To make spatial imagination more relevant to navigation, this work introduces a cross-space planning consistency loss that encourages directional agreement between the predicted map-space trajectory and the expert action direction derived from the ground-truth waypoint displacement.
Abstract
Unmanned Aerial Vehicle Vision-Language Navigation (UAV-VLN) requires agents to follow language instructions, infer spatial structure from sparse multi-view observations, and execute feasible 3D motion in complex outdoor environments. Despite recent progress with large language models, most existing methods still map vision-language inputs directly to actions, providing limited explicit scene grounding and future-aware spatial reasoning. We propose AirForesight, a current-to-future spatial map imagination framework for UAV-VLN. AirForesight first learns a structured current-map representation from multi-view observations. This representation is jointly supervised by current-map reconstruction and future-trajectory prediction, encouraging it to encode both present scene structure and future motion intent. Under structured causal attention, the current spatial knowledge is propagated to future-map reasoning, and the resulting current and future representations are aggregated to predict the next 3D waypoint. To make spatial imagination more relevant to navigation, we introduce a cross-space planning consistency loss that encourages directional agreement between the predicted map-space trajectory and the expert action direction derived from the ground-truth waypoint displacement. Experiments on OpenUAV and AerialVLN-S, together with extensive ablations, demonstrate strong performance and support the effectiveness and stability of the proposed framework.
Autonomous unmanned aerial vehicle (UAV) object search involves a closed loop of perception, decision-making, and action under partial observability. Urban environments pose several challenges: large search areas and narrow egocentric views limit coverage, dense 3D geometry constrains safe motion, and open-world instru...
Ya-Tai Ji, Zheng-Qiu Zhu, Yong Zhao et al.· 0 citations
Foresight-Guided Action Refinement (FGAR), which asymmetrically exploits proximal foresight for local action enhancement and route-critical foresight for feature-wise correction and route-level guidance, is introduced, validating the effectiveness of dual-horizon foresight and FGAR learning.
A dual-layer semantic-spatial belief mapping framework that transforms transient VLM observations into persistent spatial guidance is proposed, and object-conditioned visual reasoning with conservative evidence qualification is introduced to improve observation reliability before spatial accumulation.
Jian-Qiang Xiao, Xiang Deng, Yue-Xuan Sun et al.· 1 citation
Aerial vision-language navigation (VLN) requires an embodied agent to integrate visual evidence over time, plan future actions, and determine when it has reached a navigation goal under partial observability. Although recent VLA models offer a promising perception-to-action paradigm, adapting them to aerial navigation...
AGC-VLN (Air-Ground Collaborative VLN), the first training-free baseline for air-ground collaborative VLN, establishes that training-free methods decompose navigation into VLM-based semantic reasoning and deterministic geometric execution, exposing a collaboration interface.
Shu-Ning Zhang, Liang Li, Yun-Heng Wang et al.· 3 citations· ⚡2
SBFNav is introduced, a closed-loop navigation framework centered on a language- conditioned Spatial Belief Field (SBF) that preserves multiple spatial hypotheses under par- tial evidence and further confirms the advantages of spatial-belief modeling over single-point prediction.
Hao-Tian Xu, Yue Hu, Zheng-Qiu Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.