RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Di Lu, Bo Zhang, Xiyuan Li, Yongzhi Liao, Xuewen Dong, Yulong Shen, Zhiquan Liu, Jianfeng Ma
• Venue: arXiv: cs.CR
• Published: 2026-07-20
• Collected: 2026-07-21
• URL: http://arxiv.org/abs/2607.17951v1
• PDF: https://arxiv.org/pdf/2607.17951v1
• DOI: UNKNOWN

Plain-Language Brief

The paper proposes a system called Real-Time Self-Hosted Computer-Use Agent (RT-SHCUA) for unmanned aerial vehicles (UAVs). This system aims to address the challenges of directly applying SHCUAs to UAV control, which includes safety risks and strict timing constraints. The proposed system restructures SHCUA-based UAV control to transform its outputs into contract-bound UAV skill invocations with explicit timing, state, authority, fallback, and evidence semantics. This design separates semantic reasoning from onboard execution and security/safety enforcement.

What the Document Says

• The paper discusses a system for UAV control called RT-SHCUA.
• RT-SHCUA is designed to address the challenges of directly applying SHCUAs to UAV control.
• RT-SHCUA transforms its outputs into contract-bound UAV skill invocations with explicit timing, state, authority, fallback, and evidence semantics.
• The system separates semantic reasoning from onboard execution and security/safety enforcement.

Key Concepts Mentioned

• Real-Time Self-Hosted Computer-Use Agent (RT-SHCUA)
• UAV control
• structural mismatch
• delayed agent iterations
• continuously changing physical states
• strict timing constraints
• safety risks
• security accountability
• stale agent decision
• unauthorized or tampered agent decision
• unsafe vehicle behavior
• untraceable vehicle behavior
• contract-bound UAV skill invocations
• semantic reasoning
• onboard execution
• security/safety enforcement
• mission understanding
• TEE-style or microcontroller isolation mechanisms

Claims Made by the Document

• RT-SHCUA maintains bounded task-level responsiveness.

Evidence Used

• Prototype evaluation shows that RT-SHCUA maintains bounded task-level responsiveness.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.