Abstract
Based on lane positional information, vehicle parameters, and driver intent, the identification of dangerous area within vehicles operation is proposed in this paper. The criticality of the situation calculated by sparse Bayesian learning methodology is not a certain value, but the probability. Therefore, the method can forecast the effects of the uncertain parameters on the dangerous spacing in the vehicle driving process. Analysis of the data for driver behavior is performed using a sparse Bayesian learning methodology. Quantitative results and analysis of the experimental trials are presented to show the feasibility and promise of this identification method of minimum dangerous area. The objective of this paper is to lay a necessary foundation for the future intelligent advanced driver-assistance systems.
| Original language | English |
|---|---|
| Pages (from-to) | 41-44 |
| Number of pages | 4 |
| Journal | Journal of Beijing Institute of Technology (English Edition) |
| Volume | 19 |
| Issue number | SUPPL. 2 |
| Publication status | Published - Dec 2010 |
Keywords
- Dangerous area
- Driver behavior
- Driver intent
- Sparse Bayesian learning (SBL)