Geographic information system navigation services are now incorporating psychological well-being as a factor when devising navigation routes. However, challenges such as limited data, method generalizability, and subjective human perception remain unresolved. Therefore, a general humanized path-navigation method that effectively quantifies human emotional perception demands is required. In this study, we designed a deep learning model using a large, crowdsourced dataset to predict emotional responses to street-view images. Our method enhances urban path planning, thus providing comprehensive emotional benefits. Our approach and several goal-oriented methods were applied in Nanjing, and the findings were compared via comparative analyses and questionnaire surveys. The results confirmed that our proposed method outperforms utilitarian goal-driven path planning methods in terms of subjective perception. This study provides a widely available technique for high-quality navigation planning that meets psychological perception needs and offers a valuable guidance for the research on humanized geographic information services.

中文翻译：

---

融合人类情感感知学习的城市高质量导航路径规划

地理信息系统导航服务现在正在将心理健康作为设计导航路线时的一个因素。然而，数据有限、方法普遍性和人类主观感知等挑战仍未得到解决。因此，需要一种有效量化人类情感感知需求的通用人性化路径导航方法。在这项研究中，我们使用大型众包数据集设计了一个深度学习模型来预测对街景图像的情绪反应。我们的方法增强了城市路径规划，从而提供全面的情感效益。我们的方法和几种目标导向的方法在南京得到应用，并通过比较分析和问卷调查对结果进行比较。结果证实，我们提出的方法在主观感知方面优于功利主义目标驱动的路径规划方法。本研究为满足心理感知需求的高质量导航规划提供了一种广泛可用的技术，为人性化地理信息服务的研究提供了有价值的指导。