Vehicle Routing Incorporating Implicit Preferences: An Omnidimensional Human–Algorithm Collaboration Approach

Due to the complexity and dynamism of real-world needs, traditional vehicle routing solutions usually do not sufficiently consider implicit user preferences, leading to low acceptance and reduced practical performance. To address this issue, we propose an omnidimensional human–algorithm collaboration framework that features a novel “task assignment first, route construction second” algorithm and omnidimensional human–algorithm interaction methods. This framework supports users in expressing complex preference information across four dimensions: decision variables, constraints, objectives, and solutions. The algorithm is designed to learn user preferences and utilize computational search to provide efficient, tailored feedback. A user-friendly graphical interface system was developed to facilitate intuitive human–algorithm interaction. We conducted user experiments with 20 participants based on a real-world multiobjective road cleaning problem. The results demonstrated the system’s effectiveness in incorporating users’ implicit preferences—beyond explicit preferences—and its usability in providing positive user experience. This study represents a significant step toward making vehicle routing algorithms more practical and user-centric.