Cognitive Navigation for Intelligent Mobile Robots:A Learning-Based Approach With Topological Memory ConfigurationOACSTPCDEI

Autonomous navigation for intelligent mobile robots has gained significant attention,with a focus on enabling robots to generate reliable policies based on maintenance of spatial mem-ory.In this paper,we propose a learning-based visual navigation pipeline that uses topological maps as memory configurations.We introduce a unique online topology construction approach that fuses odometry pose estimation and perceptual similarity estima-tion.This tackles the issues of topological node redundancy and incorrect edge connections,which stem from the distribution gap between the spatial and perceptual domains.Furthermore,we propose a differentiable graph extraction structure,the topology multi-factor transformer(TMFT).This structure utilizes graph neural networks to integrate global memory and incorporates a multi-factor attention mechanism to underscore elements closely related to relevant target cues for policy generation.Results from photorealistic simulations on image-goal navigation tasks high-light the superior navigation performance of our proposed pipeline compared to existing memory structures.Comprehen-sive validation through behavior visualization,interpretability tests,and real-world deployment further underscore the adapt-ability and efficacy of our method.