Construction of Personalized Driver Models based on LSTM using Driving Simulator.
2022-01-0981
03/29/2022
- Event
- Content
- The purpose of this study is to construct personalized driver models using Long Short-Term Memory (LSTM). The driver model is used for automated driving systems and driver assistance systems and is expected to control longitudinal and lateral directions of vehicles. For example, driver models including the individual driving characteristics adapt the control of systems, which can reduce discomfort and nuisance to drivers. The LSTM models in this study enable the time series data processing. In some previous studies, LSTM models have been used to investigate pedestrian behaviors. However, there are few studies of driver behavior models based on LSTM. In this study, we measured the data of the driver's driving operation using a Driving Simulator (DS). DS consists of a visual display and a motion display, of which motion functions consist of a 6-axis motion device and a turntable. DS has a cockpit using an actual body of a vehicle, and a visual information projected on a cylindrical screen. The road geometry in a section of a Tomei Expressway between Tokyo and Nagoya in Japan is simulated in DS. The expressway consists of straight and curved roads. Based on the data of the driving maneuvers on the expressway, personalized drivers' models are constructed using LSTM.
- Citation
- Hamada, A., Oikawa PhD, S., and Hirose, T., "Construction of Personalized Driver Models based on LSTM using Driving Simulator.," SAE Technical Paper 2022-01-0981, 2022, .