A data-driven stacking fusion approach for pedestrian trajectory prediction

Chen, Hao; Zhang, Xi; Yang, Wenyan; Lin, Yiwei

doi:10.1080/21680566.2022.2103050

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first type is the data-driven model which is primarily developed for pedestrian trajectory prediction. [6] With the development of machine learning, advanced data-driven methods have also been developed, including deep learning, generative adversarial networks, reinforcement learning and attention mechanism. [7][8][9][10][11] These models usually perform well in predicting pedestrian trajectories.…”

Section: Introductionmentioning

confidence: 99%

Pedestrian lane formation with following–overtaking model and measurement of system order

Li 李,

Zhou 周

et al. 2024

Chinese Phys. B

View full text Add to dashboard Cite

Pedestrian self-organizing movement has played a significant role in evacuation studies and architectural design. For lane formation, a typical self-organizing phenomenon that helps pedestrian system to get more ordered, the majority of following and overtaking behavior models are imprecise and unrealistic compared with pedestrian movement in the real world. In this study, a pedestrian dynamic model considering detailed modelling of the following and overtaking behaviors is constructed, and a measure of lane formation and pedestrian system order based on information entropy is proposed. Simulation and analysis demonstrate that the following and avoidance behaviors are important factors of lane formation. A high tendency of following results in good lane formation. Both non-selective following behavior and aggressive overtaking behavior cause decrease of system order. The most orderly following strategy for a pedestrian is to overtake former pedestrian whose speed is lower than approximately 70% of their own. The influence of the obstacle layout on pedestrian lanes and egress efficiency is also studied with this model. The presence of a small obstacle may not obstruct the walking of pedestrians; in contrast, it may help to improve the egress efficiency by guiding the pedestrian flow and mitigating the reduction of pedestrian system orderliness.

show abstract