• 제목/요약/키워드: Collision Prediction

검색결과 111건 처리시간 0.028초

Pedestrian GPS Trajectory Prediction Deep Learning Model and Method

  • Yoon, Seung-Won;Lee, Won-Hee;Lee, Kyu-Chul
    • 한국컴퓨터정보학회논문지
    • /
    • 제27권8호
    • /
    • pp.61-68
    • /
    • 2022
  • 본 논문에서는 딥러닝 모델 기반 보행자의 GPS 경로를 예측하는 시스템을 제안한다. 보행자 경로 예측은 보행자의 위험 및 충돌 상황들을 알림을 통해 방지할 수 있으며, 다양한 마케팅 등 비즈니스 면에서도 영향을 끼치는 연구이다. 또한 보행자 뿐 아니라 많은 각광을 받고 있는 무인 이동수단의 경로 예측에도 활용될 수 있다. 다양한 경로 예측 방식들 중 본 논문은 GPS 데이터를 활용하여 경로를 예측하는 연구이다. 시계열 데이터인 보행자의 GPS 경로를 학습하여 다음 경로를 예측하도록 하는 딥러닝 모델 기반 연구이다. 본 논문에서는 보행자의 GPS 경로를 딥러닝 모델이 학습할 수 있도록하는 데이터 셋 구성 방식을 제시하였으며, 예측 범위에 큰 제약이 없는 경로 예측 딥러닝 모델을 제안한다. 본 연구의 경로 예측 딥러닝 모델에 적합한 파라메터들을 제시하였으며, 우수한 예측 성능을 보이는 결과를 제시한다.

선박운항자 의식 기반 충돌 위험도 예측 모듈 개발에 관한 연구 (A Basic Study on Prediction Module Development of Collision Risk based on Ship's Operator's Consciousness)

  • 박영수;박상원;조익순
    • 한국항해항만학회지
    • /
    • 제39권3호
    • /
    • pp.199-207
    • /
    • 2015
  • 우리나라 항구 주변에는 입 출항하는 선박으로 인하여 해상교통흐름이 복잡하다. 이러한 선박통항의 안전과 효율성을 증진하기 위해 우리나라에서는 해상교통관제 서비스를 시행하고 있다. 24시간 쉴 틈이 없는 해상교통 관제사들의 노력에도 불구하고 관제구역 내에서의 충돌사고는 지속적으로 발생하고 있으며, 위험 상황이 약 20분에 1회씩 발생하고 있는 것으로 분석되어 그 위험성은 크다고 할 수 있다. 이러한 사고는 선박운항 및 해상교통관제 정보 제공 시 충돌 위험에 대한 안전 기준을 적시에 제공함으로써 사고를 감소시킬 수 있을 것으로 조사되었다. 이에 본 연구는 선박의 충돌위험도를 선박운항자의 관점에서 평가할 수 있는 모델을 이용하여 그 위험을 선박의 속도, 침로 등을 조정하여 각 교통 상황별 충돌 위험도를 사전에 예측 할 수 있는 위험도 예측 모듈을 개발하였다. 이 모듈을 이용하여 선박운항자 및 관제사는 복잡한 교통 상황에서 위험요소를 쉽게 식별 할 수 있어, 가까운 장래의 위험 정도의 변화를 선박침로 및 속력변경 등을 제시할 수 있는 등의 적절한 피항조치를 취할 수 있다. 이 모듈의 효용성을 검증하기 위해 부산항 해역을 대상으로 조우 상황별 위험도를 예측 후 구체적인 침로 및 속력 변경에 따른 위험도 변화를 식별할 수 있는 것으로 확인되었다.

Theoretical Approach of Optimization of the Gain Parameters α, β and γ of a Tracking Module for ARPA system on Board Warships

  • Jeong, Tae-Gweon;Pan, Bao-Feng;Njonjo, Anne Wanjiru
    • 한국항해항만학회:학술대회논문집
    • /
    • 한국항해항만학회 2015년도 추계학술대회
    • /
    • pp.55-57
    • /
    • 2015
  • The tracking system plays a key role in accurate estimation and prediction of maneuvering vessel's position and velocity in a bid to enhance safety by taking avoiding action against collision. Therefore, in order to achieve this, many ocean- going vessels are equipped with radar and the ARPA system. However, the accuracy of prediction highly depends on the choice of the gain parameters, ${\alpha}$, ${\beta}$ and ${\gamma}$ employed in the tracking filter. P revious research of this paper was based on theoretically developing an algorithm for a tracking module. This research paper is hence a continuation by the authors to determine the optimal values of the gain parameters used in the tracking module. A tracking algorithm is developed using the ${\alpha}-{\beta}-{\gamma}$ filter to carry out prediction and smoothing of the positions and velocities. Numerical simulations are then performed to evaluate the optimal values of the smoothing parameters that will improve the performance of the tracking module and reduce measurement noise. The twice distance root mean square (2drms) is then calculated to determine error variation.

  • PDF

해안기름유출사고에 의한 기름확산 예측 방법 연구 (Study on Prediction for Prompt Countermeasures to Oil Spread in Ocean)

  • 김영복
    • 한국해양공학회지
    • /
    • 제25권2호
    • /
    • pp.108-112
    • /
    • 2011
  • When oil spills occur in the ocean because of a ship collision or grounding, the oil in the sea will spread to the coastline. To effectively and promptly prevent such an oil spread, the prediction of the direction and speed of the spreading oil must be made. By applying the coastal wave diffusion theory with a consideration of the effects of wind and current, the oil spreading direction and speed can be predicted promptly so that the National Disaster Prevention System can effectively and promptly take countermeasures against the attack and contamination of the coastline by such oil bands.

A Modeling of Impact Dynamics and its Application to Impact Force Prediction

  • Ahn Kil-Young;Ryu Bong-Jo
    • Journal of Mechanical Science and Technology
    • /
    • 제19권spc1호
    • /
    • pp.422-428
    • /
    • 2005
  • In this paper, the contact force between two colliding bodies is modeled by using Hertz's force-displacement law and nonlinear damping function. In order to verify the appropriateness of the proposed contact force model, the drop type impact test is carried out for different impact velocities and different materials of the impacting body, such as rubber, plastic and steel. In the drop type impact experiment, six photo interrupters in series close to the collision location are installed to measure the velocity before impact more accurately. The characteristics of contact force model are investigated through experiments. The parameters of the contact force model are estimated using the optimization technique. Finally the estimated parameters are used to predict the impact force between two colliding bodies in opening action of the magnetic contactor, a kind of switch mechanism for switching electric circuits.

노즐 형상에 따른 디젤 연료 분무의 발달 예측에 관한 수치 해석적 연구 (The Numerical Study on Prediction of Diesel Fuel Spray Evolution in a Different Types of Nozzle Geometry)

  • 민세훈;서현규
    • 한국분무공학회지
    • /
    • 제22권4호
    • /
    • pp.169-174
    • /
    • 2017
  • The objective of this study was to verify the experimental and numerical results of spray evolution injected from different types of the nozzle-hole geometries. Spray visualization was taken by high speed camera under the different conditions. For the simulations of spray tip penetration, turbulence, evaporation and break-up model were applied K-zeta-f, Dukowicz and Wave model, respectively. Also, the prediction accuracy of spray tip penetration was increased by varying the spray cone angle. At the same time, the results of this work were compared in terms of spray tip penetration, and SMD characteristics. The numerical results of spray evolution process and spray tip penetration showed good agreement with experimental one.

자동차 에어백용 원단의 수명예측 (Lifetime Prediction of Automotive Airbag Fabrics)

  • 구현진;조항원;장갑식
    • 한국신뢰성학회지:신뢰성응용연구
    • /
    • 제9권4호
    • /
    • pp.319-329
    • /
    • 2009
  • The airbag module is an inflatable restraint system that inflates within 0.05 seconds automatically in a collision to protect the occupants. The airbag fabrics used in the module are required to have the good resilience and strength and also to have retained at least 80% of mechanical properties after using longer than 10 years. In this study, we develop an accelerated test method in order to predict the lifetimes of airbag. In this test, we select temperature and humidity as environmental stresses by analyzing the failure mechanisms of coated and uncoated nylon 66 fabrics. It is found that the degradation of airbag fabrics is effectively accelerated under the combined conditions of high temperature and humidity. Analyzing the results of the accelerated test, the lifetimes of airbag fabrics are predicted to be longer than 10 years.

  • PDF

CR네트워크에서 트래픽 패턴 기반 채널 선택 기법 (Traffic Pattern-based Channel Selection for CR Networks)

  • 박형근;유윤섭;김남호
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국해양정보통신학회 2011년도 추계학술대회
    • /
    • pp.597-598
    • /
    • 2011
  • 인지 무선 네트워크에서 제어 및 데이터 정보 전송을 위한 최적의 채널 선택 방법으로 주사용자의 트래픽 정보를 이용하여 유휴 채널 구간을 예측하는 기법을 제안하다. 채널예측을 통해 채널을 선택함으로서 주 사용자에 대한 충돌을 최소화하고 전송효율을 증가시킬 수 있다. 시뮬레이션 결과 제안한 방법이 시스템 수율을 향상시킴과 동시에 주사용자에 대한 간섭 또한 적정한 임계치 이하로 줄이는 것을 확인할 수 있었다.

  • PDF

고강도강 마운팅브라켓의 성형성 향상 및 스프링백 예측에 관한 연구 (Research on Improved Formability of High-Strength Steel Mounting Brackets and Springback Prediction)

  • 임규성;최성대
    • 한국기계가공학회지
    • /
    • 제21권4호
    • /
    • pp.14-22
    • /
    • 2022
  • To reduce the weight of the car and ensure the safety of the driver while driving, the existing 440 MPa-class mounting bracket was treated at 590MPa to improve collision safety and secure the weight of the vehicle body. The following conclusions were drawn from the tensile test, forming analysis, and springback prediction. In the formability and springback analyses using FLD, it could be confirmed that bending was an essential process because the formability and flatness were much better when bending was added than when bending was not applied. Based on the research results, it was deduced that the mold design was necessary so that the molding was carried out at a strain rate of 20% or less for stable molding.

회전관성의 순환최소자승 추정을 이용한 모델 예견 기반 굴삭기의 충돌회피 알고리즘 개발 (Model-Prediction-based Collision-Avoidance Algorithm for Excavators Using the RLS Estimation of Rotational Inertia)

  • 오광석;서자호;이근호
    • 드라이브 ㆍ 컨트롤
    • /
    • 제13권4호
    • /
    • pp.59-67
    • /
    • 2016
  • This paper proposes a model-prediction-based collision-avoidance algorithm for excavators for which the recursive-least-squares (RLS) estimation of the excavator's rotational inertia is used. To estimate the rotational inertia of the excavator, the RLS estimation with multiple forgetting and two updating rules for the nominal parameter and the forgetting factors was conducted based on the excavator-swing dynamics. The average value of the estimated rotational inertia that is for the minimizing effects of the estimation error was computed using the recursive-average method with forgetting. Based on the swing dynamics, the computed average of the rotational inertia, the damping coefficient for braking, and the excavator's braking angle were predicted, and the predicted braking angle was compared with the detected-object angle for a safety evaluation. The safety level defined in this study consists of the three levels safe, warning, and emergency braking. The analytical rotational-inertia-based performance evaluation of the designed estimation algorithm was conducted using a typical working scenario. The results of the safety evaluation show that the predictive safety-evaluation algorithm of the proposed model can evaluate the safety level of the excavator during its operation.