Scholarlink

<p>Last-Mile Delivery (LMD) operations are significantly impacted by real-time traffic disruptions, leading to delays and increased costs. While traditional vehicle routing problem (VRP) model struggle to adapt to dynamic traffic environments, crowdsourced data from social media platforms presents a valuable source of real-time traffic data. This research proposes Crowdsourced Adaptive Vehicle Routing Framework (CAVRF) that integrates crowdsourced social media data into the VRP model for enhanced efficiency. The framework employs a machine learning model to classify tweets based on impact severity and effectively filtering relevant traffic information. Furthermore, a mathematical model known as the Adaptive Traffic VRP (AT-VRP) has been developed to accommodate the integration of social media data with the VRP model. The framework’s effectiveness is demonstrated through a case study using a package delivery network in Jakarta with various levels of traffic disruptions. The findings suggest that integrating crowdsourced social media data into AT-VRP significantly improves efficiency by avoiding any road closure. CAVRF offers a cost-effective and efficient solution to the dynamic challenges inherent in LMD.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Crowdsourced adaptive vehicle routing framework for Last-Mile delivery in dynamic traffic environments

  • 期刊论文

  • 发表日期：

    2025年8月25日

查看全文
  • Ahmad Faisal Dahlan,
  • Chen-Yang Cheng,
  • Pornkanok Sae-chai,
  • Ranon Jientrakul,
  • Chumpol Yuangyai

摘要

Last-Mile Delivery (LMD) operations are significantly impacted by real-time traffic disruptions, leading to delays and increased costs. While traditional vehicle routing problem (VRP) model struggle to adapt to dynamic traffic environments, crowdsourced data from social media platforms presents a valuable source of real-time traffic data. This research proposes Crowdsourced Adaptive Vehicle Routing Framework (CAVRF) that integrates crowdsourced social media data into the VRP model for enhanced efficiency. The framework employs a machine learning model to classify tweets based on impact severity and effectively filtering relevant traffic information. Furthermore, a mathematical model known as the Adaptive Traffic VRP (AT-VRP) has been developed to accommodate the integration of social media data with the VRP model. The framework’s effectiveness is demonstrated through a case study using a package delivery network in Jakarta with various levels of traffic disruptions. The findings suggest that integrating crowdsourced social media data into AT-VRP significantly improves efficiency by avoiding any road closure. CAVRF offers a cost-effective and efficient solution to the dynamic challenges inherent in LMD.