Deep Neural Network 기반의 차량 주행 경로 예측

다국어 초록 (Multilingual Abstract)

In regard to the vehicle safety services, vehicle trajectory prediction is one of the key technologies to estimate when and where the vehicle could be located. The development of the vehicle trajectory prediction algorithms using traditional physics-based models, such as kinematic and dynamic models, often required building a system model with complex equations, as well as gathering sensor noise statistics. In this paper, we proposed a vehicle trajectory prediction algorithm based on a deep neural network(DNN). The input data to the DNN were the driving status information defined in SAE J2735 basic safety message(BSM), while the output layer consisted of longitudinal and lateral trajectory predictions. The adaptive moment estimation(Adam) was used to enhance the learning speed. Through simulations, we compared the performance of the DNN-based approach with that of the traditional approach, and the results showed that the proposed method resulted in improved accuracy and precision of the vehicle trajectory prediction.

참고문헌 (Reference)

1 강현구, "충돌회피를 위한 가속도를 고려한 차선 변경 시스템 개발" 한국자동차공학회 21 (21): 81-86, 2013

2 최희재, "정적 장애물 회피를 위한 경로 계획: ADAM III" 한국자동차공학회 22 (22): 241-249, 2014

3 National Highway Traffic Safety Administration, "Vehicle-to-Vehicle Communication Technology for Light Vehicles, Preliminary Regulatory Impact Analysis, FMVSS, No. 150"

4 D. Yudin, "Vehicle Recognition and its Trajectory Registration on the Image Sequence using Deep Convolutional Neural Network" 435-441, 2017

5 S. H. JEONG, "TECHNOLOGY ANALYSIS AND LOW-COST DESIGN OF AUTOMOTIVE RADAR FOR ADAPTIVE CRUISE CONTROL SYSTEM" 한국자동차공학회 13 (13): 1133-1140, 2012

6 "SAE International Surface Vehicle Standard, Dedicated Short Range Communications (DSRC) Message Set Dictionary, SAE Standard J2735"

7 "Road Design Manual" 2012

8 "PreScan: Simulation of ADAS and Active Safety" TASS International

9 J. Walker, "Patch to the Future: Unsupervised Visual Prediction" 3302-3309, 2014

10 D. Jeong, "Long-Term Prediction of Vehicle Trajectory Based on a Deep Neural Network" 726-728, 2017

11 D. E. Rumelhart, "Learning Representations by Backpropagating Errors" 323 (323): 533-536, 1986

12 D. Vasquez, "Growing Hidden Markov Models: An Incremental Tool for Learning and Predicting Human and Vehicle Motion" 28 (28): 1486-1506, 2009

13 H. -J. Kang, "Forward Collision Damage Mitigation System" 33 (33): 44-51, 2011

14 C. H. JANG, "DESIGN FACTOR OPTIMIZATION OF 3D FLASH LIDAR SENSOR BASED ON GEOMETRICAL MODEL FOR AUTOMATED VEHICLE AND ADVANCED DRIVER ASSISTANCE SYSTEM APPLICATIONS" 한국자동차공학회 18 (18): 147-156, 2017

15 P. Lytrivis, "An Advanced Cooperative Path Prediction Algorithm for Safety Applications in Vehicular Networks" 12 (12): 669-679, 2011

16 D. Kingma, "Adam: A Method for Stochastic Optimization" 2015

17 "2016 Korea Automobile Testing and Research Institute Annual Report" Korea Transportation Safety Authority 2017