DRIVE-Nav: Directional Reasoning, Inspection, and Verification for Efficient Open-Vocabulary Navigation
2026-03-30 • Robotics
Robotics
AI summaryⓘ
The authors propose DRIVE-Nav, a new method to help robots find objects by exploring unknown spaces more efficiently. Instead of looking at many small points, their system focuses on fewer important directions and checks them more thoroughly, which reduces extra walking and revisits. They tested DRIVE-Nav in different simulated environments and on a real robot, showing it finds targets more reliably and faster than previous methods. This approach combines smart path tracking with better understanding of language and vision cues to improve navigation.
Open-Vocabulary Object NavigationEmbodied AgentFast Marching MethodSemantic InspectionZero-shot MethodsPath EfficiencySuccess Rate (SR)Success weighted by Path Length (SPL)HM3D-OVONVision-language Grounding
Authors
Maoguo Gao, Zejun Zhu, Zhiming Sun, Zhengwei Ma, Longze Yuan, Zhongjing Ma, Zhigang Gao, Jinhui Zhang, Suli Zou
Abstract
Open-Vocabulary Object Navigation (OVON) requires an embodied agent to locate a language-specified target in unknown environments. Existing zero-shot methods often reason over dense frontier points under incomplete observations, causing unstable route selection, repeated revisits, and unnecessary action overhead. We present DRIVE-Nav, a structured framework that organizes exploration around persistent directions rather than raw frontiers. By inspecting encountered directions more completely and restricting subsequent decisions to still-relevant directions within a forward 240 degree view range, DRIVE-Nav reduces redundant revisits and improves path efficiency. The framework extracts and tracks directional candidates from weighted Fast Marching Method (FMM) paths, maintains representative views for semantic inspection, and combines vision-language-guided prompt enrichment with cross-frame verification to improve grounding reliability. Experiments on HM3D-OVON, HM3Dv2, and MP3D demonstrate strong overall performance and consistent efficiency gains. On HM3D-OVON, DRIVE-Nav achieves 50.2% SR and 32.6% SPL, improving the previous best method by 1.9% SR and 5.6% SPL. It also delivers the best SPL on HM3Dv2 and MP3D and transfers to a physical humanoid robot. Real-world deployment also demonstrates its effectiveness. Project page: https://coolmaoguo.github.io/drive-nav-page/