Multi-Objective Route Planning Methods for Urban Exploration

This paper reviews route generation methods for Citywalk and urban exploration scenarios from the perspective of multi-objective route planning. The problem is formalized as MO-Citywalk-RP, where walking routes are generated by jointly considering user preferences, emotional experience, walking comfort, time windows, budget limits, and spatial accessibility. Focusing on three key issues—personalized demand analysis, multi-objective itinerary optimization, and dynamic interaction—this study summarizes related methods in preference modeling, candidate generation, constraint handling, evolutionary optimization, machine learning enhancement, and interactive adjustment. The review shows that Citywalk route planning is shifting from static shortest-path search to an intelligent urban mobility decision problem integrating POI recommendation, spatio-temporal constraints, and human feedback. Future directions include multi-source preference fusion, hybrid intelligent solvers, and natural-language-driven interactive optimization for smart tourism and sustainable pedestrian mobility.