| 研究実績の概要 |
In the first year of this research project, we have smooth progress in achieving the targeted outcomes. The fundamental framework of the cyber-physical traffic network for coordinating connected automated vehicles at an intersection is developed. A multi-agent-based traffic signal optimization scheme is formulated that can flexibly coordinate any number of vehicles for their smooth crossing the intersection. The vehicles as physical agents may pass the intersection smoothly utilizing the timings of traffic lights provided in advance. In cyberspace, the durations of upcoming traffic lights are computed by a group of cyber agents using a stochastic gradient-based method known as broadcast control of multi-agent systems.
In addition, as planned, we have developed a fuzzy tuned vehicle control scheme for eco-driving that utilizes road grade information from a digital road map. The proposed schemes are evaluated through microscopic traffic simulation at various penetration rates of the automated vehicles, and performances are compared with the existing schemes.
Besides the above works, already published in high-impact journals, we also have considerable progress in developing intelligent driving system for automated vehicles on multi-lane roads based on intervehicle and infrastructure-based communication. We are extending our cyber-physical system coverage for service-oriented parking management systems considering individual comfort and sustainability to meet the goal of a future smart city towards smart living.
|
| 今後の研究の推進方策 |
With the expected progress in the first year, we would like to extend the cyber-physical traffic control network further in the 2nd year and onward. Firstly, the overall framework will be extended for a more extensive road network, and a cloud-based coordination mechanism among the intersections will be developed. The control schemes will be extended for a non-signalized intersection, and ramp merging, and roundabouts. The multi-lane vehicle control scheme will be extended further by incorporating two-way “ cooperation” (direct or indirect) and cooperation with traffic signal systems. Secondly, cooperative control of automated vehicles using connected vehicle information will be developed for promoting eco-driving. Particularly, in this development, AI and machine learning techniques will be introduced for smarter driving using broadcasted traffic information. Finally, using the city network, the individual control schemes will be integrated under the proposed hierarchical cyber-physical framework using a traffic simulator. Through fine-tuning of the systems, the quality of transport services and safety, user comforts, and impacts on the environment will be evaluated. Finally, by extending international collaboration, new research directions incorporating other modes of transport, transport services, transport network design will be explored. As the supportive technology, new AI and machine learning based technology will also be investigated to the schemes.
|
| 次年度使用額が生じた理由 |
Due to pandemic, the intention for attending international conference and collaboration meeting are changed. Although some amount remains, it was used for purchasing some software and computing devices, and a part is kept unused for the next year.
|
