机器人2026，Vol.48Issue(1)：11-24,14.DOI:10.13973/j.cnki.robot.240248
基于拓扑图和大语言模型的灵活可控社交导航
Flexible and Controllable Social Navigation Based on Topological Graph and Large Language Model
摘要
Abstract
Social navigation requires robots to make flexible decisions based on the understanding of complex environ-ments and human social rules,get rid of dependence on specific model functions and make full use of extensive world knowledge.So a general navigation framework based on topological graphs and large language models is proposed.First-ly,an environment understanding method is developed based on obstacle clustering and graph theory to provide candidate guiding points for the robot.Secondly,role-playing and few-shot closed-loop optimization mechanisms of large language models are utilized to determine the optimal point,and trajectories are generated and optimized with the guiding point as the target.Finally,experimental verification is conducted in multiple static and dynamic scenes,and tests are performed on 4 large language models.The result shows that the navigation is controllable by combining the guiding points with traditional trajectory optimization.The world knowledge of large models enables the robot to achieve a good balance between motion efficiency and social attributes.The proportion of locally optimal decisions reaches 97.94％.关键词
社交导航/大语言模型/拓扑图/少样本学习/轨迹同伦/角色扮演Key words
social navigation/large language model/topological graph/few-shot learning/trajectory homotopy/role-playing引用本文复制引用
杨宜凡,张千一,宋一诺,朱泽卿,刘景泰..基于拓扑图和大语言模型的灵活可控社交导航[J].机器人,2026,48(1):11-24,14.基金项目
国家自然科学基金(62173189). （62173189）
