• Journal of Auto-vehicle Safety Association
• /
• v.8 no.4
• /
• pp.31-37
• /
• 2016

Since real road experiments have many restrictions, a multi-vehicle traffic simulator can be an effective tool to develop and evaluate fully automated driving systems. This paper presents multi-vehicle environment simulation tool to develop and evaluate motorway automated driving systems. The proposed simulation tool consists of following two main parts: surrounding vehicle model and environment sensor model. The surrounding vehicle model is designed to quickly generate rational complex traffic situations of motorway. The environment sensor model depicts uncertainty of environment sensor. As a result, various traffic situations with uncertainty of environment sensor can be proposed by the multi-vehicle environment simulation tool. An application to automated driving system has been conducted. A lane changing algorithm is evaluated by performance indexes from the multi-vehicle environment simulation tool.

• Journal of Korea Multimedia Society
• /
• v.19 no.12
• /
• pp.1909-1918
• /
• 2016

This paper presents a unified framework for joint Convolutional Neural Network (CNN) based vehicle detection by leveraging multi-spectral image pairs. With the observation that under challenging environments such as night vision and limited light source, vehicle detection in a single color image can be more tractable by using additional far-infrared (FIR) image, we design joint CNN architecture for both RGB and FIR image pairs. We assume that a score map from joint CNN applied to overall image can be considered as confidence of vehicle existence. To deal with various scale ratios of vehicle candidates, multi-scale images are first generated scaling an image according to possible scale ratio of vehicles. The vehicle candidates are then detected on local maximal on each score maps. The generation of overlapped candidates is prevented with non-maximal suppression on multi-scale score maps. The experimental results show that our framework have superior performance than conventional methods with a joint framework of multi-spectral image pairs reducing false positive generated by conventional vehicle detection framework using only single color image.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.5
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.167-178
• /
• 2019

In this paper, we study the multi-objectives vehicle and drone routing problem with time windows, MOVDRPTW for short, which is defined in an urban delivery network. We consider the dual modal delivery system consisting of drones and vehicles. Drones are used as a complement to the vehicle and operate in a point to point manner between the depot and the customer. Customers make various requests. They prefer to receive delivery services within the predetermined time range and some customers require fast delivery. The purpose of this paper is to investigate the effectiveness of the delivery strategy of using drones and vehicles together with a multi-objective measures. As experiment datasets, we use the instances generated based on actual courier delivery data. We propose a hybrid multi-objective evolutionary algorithm for solving MOVDRPTW. Our results confirm that the vehicle-drone mixed strategy has 30% cost advantage over vehicle only strategy.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.5
• /
• pp.51-55
• /
• 2002

This paper presents a systematic methodology and formulation for determining optimal strategies of multi-body dynamic systems, which is based on multi-body dynamics, design sensitivity, and optimization techniques, and is applicable to a wide variety of mechanical systems. The particular application discussed in this paper considers a vehicle model with four-wheel steeling capability, and the presented methodology determines an optimal steering angle ratio strategy for the vehicle. It is shown that such a strategy can improve the ride stability of the vehicle, during a variety of maneuvers, when compared against similar strategies obtained from linear and simplified vehicle models.

• Journal of Power System Engineering
• /
• v.13 no.5
• /
• pp.40-45
• /
• 2009

This article deals with the transient analysis using multi-flexible body dynamics of a trailer vehicle, which is passing a bump on the flat road. In order to investigate the transient dynamic behavior of the trailer, we developed an equivalent finite element model for the trailer and a vehicle dynamic model for the truck using multi-body dynamics. The driving condition considered here is set as the trailer vehicle passes a bump on the flat road in 7km/h. And we investigate the time histories of vertical load and deflections on connecting points between the trailer and truck during the vehicle passes a bump. Due to the dynamic load resulted from the driving condition, additional stress concentrations are found in the trailer and the suspension connecting points between the trailer and rear axles along with kingpin.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.11 no.2
• /
• pp.80-86
• /
• 2002

Previous method of computer simulation to predict the dynamic response of a vehicle has been based on the assumption that vehicle structure is rigid. If the flexibility of the vehicle structure becomes too large to ignore, rigid body assumption will no longer give good estimation of the dynamic characteristics. Therefore, in order to predict more precise vehicle dynamic characteristics, flexible multi-body dynamic analysis of a vehicle is necessary. This paper investigates dynamic characteristics of vehicle systems with flexible frames numerically. Joint reaction forces, vertical accelerations, pitch accelerations are analyzed for the vehicle systems with various flexible frames using multi-body dynamic analysis code and finite element analysis code.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.3 no.2
• /
• pp.15-22
• /
• 2000

Shock and vibration characteristics of a tractor-trailer type vehicle system with air suspension and air coupler running on a single bump road are investigated. The vehicle system is modelled and solved to two types of models, i.e. rigid-multi-body and flexible-multi-body model, by ADAMS and NASTRAN software. And the shock impulse is given by a single bump model on the road. When the analysis results of the rigid-multi-body model is compared with those of the flexible-multi-body model, it is revealed that the vibration and accelerations of the latter model are more repetitive and larger than the former.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.2
• /
• pp.102-107
• /
• 2019

The vehicle market has developed environment-friendly vehicles to comply with fuel economy regulations and exhaust regulations that have become stricter and stricter over time. Many studies have been conducted to improve the travel performance and fuel economy of environment-friendly vehicles, and vehicle manufacturers have been studying how to manufacture light-weight vehicles in order to improve the fuel economy of both existing vehicles and the newer environment-friendly vehicles. Exemplary light-weight vehicle technologies optimizes the design of the vehicle body structure, which is a vehicle weight-reducing method that modifies component shapes or layouts to optimize the structure of the vehicle. In addition, the new process technology uses new light-weight and very strong materials, and not typical materials, to manufacture light-weight vehicles. This study aims at the optimal design of vehicle body structures using multi-materials for the Fender-Apron, which is an important frame member for the external front side of a vehicle body, by conducting FEA (Finite Element Analysis) and multi-material bonding.

• Ocean and Polar Research
• /
• v.26 no.2
• /
• pp.323-332
• /
• 2004

This paper concerns about a study on dynamic responses of tracked vehicle on soft cohesive soil. For dynamic analyses of tracked vehicle, two different models were adopted, i.e. a single-body model and a multi-body model. The single-body vehicle model was assumed as a rigid body with 6-dof. The multi-body vehicle was modeled by using a commercial software, RecurDyn-LM. For the both models properties of cohesive soft soil were modeled by means of three relationships: pressure to sinkage, shear displacement to shear stress, and shear displacement to dynamic sinkage. Traveling performances of the two tracked vehicle models were compared through dynamic analyses in time domain.