kumoh national institute of technology
Networked Systems Lab.

Heidy Indrayani, Ade Pitra Hermawan, Dong-Seong Kim, Jae-Min Lee, "Vehicle Trajectory Prediction using Deep Learning for Intelligent Transportation System", 2020 Korean Institute of Communication and Sciences (KICS) Summer Conference, August 12-14, 2020, Yong Pyong Resort, Pyeongchang, Gangwon Province, Korea, (N)
By :
Date : 2020-06-07
Views : 100

 This paper proposes a prediction of vehicle trajectory by using deep learning algorithm in the intelligent transportation system. The trajectory of vehicle is adjusted based on predicted trajectory of neighboring vehicles. To achieve accurately vehicle trajectory, two kinds of deep learning algorithms such as deep neural network (DNN) and long short term memory (LSTM) are designed. The performance of the proposed algorithms is verified by using next generation simulation (NGSIM) vehicle trajectories dataset. Simulation results shown that the DNN algorithm outperformed LSTM algorithm in terms of RMSE values of predicted vehicle trajectories.