Multi-Modal Collaborative Optimization for Sustainable Transportation Systems: Last-Mile Shuttle Service and Multi-Modal Integration Design

Abstract

As urbanization continues to accelerate, traffic congestion and environmental pollution have become increasingly serious challenges, with the “last-mile” problem emerging as a critical bottleneck limiting the overall performance of public transportation systems. Existing studies have largely focused on optimizing individual shuttle services, often overlooking the systemic synergies among multiple transport modes such as shuttles, metro systems, bike-sharing, and walking. As a result, notable research gaps remain, particularly in the evaluation of multi-modal connection efficiency and sustainability.

To address these challenges, this study proposes a data-driven multi-modal collaborative optimization framework that integrates three core components: spatiotemporal demand analysis, multi-modal connection network design, and collaborative scheduling optimization. Specifically, travel demand hotspots are first identified using the DBSCAN clustering algorithm. A multi-modal connection network is then constructed to minimize transfer times and overall travel costs. Finally, an improved Genetic Algorithm (GA) is applied to jointly optimize shuttle routes, service frequencies, and their coordination with metro and bike-sharing systems. To further enhance the framework’s relevance to sustainable mobility goals, a carbon emission model is incorporated to quantitatively evaluate environmental benefits.

A reproducible case study conducted in a typical Transit-Oriented Development (TOD) area in Shenzhen, China, demonstrates that the proposed collaborative optimization scheme significantly improves overall travel efficiency and reduces last-mile transportation-related carbon emissions compared with traditional single-mode or fixed-route shuttle services under identical experimental conditions. These results highlight the effectiveness of the proposed approach and its potential to support integrated, low-carbon last-mile transport planning.

Overall, this research provides a scientific methodology and practical decision-support tool for urban transport planners seeking to design efficient, convenient, and environmentally sustainable last-mile transportation systems. It offers both theoretical contributions and real-world implications for advancing sustainable urban mobility.