Predicting Lane Keeping Behavior of Visually Distracted Drivers Using Inverse Suboptimal Control
URL: http://arxiv.org/abs/1604.03984v3
archive: archived pipeline: cataloged verified
Abstract
Driver distraction strongly contributes to crash-risk. Therefore, assistance systems that warn the driver if her distraction poses a hazard to road safety, promise a great safety benefit. Current approaches either seek to detect critical situations using environmental sensors or estimate a driver's attention state solely from her behavior. However, this neglects that driving situation, driver deficiencies and compensation strategies altogether determine the risk of an accident. This work proposes to use inverse suboptimal control to predict these aspects in visually distracted lane keeping. In contrast to other approaches, this allows a situation-dependent assessment of the risk posed by distraction. Real traffic data of seven drivers are used for evaluation of the predictive power of our approach. For comparison, a baseline was built using established behavior models. In the evaluation our method achieves a consistently lower prediction error over speed and track-topology variations. Additionally, our approach generalizes better to driving speeds unseen in training phase.
Summary
Applies inverse suboptimal control to predict lane-keeping behavior of visually distracted drivers using real traffic data from seven drivers. The approach jointly models situation, driver compensation strategies, and deficiencies, enabling situation-dependent risk assessment rather than relying solely on environment sensors or driver-state estimation. Outperforms baseline behavior models on prediction error across speed and track-topology variations and generalizes better to driving speeds unseen during training.
Key finding
Inverse suboptimal control yields lower lane-keeping prediction error and better generalization across speeds than baseline models, supporting situation-aware distraction risk assessment.
Methodology
Inverse suboptimal control fitted to real-traffic lane-keeping data from 7 drivers; comparative evaluation against established behavior-model baselines.
Sample size: 7
Quality score: 5 / 5