Characterizing Driving Styles with Deep Learning
This work addresses the need for better driving style representations in applications like autonomous driving and auto insurance, though it is incremental as it extends deep learning to a new domain.
The paper tackled the problem of characterizing driving styles from GPS data by proposing a novel deep learning solution, which achieved effective extraction of high-level, interpretable features and validated them through driver identification on a large real dataset.
Characterizing driving styles of human drivers using vehicle sensor data, e.g., GPS, is an interesting research problem and an important real-world requirement from automotive industries. A good representation of driving features can be highly valuable for autonomous driving, auto insurance, and many other application scenarios. However, traditional methods mainly rely on handcrafted features, which limit machine learning algorithms to achieve a better performance. In this paper, we propose a novel deep learning solution to this problem, which could be the first attempt of extending deep learning to driving behavior analysis based on GPS data. The proposed approach can effectively extract high level and interpretable features describing complex driving patterns. It also requires significantly less human experience and work. The power of the learned driving style representations are validated through the driver identification problem using a large real dataset.