Recommending taxi routes with an advance reservation – a multi-criteria route planner

Abstract

In this paper, we propose a multi-criteria route recommendation framework that considers real-time spatial–temporal predictions and traffic network information, aiming to optimize a taxi driver’s profit when considering an advance reservation. Our framework consists of four components. First, we build a grid-based road network graph for modelling traffic network information during the search process. Next, we conduct two prediction modules that adopt advanced deep learning techniques to guide proper search directions in the final planning stage. One module, taxi demand prediction, is used to estimate the pick-up probabilities of passengers in the city. Another one is destination prediction, which can predict the distribution of drop-off probabilities and capture the flow of potential passengers. Finally, we propose J* (J-star) algorithm, which jointly considers pick-up probabilities, drop-off distribution, road network, distance, and time factors based on the attentive heuristic function. Compared with existing route planning methods, the experimental results on a real-world dataset have shown our proposed approach is more effective and robust. Moreover, our designed search scheme in J* can decrease the computing time and make the search process more efficient. To the best of our knowledge, this is the first work that focuses on designing a guiding route, which can increase the income of taxi drivers when they have an advance reservation.Highlights• A novel system to recommend routes for taxi drivers under a reservation constraint.• The planning route can increase driver’s profit and build customer trust.• The framework effectively combines deep learning modules and a search algorithm.• The designed search algorithm boosts effectiveness and efficiency on real data.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.