ASNN-FRR: A traffic-aware neural network for fastest route recommendation

• Published in: GeoInformatica Vol. 27; no. 1; pp. 39 - 60
• Main Authors: Wang, Chaoxiong, Li, Chao, Huang, Hai, Qiu, Jing, Qu, Jianfeng, Yin, Lihua
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.01.2023; Springer; Springer Nature B.V
• Subjects: Algorithms; Analysis; Computer Science; Cost function; Data Structures and Information Theory; Geographical Information Systems/Cartography; Information Storage and Retrieval; Lower bounds; Multimedia Information Systems; Neural networks; Travel time; Traffic speed prediction; Travel time prediction; Fastest route planning; Heuristic search
• ISSN: 1384-6175; 1573-7624
• DOI: 10.1007/s10707-021-00458-7

Fastest route recommendation (FRR) is an important task in urban computing. Despite some efforts are made to integrate A ∗ algorithm with neural networks to learn cost functions by a data driven approach, they suffer from inaccuracy of travel time estimation and admissibility of model, resulting sub-optimal results accordingly. In this paper, we propose an ASNN-FRR model that contains two powerful predictors for g (⋅) and h (⋅) functions of A* algorithm respectively. Specifically, an adaptive graph convolutional recurrent network is used to accurately estimate the travel time of the observed path in g (⋅). Toward h (⋅), the model adopts a multi-task representation learning method to support origin-destination (OD) based travel time estimation, which can achieve high accuracy without the actual path information. Besides, we further consider the admissibility of A* algorithm, and utilize a rational setting of the loss function for h (⋅) estimator, which is likely to return a lower bound value without overestimation. At last, the two predictors are fused into the A ∗ algorithm in a seamlessly way to help us find the real-time fastest route. We conduct extensive experiments on two real-world large scale trip datasets. The proposed approach clearly outperforms state-of-the-art methods for FRR task.