A prediction-based forward-looking vehicle dispatching strategy for dynamic ride-pooling

TL;DR

A forward-looking vehicle dispatching strategy is proposed, which first predicts the expected distance saving that could be brought about by future orders and then solves a bipartite matching problem based on the prediction to match passengers with partially occupied or vacant vehicles or keep passengers waiting for next rounds of matching.

Abstract

For on-demand dynamic ride-pooling services, e.g., Uber Pool and Didi Pinche, a well-designed vehicle dispatching strategy is crucial for platform profitability and passenger experience. Most existing dispatching strategies overlook incoming pairing opportunities, therefore suffer from short-sighted limitations. In this paper, we propose a forward-looking vehicle dispatching strategy, which first predicts the expected distance saving that could be brought about by future orders and then solves a bipartite matching problem based on the prediction to match passengers with partially occupied or vacant vehicles or keep passengers waiting for next rounds of matching. To demonstrate the performance of the proposed strategy, a number of simulation experiments and comparisons are conducted based on the real-world road network and historical trip data from Haikou, China. Results show that the proposed strategy outperform the baseline strategies by generating approximately 31\% more distance saving and 18\% less average passenger detour distance. It indicates the significant benefits of considering future pairing opportunities in dispatching, and highlights the effectiveness of our innovative forward-looking vehicle dispatching strategy in improving system efficiency and user experience for dynamic ride-pooling services.

Figures (4)

• Figure 1: An example of vehicle dispatching problem for dynamic ride-pooling ($\text{V}_1$ and $\text{V}_2$ are partially occupied vehicles that can form ridepooling trips with the waiting passenger $\text{P}_1$, and $\text{V}_3$ is a vacant vehicle). The blue and red triangles indicate the destinations of the passengers on the partially occupied vehicles $\text{V}_1$ and $\text{V}_2$, respectively, and the black cycle is the destination of passenger $\text{P}_1$.
• Figure 2: Two ways to serve ride-pooling passengers.
• Figure 3: Variation of demand and vehicle supply in one day
• Figure 4: Comparison of the performance under the MB, RTV and FL strategies in different hours in the Haikou experiment.

Theorems & Definitions (4)

• Definition 1: seeker-state
• Definition 2: taker-state
• Proposition 1
• proof