FlockGPT: Guiding UAV Flocking with Linguistic Orchestration
Bibliographic record
Abstract
The paper introduces the first rapid drone flocking control using natural language via generative AI. This approach enables the intuitive orchestration of a drone flock of any size to form desired geometries. The core innovation is a new interface based on Large Language Models (LLMs) that allows user interaction and target geometry description. Users can modify or comment on the flock geometry model interactively. By integrating flocking technology with target surface definition through a signed distance function, smooth and adaptive swarm movement is achieved. A user 1study on FlockGPT showed high intuitive control over drone flocking. Participants without prior experience constructed complex shapes in a few iterations and accurately recognized the figures. The study demonstrated a high recognition rate for six geometric patterns generated through the LLM-based interface, with an 80% mean and up to 93% for cube and tetrahedron patterns. Users reported low temporal demand (NASA-TLX score of 19.2), high performance (NASA-TLX score of 26), attractiveness (UEQ score of 1.94), and hedonic quality (UEQ score of 1.81). The FlockGPT demo code is available at: https://github.com/Taintedy/flock_gpt
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.010 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".