Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction

Yu Liu1; Yuexin Zhang1; Kunming Li2; Yongliang Qiao3; Stewart Worrall2; You-Fu Li4; He Kong5

10.1109/ITSC57777.2023.10421989

2023-09-24

2023 IEEE 26th Int. Conf. on Intelligent Transportation Systems (ITSC)

2153-0009

979-8-3503-9947-9

2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC)

4360-4366

24-28 Sept. 2023

Bilbao, Spain

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different environments. For training, recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians, among others. This can limit the prediction performance across various scenarios since the discrepancies between training datasets have not been properly incorporated. To overcome this limitation, this paper proposes a graph transformer structure to improve prediction performance, capturing the differences between the various sites and scenarios contained in the datasets. In particular, a self-attention mechanism and a domain adaption module have been designed to improve the generalization ability of the model. Moreover, an additional metric considering cross-dataset sequences is introduced for training and performance evaluation purposes. The proposed framework is validated and compared against existing methods using popular public datasets, i.e., ETH and UCY. Experimental results demonstrate the improved performance of our proposed scheme.

Training Adaptation Models Pedestrians Shape Transformers Robustness Trajectory

第一 ; 通讯

英语

CPCI-S

Science, Technology, and Innovation Commission of Shenzhen Municipality, China[ZDSYS20220330161800001]

Automation & Control Systems ; Computer Science ; Transportation

Automation & Control Systems ; Computer Science, Artificial Intelligence ; Transportation Science & Technology

WOS:001178996704059

IEEE

1.Shenzhen Key Laboratory of Control Theory and Intelligent Systems, Southern University of Science and Technology (SUSTech), Shenzhen, China
2.Australian Centre for Field Robotics, The University of Sydney, NSW, Australia
3.Australian Institute for Machine Learning, The University of Adelaide, SA, Australia
4.Department of Mechanical Engineering, City University of Hong Kong, Hong Kong, SAR, China
5.Shenzhen Key Laboratory of Control Theory and Intelligent Systems, SUSTech, Shenzhen, China

Yu Liu,Yuexin Zhang,Kunming Li,et al. Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2023:4360-4366.