• The Journal of the Korea Contents Association
• /
• v.8 no.10
• /
• pp.76-87
• /
• 2008

Prediction of travel time on road network is one of crucial research issue in dynamic route guidance system. A new approach based on Rule-Based classification is proposed for predicting travel time. This approach departs from many existing prediction models in that it explicitly consider traffic patterns during day time as well as week day. We can predict travel time accurately by considering both traffic condition of time range in a day and traffic patterns of vehicles in a week. We compare the proposed method with the existing prediction models like Link-based, Micro-T* and Switching model. It is also revealed that proposed method can reduce MARE (mean absolute relative error) significantly, compared with the existing predictors.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.2
• /
• pp.114-122
• /
• 2014

Beacon transmission is one of the fundamental mechanisms in vehicular ad hoc networks. Variety services including context awareness can be embodied by exchanging beacons in each vehicle. In this paper, we propose dual beacon transmission instead of traditional single beacon transmission for beaconing mechanism. dual beacon transmission divides beacon into two functions and operates two beaconing process independently. We verified the superiority of dual beacon transmission by comparing beacon packet delivery ratio with single beacon transmission. In conclusion, dual beacon transmission can reduce channel load and have both wider communication range and effective context awareness. In addition, implementing dual beacon transmission has less complexity and appliable with conventional adaptive beaconing schemes.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.109-123
• /
• 2024

Research into vision-based end-to-end autonomous driving systems utilizing deep learning and reinforcement learning has been steadily increasing. These systems typically encode continuous and high-dimensional vehicle states, such as location, velocity, orientation, and sensor data, into latent features, which are then decoded into a vehicular control policy. The complexity of urban driving environments necessitates the use of state representation learning through networks like Variational Autoencoders (VAEs) or Convolutional Neural Networks (CNNs). This paper analyzes the impact of different image state encoding methods on reinforcement learning performance in autonomous driving. Experiments were conducted in the CARLA simulator using RGB images and semantically segmented images captured by the vehicle's front camera. These images were encoded using VAE and Vision Transformer (ViT) networks. The study examines how these networks influence the agents' learning outcomes and experimentally demonstrates the role of each state representation technique in enhancing the learning efficiency and decision- making capabilities of autonomous driving systems.

• 한국IT서비스학회:학술대회논문집
• /
• 2006.05a
• /
• pp.255-259
• /
• 2006

언제 어디서든 인간의 편의를 도모하고자 하는 유비쿼터스 센서 네트워크(USN) 시대에 발맞춰 많은 연구들이 이루어지고 있다. 이러한 연구들 중 차량에 설치된 단말기를 통해 길안내 서비스, 교통정보 서비스 등 다양한 정보를 제공하는 텔레매틱스 서비스가 활발하게 연구되고 있다. 텔레매틱스 서비스의 일환으로 교차로에서 발생할 수 있는 사고를 미연에 방지하기 위하여 교차로로 접근하는 차량의 위치 및 속도 등의 차량정보를 교차로 중앙에 위치한 베이스 스테이션으로 전송하기 위해 IEEE 802.11 프로토콜[1]을 사용하였을 때, 도심 지역에 위치한 교차로의 경우 신속하고 정확하게 전송되어야 하는 차량 정보들이 교차로 주변의 빌딩숲에 가려진 두개 이상의 노드가 거의 동시에 송신을 하는 경우 충돌로 인하여 베이스 스테이션에서 수신 에러가 발생하게 된다. 본 논문에서는 IEEE 802.11 프로토콜을 통해 차량 정보를 베이스 스테이션으로 전송할 때 교차로 주변 빌딩이 성능에 미치는 영향을 파악하기 위하여 NS2[2] 시뮬레이션 도구를 사용하여 성능을 평가하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.695-697
• /
• 2011

AUTOSAR 는 차량용 시스템의 소프트웨어 인프라를 표준화하여 차량용 소프트웨어의 재사용성을 높이고자 개발된 차량용 소프트웨어 구조 표준안이다. 그러나, 기존 AUTOSAR 는 새로운 하드웨어의 추가 및 변경을 지원할 수 없기 때문에 하드웨어의 변경에 대해 유연하게 적응할 수 있는 구조 또는 기법이 필요하다. 따라서, 본 논문에서는 AUTOSAR 의 모델에 Workflow 를 도입하고, 동적인 네트워크를 구축하여 Plug & Play 기능을 지원하는 차량용 소프트웨어 구조를 제안한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.105-108
• /
• 2010

The vehicle navigation system is a representative driver supporting system that available to present searching and guiding path functions, have been increased for usability. Under competition situation because of following the spreaded navigation market, to meet customer's needs about new given services, there are need differentiated services increasing dramatically. Also now, dash board indicates various vehicle's status and driver can aware of that. However it is not easy to know where is abnormal essentially and there are no devices to give warning to driver. Therefore, It is difficult to preserve accidents because it can't deal with various abnormal functions immediately on driving. In this paper, we proposed vehicle diagnosis program within navigation that is available to manage and to make a diagnosis of vehicle. And this program conform OBD-II standard, so it can transmit diagnosis data from ECU to navigation system using Bluetooth wireless communication protocol. Thus this program give enhanced services to customer as well as multimedia and geometry information services.

• Journal of Korean Society of Transportation
• /
• v.30 no.2
• /
• pp.29-42
• /
• 2012

Recently, traffic congestion has become serious due to increase of private car usages. Carsharing or other innovative public transportation systems were developed to alleviate traffic congestion and carbon emissions. These measures can make the traffic environment more comfortable, and efficient. Cloud Transportation System (CTS) is a recent carsharing model. User can rent an electronic vehicles with various traffic information through the CTS. In this study, a concept, vision and scenarios of CTS are introduced. And, authors analyzed the location of CTS rental stations and estimated CTS demands. Firstly, we analyze the number of the population, employees, students and traffic volume in study areas. Secondly, the frequency and utilization time are examined. Demand for CTS in each traffic zone was estimated. Lastly, the CTS rental station location is determined based on the analyzed data of the study areas. Evaluation standard of the determined location includes accessibility and density of population. And, the number of vehicles and that of parking zone at the rental station are estimated. The result suggests that Haewoondae Square parking lot would be assigned 11 vehicles and 14.23 parking spaces and that Dongbac parking lot be assigned 7.9 vehicles and 10.29 parking spaces. Further study requires additional real-time data for CTS to increase accuracy of the demand estimation. And network design would be developed for redistribution of vehicles.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.2
• /
• pp.64-70
• /
• 2021

Nowadays, there are significant interests in real-time remote control using wireless networks. In implementing real-time remote control, one important factor is delay performance of real-time control message. Especially, the technique to reduce jitter of delay is necessary in transmitting periodically real-time control message. In this paper, we proposed synchronized transmission to reduce jitter of delay, when real-time control message was transmitted through wireless networks. The proposed transmission kept synchronization between source node and wireless transmitter and controlled transmission instance to transmit real-tie control message with fixed delay in wireless networks. According to results of experiment in military unmanned vehicle system, the proposed transmission reduced jitter of delay as 32% as that of a non-employing case.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.425-429
• /
• 2021

Vehicle platooning in automated connected vehicle systems is an efficient transportation operation model that not only significantly reduces computational load and networking overhead of the central system but also improves traffic flow. For efficient platoon group management, it is important to maintain the platoon group size appropriately and to control the merge request of a new vehicle and other group member vehicle. In this paper, we present a merger control scheme that accepts or rejects merge requests based on the current group size and the priority of vehicles. The proposed method was analyzed and validated through mathematical models based on Markov chains. Performance evaluation shows that the proposed scheme properly manages the load of the central system.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.9
• /
• pp.208-214
• /
• 2014

Vehicle dynamic states used in various advanced driving safety systems are influenced by road geometry. Among the road geometry information, the vehicle pitch angle influenced by road slope and acceleration-deceleration is essential parameter used in pose estimation including the navigation system, advanced adaptive cruise control and others on sag road. Although the road slope data is essential parameter, the method measuring the parameter is not commercialized. The digital map including the road geometry data and high-precision DGPS system such as DGPS(Differential Global Positioning System) based RTK(Real-Time Kinematics) are used unusually. In this paper, low-cost cascade extended Kalman filter(CEKF) based road slope estimation method is proposed. It use cascade two EKFs. The EKFs use several measured vehicle states such as yaw rate, longitudinal acceleration, lateral acceleration and wheel speed of the rear tires and 3 D.O.F(Degree Of Freedom) vehicle dynamics model. The performance of proposed estimation algorithm is evaluated by simulation based on Carsim dynamics tool and T-car based experiment.