MVP-Nav: Multi-layer Value Map Planner Navigator
For embodied agents operating without depth sensors, this work provides a physically grounded navigation framework that improves safety and success rates in zero-shot object goal navigation.
MVP-Nav addresses zero-shot object goal navigation with RGB-only perception by reconstructing 3D physical occupancy from monocular images using 3D foundation models and integrating semantic and geometric information into a Multi-layer Value Map. It achieves state-of-the-art performance on zero-shot object navigation benchmarks, outperforming existing depth-free methods.
Zero-shot Object Goal Navigation (ZSON) with RGB-only perception poses a fundamental challenge for embodied agents, as the absence of explicit depth information introduces severe physical uncertainty and semantic-physical misalignment. Existing approaches either rely on high-level semantic reasoning without geometric grounding or learn end-to-end policies that lack explicit physical constraints, often resulting in semantically plausible but physically unsafe behaviors. In this paper, we propose MVP-Nav, a physical-aware RGB-only navigation framework that aligns perception, planning, and control with the real 3D world. MVP-Nav reconstructs explicit physical occupancy from monocular observations by leveraging 3D foundation models to project 2D semantic instances into 3D oriented bounding boxes, forming a global spatial semantic representation. To unify high-level semantic reasoning and low-level physical constraints, we introduce a Multi-layer Value Map (MVM) that integrates semantic priorities and reconstructed geometry into a shared cost space, enabling physically grounded geometric planning. Extensive experiments on zero-shot object navigation benchmarks demonstrate that MVP-Nav significantly outperforms existing depth-free methods, achieving state-of-the-art performance and validating that structured physical priors can effectively compensate for the absence of active depth sensors.