Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Survey of Route Recommendations: Methods, Applications, and Opportunities

Shiming Zhang, Zhipeng Luo, Li Yang, Fei Teng, Tianrui Li

TL;DR

The paper surveys route recommendation in urban computing, tracing a shift from classical search- and probabilistic-based methods to modern deep learning techniques, including hybrid, sequence-based, graph-based, multi-modal, and DRL approaches. It provides a unified taxonomy linking traditional and DL methods, catalogs datasets and evaluation metrics, and reviews applications across tourism, economics, personalization, security, and indoor contexts. Key contributions include a comprehensive methodological overview, application mapping, and a discussion of open problems such as explainability, data fusion, and privacy. The findings highlight the practical significance of intelligent, data-driven routing for smarter cities and point to future directions involving multi-modal data integration and large pre-trained city models.

Abstract

Nowadays, with advanced information technologies deployed citywide, large data volumes and powerful computational resources are intelligentizing modern city development. As an important part of intelligent transportation, route recommendation and its applications are widely used, directly influencing citizens` travel habits. Developing smart and efficient travel routes based on big data (possibly multi-modal) has become a central challenge in route recommendation research. Our survey offers a comprehensive review of route recommendation work based on urban computing. It is organized by the following three parts: 1) Methodology-wise. We categorize a large volume of traditional machine learning and modern deep learning methods. Also, we discuss their historical relations and reveal the edge-cutting progress. 2) Application\-wise. We present numerous novel applications related to route commendation within urban computing scenarios. 3) We discuss current problems and challenges and envision several promising research directions. We believe that this survey can help relevant researchers quickly familiarize themselves with the current state of route recommendation research and then direct them to future research trends.

A Survey of Route Recommendations: Methods, Applications, and Opportunities

TL;DR

The paper surveys route recommendation in urban computing, tracing a shift from classical search- and probabilistic-based methods to modern deep learning techniques, including hybrid, sequence-based, graph-based, multi-modal, and DRL approaches. It provides a unified taxonomy linking traditional and DL methods, catalogs datasets and evaluation metrics, and reviews applications across tourism, economics, personalization, security, and indoor contexts. Key contributions include a comprehensive methodological overview, application mapping, and a discussion of open problems such as explainability, data fusion, and privacy. The findings highlight the practical significance of intelligent, data-driven routing for smarter cities and point to future directions involving multi-modal data integration and large pre-trained city models.

Abstract

Nowadays, with advanced information technologies deployed citywide, large data volumes and powerful computational resources are intelligentizing modern city development. As an important part of intelligent transportation, route recommendation and its applications are widely used, directly influencing citizens` travel habits. Developing smart and efficient travel routes based on big data (possibly multi-modal) has become a central challenge in route recommendation research. Our survey offers a comprehensive review of route recommendation work based on urban computing. It is organized by the following three parts: 1) Methodology-wise. We categorize a large volume of traditional machine learning and modern deep learning methods. Also, we discuss their historical relations and reveal the edge-cutting progress. 2) Application\-wise. We present numerous novel applications related to route commendation within urban computing scenarios. 3) We discuss current problems and challenges and envision several promising research directions. We believe that this survey can help relevant researchers quickly familiarize themselves with the current state of route recommendation research and then direct them to future research trends.
Paper Structure (25 sections, 15 equations, 13 figures, 4 tables)

This paper contains 25 sections, 15 equations, 13 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background
  3. What is Route Recommendation?
  4. Evaluation Metrics
  5. Datasets
  6. Classic Methods for Route Recommendation
  7. Search-based Methods
  8. Probability-based Methods
  9. Biomimetic-based Methods
  10. Clustering-based Methods
  11. Constraint-based Methods
  12. Deep learning for Route Recommendation
  13. Why Deep Learning for Route Recommendation?
  14. Hybrid Approaches
  15. Sequence-based Approaches
  16. ...and 10 more sections

Figures (13)

  • Figure 1: A route recommendation task. A user specifies a travel plan defined by departure time, source location, destination, and other preferences, and an algorithm outputs a desired route recommendation that satisfies the query.
  • Figure 2: A graph abstraction of a road network.
  • Figure 3: An example process of search-based methods. Featured by strategically searching for available paths that connect the starting node and the end node, and finally returning the computed optimal routes.
  • Figure 4: An example process of probability-based methods. Featured by obtaining the final route through sampling points and performing a proximal search in the map.
  • Figure 5: An example process of biomimetic-based methods. Featured by obtaining the final route based on the direction and speed of particle or ant colony movement. The particle density near the optimal route is marked high.
  • ...and 8 more figures

Theorems & Definitions (4)

  • Definition 1
  • Definition 2
  • Definition 3
  • Definition 4