• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.827-828
• /
• 2006

This paper presents a vehicle control algorithm for Personal Rapid Transit (PRT) system. PRT system is a one-way direction network system which is composed of guideway branches, merging/diverging points. Vehicle control algorithm can be divided into two kinds. Those are merging control algorithm and the other. We emphasized on the merging control algorithm. For that, we first devised a front/virtual front vehicle finding strategies. Properly determined front/virtual front vehicle is the starting point of vehicle control. The objects of merging control are to avoid collision and to pass the merging point fluently. Which implies that jerk constraint and limits of acceleration and deceleration etc. are should be considered. To verify the validation of the vehicle algorithm, we executed simulations and presented test results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.8
• /
• pp.907-913
• /
• 1999

For an automated transportation system like PRT(Personal Rapid Transit) system or IVHS, an efficient vehicle-merging algorithm is required for smooth operation of the network. For management of merging, collision avoidance between vehicles, ride comfort, and the effect on traffic should be considered. This paper proposes an unmanned vehicle-merging algorithm that consists of two procedures. First, a longitudinal control algorithm is designed to keep a safe headway between vehicles in a single lane. Secondly, 'vacant slot and ghost vehicle' concept is introduced and a decision algorithm is designed to determine the sequence of vehicles entering a converging section considering energy consumption, ride comfort, and total traffic flow. The sequencing algorithm is based on fuzzy rules and the membership functions are determined first by an intuitive method and then trained by a learning method using a neural network. The vehicle-merging algorithm is shown to be effective through simulations based on a PRT model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.186-191
• /
• 2020

In this paper, we proposed an optimization technique for efficiently placing vehicles on decks in a vehicle-carrying ship to efficiently handle loading and unloading. For this purpose, we utilized the transformation method of the XML data representing the ship's spatial information, merging and branching algorithm and genetic algorithm, and implemented the function to visualize the optimized vehicle placement results. The techniques of selection, crossover, mutation, and elite preservation, which are used in the conventional genetic algorithms, are used. In particular, the vehicle placement optimization method is proposed by merging and branching the ship space for the vehicle loading. The experimental results show that the proposed merging and branching method is effective for the optimization process that is difficult to optimize with the existing genetic algorithm alone. In addition, visualization results show vehicle layout results in the form of drawings so that experts can easily determine the efficiency of the layout results.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.62-73
• /
• 2020

Access management is aimed at preserving the road's high intercity mobility. In urbanized areas, immoderate acceleration lane-length requirements restrict the accessibility of land. Therefore, there are many opinions to revise the minimum acceleration lane-length requirement. For this purpose, it is important to diagnose the effects of slow vehicles on the mainline. This study analyzed a single merging vehicle's total delay occurrence depending on the mainline traffic flow rate and merging speed. A linear relationship was observed between the mainline traffic flow rate and total delay. As a merging speed increases gradually from 40km/h to 100km/h in 20km/h intervals, the total delay decreases by 5.0, 1.6, and 5.1 times, respectively. This shows that the ideal condition with the total delay is less than 0.5 vehicle·sec when there is no speed difference between the mainline and merging vehicle. On the other hand, given the one-second response time of drivers, the total delay occurrence was slightly low when the speed difference between the mainline and merging vehicle was less than 20km/h.

• Journal of Korean Institute of Industrial Engineers
• /
• v.16 no.2
• /
• pp.71-79
• /
• 1990

In this paper, the Double Shortest Arborescence & Merging method is presented as an efficient heuristic algorithm for the Public Vehicle Routing Problem which is to find the minimum total cost routes of M or less vehicles to traverse the required arcs(demand streets) at least once and return to their starting depot on a directed network. Double Shortest Arborescence which consists of forward shortest aborescence and backward one informs M or less shortest routes to traverse all required arcs. The number of these routes is reduced to M or less by merging routes. The computational experiment based on randomly generated networks reports that this algorithm is efficient.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.1
• /
• pp.63-71
• /
• 2024

Deep reinforcement learning (RL) significantly influences autonomous vehicle development by optimizing decision-making and adaptation to complex driving environments through simulation-based training. In deep RL, an activation function is used, and various activation functions have been proposed, but their performance varies greatly depending on the application environment. Therefore, finding the optimal activation function according to the environment is important for effective learning. In this paper, we analyzed nine commonly used activation functions for RL to compare and evaluate which activation function is most effective when using deep RL for autonomous vehicles to learn highway merging. To do this, we built a performance evaluation environment and compared the average reward of each activation function. The results showed that the highest reward was achieved using Mish, and the lowest using SELU. The difference in reward between the two activation functions was 10.3%.

• Journal of Positioning, Navigation, and Timing
• /
• v.6 no.4
• /
• pp.135-140
• /
• 2017

This paper proposes a signal merging algorithm to increase the signal-to-noise ratio (SNR) of a GPS correlator output to estimate the roll angle of a rotating vehicle in a weak GPS signal environment. Rotation Locked Loop (RLL) algorithm is used to estimate a roll angle using the characteristics that the power of the GPS signal measured at the receiver of a rotating vehicle varies periodically. First, delay times are calculated to synchronize GPS signals using satellites' and receiver's positions and the rotation frequency of a vehicle, and then correlator outputs are delayed in time and merged with each other, resulting in the increase of an SNR in a correlator output. Finally, simulations are conducted and the performance of the proposed algorithm is validated.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.192-192
• /
• 2000

In this paper, a platoon merging is considered as a remote-controlled system with the state represented by a stochastic process. In this system, it becomes to encounter situations where a single decision maker controls a large number of subsystems, and observation and control signals are sent over a communication channel with finite capacity and significant transmission delays. Unlike classical estimation problem in which the observation is a continuous process corrupted by additive noise, there is a constraint that the observation must be coded and transmitted over a digital communication channel with finite capaci쇼. A recursive coder-estimator sequence is a state estimation scheme based on observations transmitted with finite communication capacity constraint. Using the coder-estimator sequence, the remote control station designs a feedback controller. In this paper, we introduce a stochastic model for the lead vehicle in a platoon of vehicles considering the angle between a road surface and a horizontal plane as a stochastic process. The simulation results show that the inter-vehicle distance and the deviation from the desired inter-vehicle distance are well regulated.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.3
• /
• pp.9-23
• /
• 2015

A lane change maneuver which has a high driver cognitive workload and skills sometimes leads to severe traffic accidents. In this study, the Advanced Lane Change Assist System (ALCAS) was developed to assist with the automatic lane changes in merging sections which is mainly based on an automatic control algorithm for detecting an available gap, determining the Optimal Lane Change Start Point (OLCSP) in various traffic conditions, and positioning the merging vehicle at the OLCSP safely by longitudinal automatic controlling. The analysis of lane change behavior and modeling of fundamental lane change feature were performed for determining the default parameters and the boundary conditions of the algorithm. The algorithm was composed of six steps with closed-loop. In order to confirm the algorithm performance, numerical scenario tests were performed in various surrounding vehicles conditions. Moreover, feasibility of the developed system was verified in microscopic traffic simulation(VISSIM 5.3 version). The results showed that merging vehicles using the system had a tendency to find the OLCSP readily and precisely, so improved merging performance was observed when the system was applied. The system is also effective even during increases in vehicle volume of the mainline.

• Journal of Korean Society of Transportation
• /
• v.20 no.6
• /
• pp.115-128
• /
• 2002

Traffic engineers have developed and implemented various microscopic simulation models to verify the traffic performance and to prevent the expected problems. The existing microscopic simulation models categorize drivers into several types to reflect various drivers' driving patterns but miss the dynamics of drivers' behavior changed based upon the traffic conditions. It was found from the field data collected from two different merging sections on an urban freeway in Seoul, Korea, that the drivers' critical gap distributions are changed based on (1) the traffic density on the adjacent lane to the acceleration lane and (2) the opportunities left to merge in terms of distance to the end of acceleration lane. It was also found from the study that the drivers' critical gap distributions follow the Normal distribution. and its mean and variance change while a vehicle progresses on an acceleration lane. This paper proposes a new gap-acceptance model developed based on a set of drivers' critical gap distributions from each segment on the acceleration lanes. Through the comparison study between the field data and the results from the simulation utilizing the proposed model, it was verified that (1) the distribution of merging points on an acceleration lane to the adjacent main lane at different density levels, (2) the size of the gap accepted for merging and (3) the speed difference between the merging vehicle and the trailing vehicle at the time of merging are statistically identical to the field data at 95% confidence level.