Driving Skill Modeling Using Neural Networks for Performance-based Haptic Assistance
This addresses training novice drivers with haptic feedback, but it is incremental as it builds on existing data-driven and haptic assistance methods.
This paper tackled the problem of modeling expert driving skills for haptic assistance using neural networks, resulting in a skill model that captured steering/pedaling skills and haptic assistance that helped novices perform steering like experts but not pedaling.
This paper addresses a data-driven framework, modeling expert driving skills for performance-based haptic assistance using neural networks (NNs). We have built a haptic driving training simulator to collect expert driving data and to provide proper haptic feedback. We establish an expert driving skill model by training NNs with the collected data. Then, the skill model is applied to performance-based haptic assistance to provide optimized references of the steering/pedaling movements. We evaluate the skill model and its application to performance-based haptic assistance in two user experiments. The results of the first experiment demonstrate that our skill model has appropriately captured experts' steering/pedaling skills. The results of the second experiment show that our performance-based haptic assistance can help novice drivers perform steering as expert drivers, but cannot assist their pedaling performance.