paper-with-me

홈 › Papers

CLIPSwarm: Generating Drone Shows from Text Prompts with Vision-Language Models

2024-03-20 · Pablo Pueyo, Eduardo Montijano, Ana C. Murillo, Mac Schwager

This paper introduces CLIPSwarm, a new algorithm designed to automate the modeling of swarm drone formations based on natural language. The algorithm begins by enriching a provided word, to compose a text prompt that serves as input to an iterative approach to find the formation that best matches the provided word. The algorithm iteratively refines formations of robots to align with the textual description, employing different steps for "exploration" and "exploitation". Our framework is currently evaluated on simple formation targets, limited to contour shapes. A formation is visually represented through alpha-shape contours and the most representative color is automatically found for the input word. To measure the similarity between the description and the visual representation of the formation, we use CLIP [1], encoding text and images into vectors and assessing their similarity. Subsequently, the algorithm rearranges the formation to visually represent the word more effectively, within the given constraints of available drones. Control actions are then assigned to the drones, ensuring robotic behavior and collision-free movement. Experimental results demonstrate the system's efficacy in accurately modeling robot formations from natural language descriptions. The algorithm's versatility is showcased through the execution of drone shows in photorealistic simulation with varying shapes. We refer the reader to the supplementary video for a visual reference of the results.

📄 PDF Abstract BibTeX arXiv:2403.13467

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Generative AI for Safe and Photorealistic Drone Light Shows

2026-06-24 · Pascal Reinhold, Alexander Gräfe, Sebastian Trimpe arxiv

Drone light shows are redefining aerial entertainment, yet their widespread adoption is bottlenecked by labor-intensive, manual animation. While generative AI promises an automated alternative, current frameworks fail to…

DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators

2023-12-14 · Hanyang Kong, Dongze Lian, Michael Bi Mi, Xinchao Wang

We introduce DreamDrone, a novel zero-shot and training-free pipeline for generating unbounded flythrough scenes from textual prompts. Different from other methods that focus on warping images frame by frame, we advocate…

Image GenerationPerpetual View GenerationScene Generation

Enhancing Drone Light Shows Performances: Optimal Allocation and Trajectories for Swarm Drone Formations

2026-03-25 · Yunes Alqudsi arxiv

Drone light shows (DLShows) represent a rapidly growing application of swarm robotics, creating captivating aerial displays through the synchronized flight of hundreds or thousands of unmanned aerial vehicles (UAVs) as e…

Computational EfficiencyCollision Avoidance

Gen-Swarms: Adapting Deep Generative Models to Swarms of Drones

2024-08-28 · Carlos Plou, Pablo Pueyo, Ruben Martinez-Cantin, Mac Schwager 외

Gen-Swarms is an innovative method that leverages and combines the capabilities of deep generative models with reactive navigation algorithms to automate the creation of drone shows. Advancements in deep generative model…

Point Cloud Generation

AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK

2026-03-15 · Kautuk Astu, Yogesh Simmhan arxiv

Designing correct UAV autonomy programs is challenging due to joint navigation, sensing and analytics requirements. While LLMs can generate code, their reliability for safety-critical UAVs remains uncertain. This paper p…