http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Deep Reinforcement Learning for Traffic Signal Control Considering Adjacent Intersection States
Junseok Kim,Hwasoo Yeo 대한교통학회 2022 대한교통학회 학술대회지 Vol.87 No.-
Recently, various studies have been conducted on reinforcement learning for traffic signal control. However, these studies have a limited environment and didnt consider the perspective of drivers. It will be possible to operate a coordinated signal for the drivers predictability and a cycle with a realistic minimum green time. In this study, to achieve these two objectives, we studied whether the coordinated signal situation can be learned considering the state of the adjacent intersection. Reinforcement learning is used for optimization, the state of adjacent intersections was reflected and an appropriate reward was found. In addition, more methodologies for coordination and actual road network data will be applied. It is expected that future research can be expanded to a multi-intersection environment and intersections between coordinated arteries to progress vehicles.
Kyowon Song,Hwasoo Yeo,문정호 한국항공우주학회 2021 International Journal of Aeronautical and Space Sc Vol.22 No.4
In this study, we proposed concepts of a vertiport airspace design that must precede for the practical operation of urban air mobility, an emerging new urban mobility solution. We developed algorithms to find the optimal radius of airspace for each concept and, through simulations, derived comparisons among them. We also introduced the concept of a vertiport terminal control area where an personal air vehicle (PAV) approach control is performed, which consists of holding points and holding circles. Two strategies of PAV movement into the inner holding circles were proposed: the sequence-based approach (SBA) and the branch-queuing approach (BQA). The efficiency of these strategies was compared through a simulation, which demonstrated that the SBA is suitable for a space-constrained vertiport design and the BQA for a safer airspace design.
Development of a Deceleration-Based Surrogate Safety Measure for Rear-End Collision Risk
Sehyun Tak,Sunghoon Kim,Hwasoo Yeo IEEE 2015 IEEE transactions on intelligent transportation sy Vol.16 No.5
<P>A surrogate safety measure can be used for preventing hazardous roadway events by evaluating the potential safety risk by using information on the driving environment gathered from vehicles. In this paper, the deceleration-based surrogate safety measure (DSSM) is proposed as a safety indicator for rear-end collision risk evaluation based on the safety conditions and the decision-making process during human driving. The DSSM shows how drivers deal with collision risk differently in acceleration and deceleration phases. The proposed surrogate safety model has been validated for severe deceleration behavior, which is a driver-critical behavior in high-risk situations of collision based on microscopic vehicle trajectory data. The results indicate that there is a strong relationship between the proposed surrogate safety measures and crash potential. The measure could be used for collision warning and collision avoidance systems. It has a merit in that it reflects the characteristics of both vehicle (e.g., mechanical braking capability) and driver (e.g., preference for certain acceleration rates).</P>