Frame diagram of the ST-GNN model.

<div><p>Urban dynamic ride-pooling faces significant challenges in achieving efficient real-time order matching and path planning, primarily due to the complex spatio-temporal coupling of passenger demand and traffic conditions. Traditional algorithms often struggle to dynamically integr...

وصف كامل

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Xue Xing (20756069) (author)
مؤلفون آخرون:	Yuqi Peng (7865273) (author), Le Wan (4905928) (author), Fahui Luo (21722006) (author)
منشور في:	2025
الموضوعات:	Medicine Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified shared mobility systems optimize travel distance improved dijkstra algorithm generate optimal paths didi chuxing ), pooling orders based learn node embeddings urban dynamic ride matching success rate passenger time windows div >< p 34 kg co time order matching achieving efficient real passenger ride pooling pairs per order embeddings inform efficient solution suitable ride passenger detour world dataset world constraints transformer mechanisms traffic conditions temporal graph temporal coupling temporal collaboration study proposes strictly adhering scale real results demonstrate primarily due path planning novel dual method achieves intelligent upgrade head attention dynamically integrate complex scenarios carbon emissions built upon approach begins
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

Frame diagram of the ST-GNN model.

مواد مشابهة