• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.297-305
• /
• 2017

As the development of autonomous vehicles becomes realistic, many automobile manufacturers and components producers aim to develop 'completely autonomous driving'. ADAS (Advanced Driver Assistance Systems) which has been applied in automobile recently, supports the driver in controlling lane maintenance, speed and direction in a single lane based on limited road environment. Although technologies of obstacles avoidance on the obstacle environment have been developed, they concentrates on simple obstacle avoidances, not considering the control of the actual vehicle in the real situation which makes drivers feel unsafe from the sudden change of the wheel and the speed of the vehicle. In order to develop the 'completely autonomous driving' automobile which perceives the surrounding environment by itself and operates, ability of the vehicle should be enhanced in a way human driver does. In this sense, this paper intends to establish a strategy with which autonomous vehicles behave human-friendly based on vehicle dynamics through the reinforcement learning that is based on Q-learning, a type of machine learning. The obstacle avoidance reinforcement learning proceeded in 5 simulations. The reward rule has been set in the experiment so that the car can learn by itself with recurring events, allowing the experiment to have the similar environment to the one when humans drive. Driving Simulator has been used to verify results of the reinforcement learning. The ultimate goal of this study is to enable autonomous vehicles avoid obstacles in a human-friendly way when obstacles appear in their sight, using controlling methods that have previously been learned in various conditions through the reinforcement learning.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.2
• /
• pp.255-263
• /
• 2016

Lane Keeping Assistance System (LKAS) is a kind of Advanced Driver Assistance Systems (ADAS) which are developed to automate/ adapt/ enhance vehicle systems for safety and better driving. The main system function of LKAS is to support the driver in keeping the vehicle within the current lane. LKAS acquires information on the position of the vehicle within the lane and, when required, sends commands to actuators to influence the lateral movement of the vehicle. Recently, the vehicles equipped with LKAS are commercially available in a few vehicle-advanced countries and the installation of LKAS increases for safety enhancement. The test procedures for LKAS evaluations are being discussed and developed in the international committees such as ISO (the International Organization for Standardization) and UNECE (United Nations Economic Commission for Europe). In Korea, the evaluations of LKAS for vehicle safety are planned to be introduced in 2016 KNCAP (Korean New Car Assessment Program). Therefore, the test procedures of LKAS suitable for domestic road and traffic conditions, which accommodate international standards, should be developed. In this paper, some bullet points of the test procedures for LKAS are discussed and proposed by extensive researches of previous documents and reports, which are released in public in regard to lateral test procedures including LKAS and Lane Departure Warning System (LDWS). And then, to evaluate the validity of the proposed test procedures, a series of experiments were conducted using commercially available two vehicles equipped with LKAS. Later, it can be helpful to make a draft considering domestic traffic situations for test procedures of LKAS.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.201-208
• /
• 2015

This paper proposes a method for detecting the direction indicator shown in the road surface efficiently from the black box system installed on the vehicle. In the proposed method, the direction indicators are detected by inverse perspective mapping(IPM) and bag of visual features(BOF)-based NN classifier. In order to apply the proposed method to real-time environments, the candidated regions of direction indicator in an image only performs IPM, and BOF-based NN is used for the classification of feature information from direction indicators. The results of applying the proposed method to the road surface direction indicators detection and recognition, the detection accuracy was presented at least about 89%, and the method presents a relatively high detection rate in the various road conditions. Thus it can be seen that the proposed method is applied to safe driving support systems available.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.17
• /
• pp.7595-7597
• /
• 2015

Background: The aim of this study was to evaluate the effect of whole brain radiotherapy (WBRT) combined with streotactic radiosurgery versus stereotactic radiosurgery (SRS) alone for patients with brain metastases. Materials and Methods: This was a retrospective study that evaluated the results of 46 patients treated for brain metastases at Dr. Abdurrahman Yurtaslan Ankara Oncology Training and Research Hospital, Radiation Oncology Department, between January 2012 and January 2015. Twenty-four patients were treated with WBRT+SRS while 22 patients were treated with only SRS. Results: Time to local recurrence was 9.7 months in the WBRT+SRS arm and 8.3 months in SRS arm, the difference not being statistically significant (p=0.7). Local recurrence rate was higher in the SRS alone arm but again without significance (p=0,06). Conclusions: In selected patient group with limited number (one to four) of brain metastases SRS alone can be considered as a treatment option and WBRT may be omitted in the initial treatment.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.17
• /
• pp.7371-7375
• /
• 2014

Background: Concurrent chemo-radiotherapy is the recommended standard treatment modality for patients with locally advanced lung cancer. The purpose of three-dimensional conformal radiotherapy (3DCRT) is to minimize normal tissue damage while a high dose can be delivered to the tumor. The most common dose limiting side effect of thoracic RT is radiation pneumonia (RP). In this study we evaluated the relationship between dose-volume histogram parameters and radiation pneumonitis. This study targeted prediction of the possible development of RP and evaluation of the relationship between dose-volume histogram (DVH) parameters and RP in patients undergoing 3DCRT. Materials and Methods: DVHs of 41 lung cancer patients treated with 3DCRT were evaluated with respect to the development of grade ${\geq}2$ RP by excluding gross tumor volume (GTV) and planned target volume (PTV) from total (TL) and ipsilateral (IPSI) lung volume. Results: Were admitted statistically significant for p<0.05. Conclusions: The cut-off values for V5, V13, V20, V30, V45 and the mean dose of TL-GTV; and V13, V20,V30 and the mean dose of TL-PTV were statistically significant for the development of Grade ${\geq}2$ RP. No statistically significant results related to the development of Grade ${\geq}2$ RP were observed for the ipsilateral lung and the evaluation of PTV volume. A controlled and careful evaluation of the dose-volume histograms is important to assess Grade ${\geq}2$ RP development of the lung cancer patients treated with concurrent chemo-radiotherapy. In the light of the obtained data it can be said that RP development may be avoided by the proper analysis of the dose volume histograms and the application of optimal treatment plans.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.17
• /
• pp.7401-7405
• /
• 2014

Background: Postoperative chemoradiotherapy is accepted as standard treatment for stage IB-IV, M0 gastric cancer. Radiotherapy (RT) planning of gastric cancer is important because of the low radiation tolerance of surrounding critical organs. The purpose of this study was to compare the dosimetric aspects of 2-dimensional (2D) and 3-dimensional (3D) treatment plans, with the twin aims of evaluating the adequacy of 2D planning fields on coverage of planning target volume (PTV) and 3D conformal plans for both covering PTV and reducing the normal tissue doses. Materials and Methods: Thirty-six patients with stage II-IV gastric adenocarcinoma were treated with adjuvant chemoradiotherapy using 3DRT. For each patient, a second 2D treatment plan was generated. The two techniques were compared for target volume coverage and dose to normal tissues using dose volume histogram (DVH) analysis. Results: 3DRT provides more adequate coverage of the target volume. Comparative DVHs for the left kidney and spinal cord demonstrate lower radiation doses with the 3D technique. Conclusions: 3DRT produced better dose distributions and reduced radiation doses to left kidney and spinal cord compared to the 2D technique. For this reason it can be predicted that 3DRT will result in better tumor control and less normal tissue complications.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.4
• /
• pp.68-80
• /
• 2016

This study proposes the traffic prediction and optimal traffic control system based on cell transmission model and genetic algorithm in cloud environment. The proposed prediction and control system consists of four parts. 1) Data preprocessing module detects and imputes the corrupted data and missing data points. 2) Data-driven traffic prediction module predicts the future traffic state using Multi-level K-Nearest Neighbor (MK-NN) Algorithm with stored historical data in SQL database. 3) Online traffic simulation module simulates the future traffic state in various situations including accident, road work, and extreme weather condition with predicted traffic data by MK-NN. 4) Optimal road control module produces the control strategy for large road network with cell transmission model and genetic algorithm. The results show that proposed system can effectively reduce the Vehicle Hours Traveled upto 60%.

• Journal of Korea Multimedia Society
• /
• v.5 no.2
• /
• pp.176-190
• /
• 2002

According as vehicles increases, system such as Advanced Drivers Assistance System(ADAS ) to inform forward situation to driver is required. In this paper, we proposes method to detect forward vehicles and lane from sequential color images by basis process to inform forward situation to driver. We detect a front vehicle using that shadow area exists on part under vehicles and that road area occupies many parts even if road traffic is confused. We detect lane information using that lane part is white order by reverse characteristic of shadow area. This method shows good result in case road is confused or there is direction indication to road. HSV color space is selected for color modeling. This method uses saturation component and value component in HSV color model to detect vehicles and lane. It uses statistics features of HSV component and position to know whether detected vehicles area is vehicles such as vehicles previous frame. To verify the effects of the proposed method, we capture the road images with notebook and CCD camera for PC and Present the results such as processing time, accuracy and vehicles detection against the images.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.1-8
• /
• 2017

This paper presents the development of an adaptive cruise control (ACC) system, which is one of the typical advanced driver assist systems, for 4-wheel drive hybrid in-wheel electric vehicles. The front wheels of the vehicle are driven by a combustion engine, while its rear wheels are driven by in-wheel motors. This paper proposes an adaptive cruise control system which takes advantage of the unique driveline configuration presented herein, while the proposed power distribution algorithm guarantees its tracking performance and fuel efficiency at the same time. With the proposed algorithm, the vehicle is driven only by the engine in normal situations, while the in-wheel motors are used to distribute the power to the rear wheels if the tracking performance decreases. This paper also presents the modeling of the in-wheel motors, hybrid in-wheel driveline, and integrated ACC control system based on a commercial high-precision vehicle dynamics model. The simulation results obtained with the model are presented to confirm the performance of the proposed algorithm.