SWAN generates collision-free drone swarm trajectories from text prompts via video synthesis, adaptive point tracking, planning, and safety filtering, demonstrated in simulation up to 2000 drones and real tests with 49 quadcopters.
Swarm-gpt: Combining large language models with safe motion planning for robot choreography design
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
method 1polarities
use method 1representative citing papers
An LLM agent framework with Web-of-Things standardization and a Model Context Protocol gateway enables natural-language UAV swarm missions, with simulation results showing that explicit grounding tools and guardrails substantially raise execution reliability across six models and four tasks.
A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.
citing papers explorer
-
Generative AI for Safe and Photorealistic Drone Light Shows
SWAN generates collision-free drone swarm trajectories from text prompts via video synthesis, adaptive point tracking, planning, and safety filtering, demonstrated in simulation up to 2000 drones and real tests with 49 quadcopters.
-
Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones
An LLM agent framework with Web-of-Things standardization and a Model Context Protocol gateway enables natural-language UAV swarm missions, with simulation results showing that explicit grounding tools and guardrails substantially raise execution reliability across six models and four tasks.
-
Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.