Natural-language control offers a promising interface for unmanned aerial vehicles (UAVs), but directly applying self-hosted computer-use agents (SHCUAs) to UAV control introduces a structural mismatch. SHCUAs are designed for interactive host-side tool use, where delayed agent iterations are often acceptable. UAV control, however, is coupled with continuously changing physical states, strict timing constraints, safety risks, and security accountability. A stale, unauthorized, or tampered agent decision may therefore lead to unsafe or untraceable vehicle behavior. This paper proposes a real-time and security-oriented restructuring of SHCUA-based UAV control. Instead of allowing an SHCUA to directly issue flight commands, we transform its outputs into contract-bound UAV skill invocations with explicit timing, state, authority, fallback, and evidence semantics. Based on this abstraction, we design an architecture that separates semantic reasoning from onboard execution and security/safety enforcement. Slow cloud or edge reasoning is used for mission understanding, while onboard components validate and dispatch only timely, authorized, and state-consistent skills. Security-critical enforcement points can be protected by TEE-style or microcontroller isolation mechanisms without moving the full language agent or high-frequency flight-control loop into trusted components. Prototype evaluation shows that RT-SHCUA maintains bounded task-level responsiveness while supporting degraded handling, trusted admission, and auditable evidence preservation for SHCUA-mediated UAV actions.
The massive influx of uplink task offloading in Multi-access Edge Computing (MEC) systems poses a significant challenge to the capacity of wireless networks. This challenge highlights a fundamental trade-off between Orthogonal Multiple Access (OMA), which provides interference-free but spectrally inefficient communication, and Non-Orthogonal Multiple Access (NOMA), which enhances capacity at the cost of significant inter-user interference. To navigate this trade-off, we introduce a novel Hybrid NOMA (H-NOMA) framework that offers differentiated communication services. The framework allows users to choose between premium OMA channels for latency-sensitive tasks and shared NOMA channels for others, creating an economy where performance can be traded for cost. Within this framework, we formulate the resource allocation problem with the objective of maximizing the total system utility, defined as the sum of all individual user utilities, under budget, computation, and communication constraints. To solve this NP-hard problem, we devise a novel multi-stage game-theoretic algorithm, the Matching-Coalition Game with Coordinate Descent (MCGCD). Our approach synergistically combines matching theory for a fast and initial channel assignment, a cooperative coalition game to refine allocations by explicitly managing NOMA externalities, and a coordinate-descent-based algorithm for optimal power control. Extensive simulations demonstrate that our proposed algorithm significantly outperforms benchmark methods in improving system utility, reducing average task completion latency, and increasing the number of admitted tasks.
Haolin Liu, Hao Yin, Haibo Zhou et al.· IEEE Transactions on Mobile...· 0 citations