• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.4
• /
• pp.63-77
• /
• 2023

This study applies reinforcement learning to effectively operate expressway hard shoulder running (HSR). An HSR algorithm was developed, and its effectiveness was evaluated using the VISSIM microscopic simulation program. The simulation evaluated two aspects: mobility and safety. The DQN-based HSR algorithm found speed improvement of up to 26 km/h. Compared to the current method, the difference in the number of conflicts was not significant. Considering the results, a DQN-based HSR operation has a clear effect, and it is necessary to consider adjusting the current operational criteria.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.108-126
• /
• 2023

In this paper, the dynamic hard shoulder running for bus only (HSRFBO) was presented to solve the traffic congestion by increase the capacity in chronic congested sections of highways, and a simulation was performed to evaluate the comparison with the current hard shoulder running for all vehicles(HSRFAV) and median bus only lane and HSR(MBOLHSR). According to the evaluation results, it was evaluated to be more advantageous in terms of traffic flow and safety than the current HSRFAV. In addition, the speed of passing buses is slightly reduced compared to the MBOHSR, but the speed of entering and exiting buses is increased and the speed of buses and cars is greatly improved. Therefore It was analyzed that the efficiency of transport personnel was also improved. In particular, it is expected that traffic flow will be stabilized as the difference in speed between passenger cars and buses will be greatly reduced, and violations of exclusive bus lanes by passenger cars will be greatly reduced. In addition, the operation time of HSR is greatly reduced, so that the original function of the shoulder lane can be maintained as much as possible. As a result, it was analyzed that the risk of accidents was significantly reduced when operating HSRFBO compared to when operating MBOHSR, and cross-conflicts with high accident severity did not occur.

• Transportation Technology and Policy
• /
• v.5 no.4
• /
• pp.9-22
• /
• 2008

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.36-47
• /
• 2020

The objective of this study is to analyze the effect of the shoulder-use lane, which is a representative traffic management technique that increases the road capacity. The operation of the shoulder-use lane has been actively used as a countermeasure to improve traffic congestion, because it has the effect of improving traffic flow during rush hour. In Korea, the shoulder-use lanes are available at Gyeongbu, Yeongdong, and on the Seoul Outer Ring expressway, and their use is gradually increasing. Therefore, a comprehensive analysis was conducted to analyze the effects of the shoulder-use lane; including 1) analysis of individual shoulder lanes based on a time space diagram, and 2) analysis of shoulder lanes by road axis. These findings can contribute to the efficient installation and operation of shoulder-use lanes on expressways.