2013 Fiscal Year Final Research Report
Multi layered behavior modeling based on hierarchical mode segmentation
| Project/Area Number |
23760389
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Control engineering
|
|---|
| Research Institution | Nagoya University |
|---|
Principal Investigator |
OKUDA Hiroyuki 名古屋大学, グリーンモビリティ連携研究センター, 助教 (90456690)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Keywords | 人間機械システム / 行動モデル / ハイブリッドシステム |
|---|
| Research Abstract |
Understanding and modeling of the human behavior is the key technology to realize a human friendly human-machine collaborative system. Hierarchical structure is one of important features of the human behavior, and the mathematical representation of the human behavior considering the feature is approached in this research. Finally the hierarchical piece-wise auto-regressive and exogenous model(Hi-PWARX) and its identification algorithm was developed. Driving behavior on expressway is represented by the Hi-PWARX model and analyzed based on the obtained model parameters and the mode segmentation structure of the model. It is possible to change the abstraction level of expressing the driving behavior from the combinations of a few of abstract motions to combinations of many concrete motions, smoothly. So this model can trade off the computational burden to the model precision.
|
