Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.26916

StarMind: Challenges and Opportunities in Orbital Computing

Zisheng Gong·Zhaoyu Liu·Houtianfu Wang·O. Tansel Baydas·Liu Cao·Xia Xu·Ozgur B. Akan
View original source ↗Read source document ↗Export metadata ↓

Abstract

Space-based artificial intelligence (AI) is moving beyond isolated onboard processing toward constellation-scale computing over optical inter-satellite links (OISLs). Yet current infrastructures remain fragmented, making end-to-end (E2E) coordination across heterogeneous and multi-vendor systems difficult. This article examines the StarMind vision and develops a reference framework for distributed orbital computing. It organizes the system into five layers and defines six standardizable interfaces that link mission intent to resource conditions and trustworthy result delivery. The framework also clarifies the operational constraints that determine whether orbital cooperation is worthwhile. In a representative synthetic aperture radar/interferometric SAR (SAR/InSAR) case study, the framework reduces E2E latency to 41-min, compared with 61-min for localized onboard computing and 146-min for ground-based processing. This gain does not rely on faster processors in orbit. Instead, it comes from reducing contact waiting and urgent Earth downlink traffic through resource-aware task placement and gateway selection. Feasibility analysis shows that the proposed framework is more effective when source datasets are large, output products are compact, and optical inter-satellite link capacity is sufficient. When these conditions are absent, conventional processing may remain preferable. Finally, we discuss research opportunities in joint task partitioning and cross-domain orchestration, hierarchical federated intelligence, and large model-enabled intelligence to advance an interoperable space-ground computing continuum.

Explore related subjects

cs.NIcs.SYeess.SY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Zisheng Gong, Zhaoyu Liu, Houtianfu Wang, O. Tansel Baydas, Liu Cao, Xia Xu, Ozgur B. Akan. 2026-10-17. StarMind: Challenges and Opportunities in Orbital Computing. https://arxiv.org/abs/2610.26916

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

6G: From Connectivity Infrastructure to Guaranteed Digital Services

Sixth-generation (6G) mobile networks offer an opportunity to align network architecture with operator control, verifiable service outcomes, and governed automation. This article develops four complementary contributions. The Control Compact allocates ownership and governance responsibilities through an own-federate-consume taxonomy. The Guarantee Economy proposes six outcome-priced service tiers aligned with IMT-2030 usage scenarios. The Network MCP Platform, the principal contribution, is a conceptual reference architecture that uses the Model Context Protocol (MCP) to connect agentic workflows to operational tools and telecom execution interfaces under operator-defined governance. Two real-network examples from Rakuten Mobile illustrate MCP-enabled agentic workflows: radio access network (RAN) second-line (L2) support combines diagnosis, remediation, and outcome verification, while IP Multimedia Subsystem (IMS) availability investigation combines evidence collection, adaptive investigation, and reporting. These examples support operational feasibility; evaluation of the complete platform, and its performance and security properties, remains future work. A separate TM Forum Level 4 assessment corroborates deployed closed-loop autonomy for a scoped RAN energy-optimization scenario. The fourth contribution presents Rakuten Mobile's public standardization position and a phased deployment roadmap. The analysis distinguishes operational records, external assessment evidence, standards-based requirements, and proposed architectural and commercial extensions. It identifies validation requirements for broader deployment and outcome-based service assurance.

cs.NI↗
arXiv2026

Blackbox Performance Analysis of LLM-based Network Control

LLMs are becoming an indispensable part of network control systems due to their impressive reasoning. Before such LLM-enabled systems can be deployed, it is imperative to develop tools that can audit their performance on previously unseen inputs. However, auditing these systems is challenging due to the inherent opacity of LLMs. LENS is the first step towards black-box performance analysis of LLM-enabled network control systems. It uses novel methods to extend deep reinforcement learning to guide the search for performance gaps and inputs that make LLMs struggle. LENS finds large gaps for LLM-based traffic engineering and GPU allocation systems, and even matches existing white-box analyzers designed for hand-crafted TE heuristics.

cs.NI↗
arXiv2026

NetGuise: Adversarial Traffic Generation for Early-Stage Classifier Evasion

Early-stage encrypted traffic classifiers make decisions from only the first few packets of a connection, enabling low-latency classification but raising robustness concerns under realistic traffic morphing. Existing adversarial traffic generation methods often assume complete flows, feature-level perturbations, or iterative runtime feedback, which do not match the constraints of early-stage execution. We present NetGuise, a target-conditioned traffic morphing framework that generates packet-level padding and non-negative delay actions while preserving packet direction, ordering, and packet count and respecting MTU, bandwidth, and latency constraints. We evaluate NetGuise for censorship evasion under two observation interfaces, i) a history-only causal interface for online packet-by-packet execution, ii) and a full-window oracle interface that provides an upper-bound characterization of early-stage morphability. On VANT, NetGuise achieves 33.2% mean targeted evasion under the causal interface versus 82.0% under the oracle interface; on UTMobileNet, the corresponding results are 5.6% and 81.8%. NetGuise outperforms the strongest causal baseline, BAP, on both datasets and, on VANT, reduces bandwidth overhead from 19.80% to 3.02% and generation latency from 37.42 ms/flow to 1.16 ms/flow. Under the oracle interface, it achieves up to 85.7% targeted evasion, retains 43.5% after four rounds of adaptive censor retraining, and maintains 48% under zero-shot cross-environment transfer. Our results show that early-stage classifiers can remain morphable despite high clean accuracy and that robustness evaluation should account for targeted morphability, observation constraints, defender adaptation, and operational network conditions.

cs.NI↗