TY - GEN
T1 - Trajectory Prediction for Autonomous Driving System Using Graph Feature Fusion Network
AU - Li, Wenwen
AU - Li, Mingxing
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.
PY - 2024
Y1 - 2024
N2 - To accurately predict trajectories of surrounding moving objects, we propose a Graph Feature Fusion Network to capture informa tion more fully and effectively on moving objects. Unlike previous works, this work not only designs a 3D graph to incorporate both spatial and temporal edges, but also proposes a multi-level interactive feature fusion network which integrates graph attention model and graph convolution model to obtain the graph feature. Furthermore, encoder-decoder convo lutional gated recurrent units are used to predict trajectories of different types of moving objects. ApolloScape dataset is used to evaluate the performances. Results show that our model outperforms several baseline methods on the average displacement error (ADE) and final displacement error (FDE).
AB - To accurately predict trajectories of surrounding moving objects, we propose a Graph Feature Fusion Network to capture informa tion more fully and effectively on moving objects. Unlike previous works, this work not only designs a 3D graph to incorporate both spatial and temporal edges, but also proposes a multi-level interactive feature fusion network which integrates graph attention model and graph convolution model to obtain the graph feature. Furthermore, encoder-decoder convo lutional gated recurrent units are used to predict trajectories of different types of moving objects. ApolloScape dataset is used to evaluate the performances. Results show that our model outperforms several baseline methods on the average displacement error (ADE) and final displacement error (FDE).
KW - feature fusion network
KW - graph attention model
KW - graph convolution model
KW - trajectory prediction
UR - https://www.scopus.com/pages/publications/105000381220
U2 - 10.1007/978-981-97-8650-3_37
DO - 10.1007/978-981-97-8650-3_37
M3 - 会议稿件
AN - SCOPUS:105000381220
SN - 9789819786497
T3 - Lecture Notes in Electrical Engineering
SP - 366
EP - 373
BT - Proceedings of 2024 Chinese Intelligent Systems Conference
A2 - Jia, Yingmin
A2 - Fu, Yongling
A2 - Zhang, Weicun
A2 - Yang, Yang
PB - Springer Science and Business Media Deutschland GmbH
T2 - 20th Chinese Intelligent Systems Conference, CISC 2024
Y2 - 26 October 2024 through 27 October 2024
ER -