yuu.nakajima <replace-this-with-atmark>
is.sci.toho-u.ac.jp
In order to model diverse traffic situations, such as vehicular traffic with significant numbers of senior drivers, it is essential to model the individuality of drivers; almost all previous works on multiagent simulation assumed the uniform driver model. In order to accomplish the key issue, I propose a novel methodology that can model each driver’s individual behaviour. The proposed approach uses a 3D virtual driving simulator to collect realistic driving log data from human subjects. We extract driving rules from the log data by interviewing each subject. We then construct unique driving models, which can explain each driver’s behaviour, by the application of hypothetical reasoning. In our research, we show that our proposed method can generate driving models which represent different types of driving styles.
In a guidance system which uses ubiquitous information infrastructure on a city, the system can acquire information of each individual user in real time. However, quantity of the information becomes enormous. There occurs a problem that a human who control system cannot handle all the information. Our approach is that a human gives rough navigation to agents and the agents give precise navigation to each person. We aim at realizing a mega scale navigation system using GPS-capable cellular phones.
A system which provides personalized navigation on city space can be developed based on a massively multi-agent system. In our research, an evacuation system, which uses multi-agent simulation and assumes a disaster in city, was implemented. Using this system, an evacuation experiment was conducted using real world human subjects and virtual space simulation agents. The system informed human evacuees of situation of the simulation by sending evacuation information to GPS mobile phones. As a result, the system succeeded in letting subjects feel the existence of crowds. Moreover, the scalability of the system was also confirmed in a performance evaluation.
Please, read Copyright Policy before downloading following pdf files.
Please, read Copyright Policy before downloading following pdf files.