{
  "abstract": "Spacecraft increasingly face faults that onboard rule-based systems were never designed to handle, yet flight operators cannot give a probabilistic AI agent direct control of a vehicle. This paper presents AEGIS-Sat, a framework that places a deterministic policy gate between an AI agent and the spacecraft. The agent observes a fault and proposes a single structured recovery action; it can execute nothing itself. A policy gate, written as human-readable YAML, rules on every proposal — AUTO (execute now), AUTO+LOG (execute and flag for ground review), ESCALATE (hold safe and request ground approval), or DENY (blocked) — after checking hard safety invariants and a context-adaptive autonomy envelope that tightens the tiers during communications blackout and eclipse and widens them as power margin recovers. Every proposal, ruling, and state snapshot is recorded in a hash-chained, tamper-evident audit ledger. In a fault-injection evaluation (6 scenarios × 3 setups × 100 episodes = 1,800 episodes), an unguarded agent recovered from 88% of episodes but executed 75 unsafe actions. The guarded agent executed zero unsafe actions, recovered in 100% of episodes (67% full recovery, 33% safe-state recovery), and lost no spacecraft, at the cost of 659 ground escalations. A rule-only FDIR baseline was equally safe but fully recovered from only 33% of episodes. The gate and benchmark are anchored on real telemetry: a deliberately simple logistic detector over ESA's OPS-SAT-AD dataset reaches AUC 0.887, detecting 58% of anomalous segments at a 2.2% false-alarm rate. Gating an untrusted controller is not new — the approach is Simplex-inspired runtime assurance translated to agent-based fault response. The contribution claimed here is the combination: readable policy tiers, a context-adaptive envelope, an open unsafe-action benchmark, and a tamper-evident audit trail, evaluated head-to-head on injected faults.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "name": "Karmendra Pandey",
      "orcid": "0009-0000-3461-9889"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/78201qmef707t.bib",
  "cited_by": 0,
  "doi": "10.5281/zenodo.23425891",
  "fulltext_url": null,
  "id": "78201qmef707t",
  "issns": [],
  "landing_url": "https://zenodo.org/records/23425891",
  "language": "eng",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [],
  "openalex": null,
  "pdf_url": "https://zenodo.org/api/records/23425891/files/aegis-sat-whitepaper-v1.pdf/content",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-16",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/78201qmef707t.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:27Z",
      "native_id": "23425891",
      "source": "zenodo",
      "url": "https://zenodo.org/records/23425891"
    }
  ],
  "subjects": [],
  "title": "Guarded Autonomy for Satellites: A Policy-Gated AI Agent Framework for Safe Onboard Fault Response",
  "title_text": "Guarded Autonomy for Satellites: A Policy-Gated AI Agent Framework for Safe Onboard Fault Response",
  "type": "preprint",
  "updated_at": "2026-10-30T12:33:26Z",
  "url": "https://research.draconitic.com/paper/78201qmef707t",
  "venue": "Zenodo",
  "versions": []
}