REVIEW 8 cited by
NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Vision-and-Language Navigation (VLN), as a widely discussed research direction in embodied intelligence, aims to enable embodied agents to navigate in complicated visual environments through natural language commands. Most existing VLN methods focus on indoor ground robot scenarios. However, when applied to UAV VLN in outdoor urban scenes, it faces two significant challenges. First, urban scenes contain numerous objects, which makes it challenging to match fine-grained landmarks in images with complex textual descriptions of these landmarks. Second, overall environmental information encompasses multiple modal dimensions, and the diversity of representations significantly increases the complexity of the encoding process. To address these challenges, we propose NavAgent, the first urban UAV embodied navigation model driven by a large Vision-Language Model. NavAgent undertakes navigation tasks by synthesizing multi-scale environmental information, including topological maps (global), panoramas (medium), and fine-grained landmarks (local). Specifically, we utilize GLIP to build a visual recognizer for landmark capable of identifying and linguisticizing fine-grained landmarks. Subsequently, we develop dynamically growing scene topology map that integrate environmental information and employ Graph Convolutional Networks to encode global environmental data. In addition, to train the visual recognizer for landmark, we develop NavAgent-Landmark2K, the first fine-grained landmark dataset for real urban street scenes. In experiments conducted on the Touchdown and Map2seq datasets, NavAgent outperforms strong baseline models. The code and dataset will be released to the community to facilitate the exploration and development of outdoor VLN.
Forward citations
Cited by 8 Pith papers
-
Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification
Rule-VLN is the first large-scale benchmark injecting 177 regulatory categories into an urban environment, and the proposed SNRM module equips pre-trained VLN agents with zero-shot semantic reasoning and detour planni...
-
Parse, Search, and Confirmation: Training-Free Aerial Vision-and-Dialog Navigation with Chain-of-Thought Reasoning and Structured Spatial Memory
A three-stage parse-search-confirm MLLM pipeline plus structured spatial memory sets training-free SOTA on AVDN, matching or beating several supervised methods on ANDH and ANDH-Full.
-
Deliberate Before You Fly: Vision-Guided Spatial Deliberation for UAV See-and-Reach Navigation
DBFly improves UAV see-and-reach success by adding explicit spatial reasoning steps (direction, diagnosis, maneuver, stop) before predicting waypoints, reporting a 25-point gain over the prior SOTA on the UAV-VLN-FOV ...
-
When Large Language Models Meet UAV Projects: An Empirical Study from Developers' Perspective
The first empirical taxonomy of LLM tasks in UAVs, with an academia-industry comparison and survey, shows LLMs are used mainly for planning and interaction, not direct control.
-
UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agents
UAV-ON is a new benchmark of 14 Unreal Engine environments with 1270 annotated objects that tests whether aerial agents can navigate to goals described by semantic instance-level instructions.
-
A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigation
VLN methods show a large sim-to-real gap; a hierarchical system reaches 51% real-world success versus 22% for a monolithic RGB-only system across ten physical scenes.
-
Towards Effcient Low Altitude Sensing: A Dual Heterogeneous Graph Learning Method for UAV Task Allocation
Matching a directed task graph to a UAV communication graph with GAT, cross-attention, and PPO yields more completed dependent sensing tasks and lower makespan than standard baselines in simulation.
-
Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation
A zero-shot aerial VLN system that has an MLLM output only 2D image coordinates, then uses depth unprojection and Ego-Planner to navigate, reporting >20 percentage-point SR gains and 31–37% NE reductions over baselines.
Discussion (0). Sign in to comment.