Topic: Large Models for Aerial Robotics: Perception, Reasoning, and Edge Computing

Unmanned Aerial Vehicles (UAVs) are rapidly evolving from remotely controlled sensors into autonomous intelligent agents. While traditional visual perception algorithms (detection, tracking, and segmentation) have reached a level of maturity, the next frontier lies in semantic understanding and real-time reasoning in complex, open-world environments.

The emergence of Vision-Language Models (VLMs) and Large Multimodal Models (LMMs) offers unprecedented capabilities for zero-shot learning, open-vocabulary detection, and human-machine interaction. However, deploying these massive models on UAVs presents significant challenges due to the strict constraints on Size, Weight, and Power (SWaP).

This Special Issue aims to bridge the gap between high-level artificial intelligence (AI) capabilities and low-level edge implementation in aerial robotics. We seek cutting-edge research that addresses the adaptation of foundation models for aerial imagery, the design of lightweight networks for onboard processing, and the development of embodied AI systems that enable UAVs to perceive, reason, and act autonomously.

Topics of interest include, but are not limited to:

● VLMs for UAVs;

● Open-vocabulary perception;

● Visual grounding andreasoning;

● Generative AI for data augmentation;

● 3D perception and neural rendering for aerial scenes;

● Mobile-friendly Transformers and convolutional neural networks (CNNs) designed specifically for aerial inputs;

● Image restoration and enhancement for UAVs operating inchallenging conditions such as fog, rain, low light, or haze;

● Embodied AI andautonomy, UAV path planning, multi-UAV visual fusion, and swarm intelligence.

UAV Vision, vision-language models, edge AI, onboard processing, open-vocabulary detection, embodied AI, model compression, aerial semantic understanding