Large multimodal models display emerging but limited spatial action capabilities in goal-oriented urban 3D navigation, remaining far from human-level performance with errors diverging rapidly after critical decision points.
Aeroverse: Uav- agent benchmark suite for simulating, pre-training, finetuning, and evaluating aerospace embodied world models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 5polarities
background 2representative citing papers
This survey organizes aerial vision-language navigation methods into five architectural categories, critically reviews evaluation infrastructure, and synthesizes seven open problems for LLM/VLM integration.
A universal LLM-to-drone interface is implemented via the Model Context Protocol (MCP) and Mavlink, demonstrated with real UAV flight control and simulated flights using live map data.
AirVista-II integrates agent-based task identification and scheduling, multimodal perception, and scenario-tailored keyframe extraction to deliver high-quality zero-shot semantic understanding for embodied UAVs in dynamic environments.
Automation in embodied benchmark construction shifts costs from acquisition toward validation, auditability, version control, and long-term governance instead of simply lowering total cost.
citing papers explorer
-
How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace
Large multimodal models display emerging but limited spatial action capabilities in goal-oriented urban 3D navigation, remaining far from human-level performance with errors diverging rapidly after critical decision points.
-
Vision-Language Navigation for Aerial Robots: Towards the Era of Large Language Models
This survey organizes aerial vision-language navigation methods into five architectural categories, critically reviews evaluation infrastructure, and synthesizes seven open problems for LLM/VLM integration.
-
A Universal Large Language Model -- Drone Command and Control Interface
A universal LLM-to-drone interface is implemented via the Model Context Protocol (MCP) and Mavlink, demonstrated with real UAV flight control and simulated flights using live map data.
-
AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding
AirVista-II integrates agent-based task identification and scheduling, multimodal perception, and scenario-tailored keyframe extraction to deliver high-quality zero-shot semantic understanding for embodied UAVs in dynamic environments.
-
Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends
Automation in embodied benchmark construction shifts costs from acquisition toward validation, auditability, version control, and long-term governance instead of simply lowering total cost.