Guest Editor(s)
Prof. Jordan Pascual Espada
Email: pascualjordan@uniovi.es
Affiliation: Department of Computer Science
University of Oviedo, Oviedo, Spain
Homepage:
Research Interests: internet of Things (IoT); large language models (LLMs) & generative AI; human-computer interaction & web technologies; applied emerging technologies
Prof. José Rodríguez Piñeiro
Email: j.rpineiro@tongji.edu.cn
Affiliation: College of Electronics and Information Engineering, Tongji University, Shanghai, China
Homepage:
Research Interests: millimeter-wave channel characteristics; UAV communications & mobile systems; AI-based communication solutions; applied photogrammetry
Prof. Lucía Alonso Virgós
Email: lucia.alonso.virgos@unir.net
Affiliation: International University of La Rioja, Logroño, Spain
Homepage:
Research Interests: artificial intelligence & computer vision: large language models (LLMs) & generative AI; web usability and UI guidelines; industrial engineering & automated systems
Summary
Recent advancements in Large Language Models (LLMs) and Multi-Agent Systems (MAS) have shifted the paradigm of artificial intelligence from passive text processing to active, real-world decision-making. "Embodied AI" bridges the gap between digital cognitive capabilities and physical execution. Integrating LLMs and autonomous agents into Robotics, Unmanned Aerial Vehicles (UAVs/Drones), and Internet of Things (IoT) ecosystems allows these systems to understand complex human instructions, reason about physical environments, and collaborate autonomously. This intersection is crucial for advancing smart manufacturing, autonomous search and rescue, precision agriculture, and next-generation cyber-physical infrastructure.
This Special Issue aims to gather cutting-edge research, novel methodologies, and comprehensive reviews focused on the deployment, optimization, and security of LLMs and AI agents within physical and constrained environments. We welcome contributions that address the challenges of computational efficiency, real-time processing, multi-modal sensor fusion, and reliable decision-making in robotic, drone, and IoT networks. By fostering interdisciplinary research, this issue seeks to bridge computer science applications with multidisciplinary engineering and simulation.
Scope (including but not limited to):
· LLM-based task planning and reasoning for autonomous robots and drones.
· Multi-agent collaboration and orchestration in IoT-enabled smart environments.
· Edge-computing and optimization of Lightweight LLMs for resource-constrained hardware.
· Multi-modal LLMs (Vision-Language-Action models) for real-world environmental perception.
· Simulation and modeling frameworks for testing Embodied AI in cyber-physical systems.
· Security, privacy, and safety-critical alignment of LLM agents in physical infrastructure.
· Real-time human-robot interaction (HRI) mediated by natural language processing.
· Applications of LLM agents in autonomous logistics, smart cities, and environmental monitoring.
· Applications of LLM agents in autonomous logistics, smart cities, and environmental monitoring.
Keywords
embodied AI, large language models (LLMs), vision-language models (VLMs);large multimodal models (LMMs); autonomous agents; robotic task planning; UAV and drone swarms; internet of things (IoT), cyber-physical systems; multi-agent simulation.
Login
Register
Submit a Paper
Propose a Special lssue