SemGeoNav:A Safety-Guided Visual Navigation Approach with Semantic Reasoning and Geometric Planning
For mobile robots navigating in open environments, this work addresses the safety limitations of end-to-end models by combining them with geometric planners.
SemGeoNav integrates semantic reasoning with geometric planning to improve obstacle avoidance in visual navigation, achieving higher success rates and shorter navigation times than ViNT and NoMaD on a real quadruped robot.
Learning-based visual navigation has enhanced semantic goal-reaching capabilities. However, due to their black-box nature, purely end-to-end models often lack explicit geometric constraints, leading to unpredictable and unreliable obstacle avoidance in open environments. Conversely, traditional geometric planners ensure safety but struggle with high-dimensional visual targets. To address these limitations, we propose SemGeoNav, a novel hierarchical visual navigation framework.It tightly integrates the high-level semantic reasoning of end-to-end models with the reliable local planning ability of geometry-based methods, achieving robust image-based navigation while significantly improving obstacle avoidance. Furthermore, we introduce a temporal trajectory smoothing mechanism to ensure continuous and stable robot motion. We evaluated SemGeoNav on a Unitree Go2 quadruped robot in real-world environments. The results demonstrate that SemGeoNav outperforms existing representative methods, including ViNT and NoMaD, achieving higher success rates and shorter navigation times.