TY - GEN
T1 - DAT-RNN
T2 - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
AU - Li, Zheng
AU - Du, Xiaocong
AU - Cao, Yu
N1 - Funding Information:
VI. ACKNOWLEDGMENTS This work was supported in part by C-BRIC, one of six centers in JUMP, a Semiconductor Research Corporation (SRC) program sponsored by DARPA. It was also partially supported by National Science Foundation (NSF) CCF 1715443.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - Trajectory prediction, an emerging application of spatial-temporal graph, is extremely critical in dynamic applications such as autonomous vehicles and robots. However, the diversity of trajectories and the modeling of mutual relations make it difficult to predict trajectories precisely and efficiently. In this work, we propose a novel approach, diverse attention RNN (DAT-RNN), to handle the diversity of trajectories and the accurate modeling of neighboring relations with two novel and well-designed modules: DAT-RNN first uses a diversity-aware memory (DAM) module, which is based on the detour integral of each individual, to capture the temporal behavior of each person; then DAT-RNN employs an anomaly attention module (AAM), which integrates a weighted sum of spatial relations from multiple neighbors to assist the prediction. With the well-elaborated modules, DAT-RNN integrates both temporal and spatial relations to improve the prediction under various circumstances. Comprehensive experiments on ETH and UCY datasets demonstrate the efficacy of the proposed approach.
AB - Trajectory prediction, an emerging application of spatial-temporal graph, is extremely critical in dynamic applications such as autonomous vehicles and robots. However, the diversity of trajectories and the modeling of mutual relations make it difficult to predict trajectories precisely and efficiently. In this work, we propose a novel approach, diverse attention RNN (DAT-RNN), to handle the diversity of trajectories and the accurate modeling of neighboring relations with two novel and well-designed modules: DAT-RNN first uses a diversity-aware memory (DAM) module, which is based on the detour integral of each individual, to capture the temporal behavior of each person; then DAT-RNN employs an anomaly attention module (AAM), which integrates a weighted sum of spatial relations from multiple neighbors to assist the prediction. With the well-elaborated modules, DAT-RNN integrates both temporal and spatial relations to improve the prediction under various circumstances. Comprehensive experiments on ETH and UCY datasets demonstrate the efficacy of the proposed approach.
KW - Recurrent neural network
KW - deep learning
KW - spatial-temporal graph
KW - trajectory prediction
UR - http://www.scopus.com/inward/record.url?scp=85102533506&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102533506&partnerID=8YFLogxK
U2 - 10.1109/ICMLA51294.2020.00233
DO - 10.1109/ICMLA51294.2020.00233
M3 - Conference contribution
AN - SCOPUS:85102533506
T3 - Proceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
SP - 1512
EP - 1518
BT - Proceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
A2 - Wani, M. Arif
A2 - Luo, Feng
A2 - Li, Xiaolin
A2 - Dou, Dejing
A2 - Bonchi, Francesco
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 14 December 2020 through 17 December 2020
ER -