作者: Zhixiang Fang , Qingquan Li , Xing Zhang
DOI: 10.1080/13658816.2010.500290
关键词: Pedestrian navigation 、 Landmark 、 Pedestrian 、 Machine learning 、 Artificial intelligence 、 Process (computing) 、 Geography 、 Representation (mathematics) 、 Overall performance 、 Ant colony optimization algorithms
摘要: Landmarks provide the most predominant navigational cue for pedestrian navigation. The choice and representation of landmarks require an optimal approach to meet needs pedestrians, example, shorter distances, fewer turns, easy confirmation. This article proposes a multiobjective model generate landmark sequences route instructions. offers general diverse pedestrians. A modified ant colony optimization (ACO) algorithm is used implement proposed model. research determined parameters ACO by testing whole study area using various weight combinations. also discusses process cases, different origin-destination (OD) pairs, areas, influence density, overall performance comparison in achieving four objectives. Experimental results have confirmed that this can optimize