediction is a promising approach for the detection of the riding intention of PTW regarding lateral dynamics.