UAV guidance improves finding objects using persistent belief maps
Dual-Layer Semantic-Spatial Belief Mapping for Aerial Object Goal Navigation
RoboticsArtificial Intelligence
Summary
Finding specific objects with drones is tricky because cameras give brief and unclear information about the environment. The authors created a system called AeroBelief that helps drones remember important clues about where an object might be by keeping two layers of information: one about the general scene and one about specific details of the target. Their method combines these layers to make smart guesses about where to go next and uses stable directions to keep exploring efficiently. Tests show this approach helps drones find targets better and move more effectively than previous methods.
Unmanned aerial vehicle (UAV)Object goal navigationVision-language model (VLM)Semantic-spatial belief mappingEgocentric guidanceQuadtree coverageSpatial belief hotspotTemporal commitmentConservative evidence qualification
Authors
Jianqiang Xiao, Xiang Deng, Yuexuan Sun, Yanjin Wu, Wenbiao Yan, Liqiang Nie
Abstract
Aerial Object Goal Navigation (ObjectNav) requires an unmanned aerial vehicle (UAV) to locate a described target in an unknown outdoor environment using onboard visual observations. Vision-language models (VLMs) can interpret open-ended target descriptions and visual observations, but their frame-level outputs are often noisy, sparse, and spatially transient. We propose AeroBelief, a dual-layer semantic-spatial belief mapping framework that transforms transient VLM observations into persistent spatial guidance. It separates broad contextual plausibility from target-specific evidence: an intuition layer accumulates scene-level semantic cues for exploration, while an evidence layer preserves qualified target-specific observations for approach and confirmation. Evidence-gated fusion combines the two layers into spatial belief hotspots. We further introduce object-conditioned visual reasoning with conservative evidence qualification to improve observation reliability before spatial accumulation. In parallel, egocentric regional guidance converts quadtree coverage into UAV-centered, yaw-aligned directional proposals and stabilizes them through temporal commitment. Its regional scoring is independent of semantic belief values, maintaining exploration pressure and reducing repeated low-gain search. Experiments on the UAV-ON benchmark show that AeroBelief achieves the best reported overall SR, OSR, and SPL among the compared methods, reaching 21.61%, 35.57%, and 10.62, respectively. These results support the effectiveness of persistent semantic-spatial belief, conservative evidence qualification, and temporally stable regional guidance for aerial ObjectNav.