Abstract:
With the development of artificial intelligence (AI) for wireless, which results in burgeoning demand pressure on conventional terrestrial infrastructure, compounded by the exponential surge in Internet of Things (IoT) service requirements, the development of integrated low altitude economy (LAE) network systems. Specifically, low-altitude wireless networks confront three fundamental constraints: inherent architectural bandwidth limitations, restricted computational capabilities at aerial edge devices (e.g., drones, high-altitude platforms), and latency bottlenecks within low-altitude backhaul links. Consequently, critical functionalities like mobile sensing, data transmission, and distributed computation within these vertically stratified networks have historically been designed and deployed in isolation. This siloed approach impedes the holistic optimisation essential for minimising end-to-end latency and maximising energy efficiency across the entire low-altitude network fabric. Unlike incremental strategies focused solely on augmenting terrestrial network capacity, LAE networks offer a fundamentally distinct approach to enhancing overall network performance. Crucially, the integration of advanced computational intelligence methodologies – encompassing deep learning, optimisation theory, and LLMs – significantly augments the operational capabilities of LAE networks. These methodologies enhance the network's cognitive capacity for environmental perception and situational understanding, its learning capability to adaptively improve performance based on historical and real-time data, and its autonomous decision-making proficiency for complex resource orchestration tasks. This intelligent augmentation facilitates the dynamic and efficient allocation of scarce resources (e.g., spectrum, transmission power, computational capacities, platform trajectory) in response to fluctuating demands and heterogeneous application requirements. The core objective of this workshop is to systematically address the intricate complexities inherent in designing and implementing integrated sensing, communications, and computing IoT networks for 6G-enabled LAE systems. The advanced LAE networks must enable seamless interconnection across diverse communication environments, spanning from the stringent ultralow latency requirements of low-altitude autonomous systems to the resilient communication protocols essential for operations in different complex urban environments. Furthermore, embedding computational capabilities within these 6G IoT networks enables transformative advances in distributed data processing, edge intelligence, and decentralised computation. By leveraging technological breakthroughs such as advanced edge computing and cognitive techniques, novel capabilities emerge for real-time decision-making, robust cybersecurity enforcement, digital twin-enabled network state monitoring, and cross-domain resource optimisation within interconnected LAE domains. Sensing constitutes the critical foundation for situational awareness within integrated LAE networks, facilitating context-aware communication protocols and precise navigation in vertically stratified airspace. Deploying sophisticated sensing technologies—including distributed IoT devices and aerial remote sensing platforms—enhances environmental comprehension and refines network performance under dynamically evolving, demanding low-altitude conditions. This necessitates co-design methodologies, wherein computing, communications, and sensing functionalities are concurrently engineered and optimised. Such a holistic approach is paramount for maximising performance across diverse 6G LAE integrated sensing, computing, and communications scenarios.
Organizers:
- Prof. Shugong Xu, Xi’an Jiaotong-Liverpool University, China
- Prof. Shahid Mumtaz, Nottingham Trent University, UK
- Dr. Bintao Hu, Xi’an Jiaotong-Liverpool University, China
- Dr. Haotong Cao, Nanjing University of Posts and Telecommunications, China
- Dr. Jianbo Du, Xi'an University of Posts and Telecommunications, China