BLADE-SWARM Governance Node

An Authority Layer for Decentralized Swarms

BLADE-SWARM is the swarm-scale instantiation of the AUTHREX authority-governance architecture. Where the single-node BLADE platforms govern one autonomous system, BLADE-SWARM governs the collective decision: before a swarm commits to a coordinated action, a quorum of agents must agree, and that agreement must pass the same authority checks that govern a single node. The contribution is the protocol that makes this agreement Byzantine-fault-tolerant, authority-bound, and provable after the fact.

Each agent independently computes peer trust (SATA), evaluates the current authority tier (HMAA), and casts a weighted vote (MAIVA). A two-phase commit then requires an intersecting quorum to agree before the action proceeds. The protocol tolerates up to f = (N-1)/3 compromised or faulty agents per quorum, resists Sybil attacks through attested per-node identity, and halts safely by default when the radio-frequency environment is denied or degraded. Every step writes a signed entry into a hash-chained distributed audit ledger that is gossiped across the mesh, so the swarm's decisions remain reconstructable and tamper-evident.

National Importance

Attritable autonomy at scale has moved from concept to acquisition priority. Public programs and challenges in this area, including DAWG-class autonomous operations, the Replicator initiative, and open swarm-autonomy challenges, emphasise large numbers of low-cost autonomous platforms acting in coordination. As these systems scale, the unsolved problem shifts from flying the swarm to governing it: who, or what, is authorized to commit the collective to an action, on what evidence, and how is that decision proven afterward, especially when communications are contested and some agents may be compromised.

BLADE-SWARM is a fundamental-research contribution toward that authority-governance problem. It treats the swarm as a distributed decision-maker whose commits must be both Byzantine-fault-tolerant and authority-gated, and whose actions must leave a tamper-evident record. The architecture governs decision authority and audit; it does not govern weapons and makes no empirical claims about specific systems, operations, or named officials.

Byzantine-Tolerant, Authority-Gated Commit

Each agent runs a two-phase consensus protocol gated by three of the seven AUTHREX architectures. The protocol is designed so that no single compromised agent, and no minority faction up to the Byzantine bound, can cause the swarm to commit to an unauthorized action or to escalate its authority tier without an intersecting quorum.

One Protocol, Three Scales

The same protocol and simulator are parameterised over three operating scales. The physical testbed validates the N=10 baseline; the simulator extends the analysis to combined-operation and DAWG-class scales.

Seven-Stage AUTHREX Pipeline, Swarm Instantiation

BLADE-SWARM instantiates the AUTHREX governance pipeline at swarm scale. The pipeline runs once per proposed coordinated action; the consensus and authority stages require an intersecting quorum before the action is allowed to commit.

1. SENSE, each agent gathers local state and peer telemetry over the mesh.
2. SATA, per-peer trust scoring from attested identity and audit-chain integrity.
3. ADARA + IFF, adversarial and identity checks; Sybil and spoofed-peer detection.
4. HMAA, authority-tier evaluation; escalation requires quorum, downgrade is unilateral.
5. MAIVA, weighted sub-quorum voting with the quorum-intersection safety bound.
6. FLAME, deliberation window; two-phase commit only on intersecting-quorum agreement.
7. ERAM + CARA, engagement-risk readout; bounded-liveness recovery and signed corrective audit on fault.

TLA+ Specification

The protocol is specified in TLA+ (AUTHREX_SWARM.tla), refining the existing AUTHREX_MAIVA module with sub-quorum decomposition, Byzantine fault bounds, FLAME deliberation-window contraction, tier-downgrade asymmetry, and CARA bounded liveness. The specification was model-checked on a reduced-scale instance.

Model checking on a reduced-scale instance establishes the safety and liveness properties for that instance; it is not a proof for arbitrary N. The full specification, configuration, and verification report are included in the repository and the Zenodo deposit.

Policy and Standards Context

BLADE-SWARM is framed against the public policy and standards instruments that govern autonomous systems and AI risk. These are cited as context that the architecture is designed to support; no empirical claims are made about specific programs or officials.

• DoDD 3000.09, autonomy in weapon systems; BLADE-SWARM governs decision authority and audit, not weapons, and is designed to keep meaningful human authority in the loop through the HMAA tier model.
• FY26 NDAA, provisions on autonomous-systems assurance and audit.
• NIST AI Risk Management Framework, govern, map, measure, and manage functions, reflected in the authority-gating and tamper-evident-audit design.

Per-Node Bill of Materials

The reference node is a Holybro X500 V2 quadrotor with a COTS governance stack. One node is approximately $1,333; the N=10 testbed baseline is approximately $13.3K. The full parts list, electrical and mechanical connection maps, and assembly guide are in the repository.

Electrical Design System Schematic

The node electrical design, power rails, data interfaces, and the governance-bus level shifter that bridges the Pixhawk 6X, the Raspberry Pi 5, and the ATECC608B secure element. The full-resolution schematic is available as a download.

Browser Swarm Simulator

A single-file, deterministic discrete-event simulator runs the full consensus and authority protocol in the browser, parameterised over N = 10, 50, and 500, with five scripted scenarios from nominal operation through denied and degraded conditions. It visualises the live pipeline, the per-node tier state, and the growing distributed audit ledger.

Reproducibility Artifacts

• Working paper (PDF), the BLADE-SWARM Governance Node paper.
• Browser simulator, single-file HTML/CSS/JS, N = 10/50/500.
• TLA+ specification and verification report.
• Electrical schematic (PDF) and parts list (CSV).
• Assembly guide, build guide, and simulation methodology.
• Full repository and Zenodo deposit (DOI 10.5281/zenodo.20351198).

Related Platforms

BLADE-SWARM is the eighth platform in the BLADE family, each instantiating the AUTHREX authority pipeline in a different domain. It develops the swarm-governance direction first set out in the single-agent Authority-Governed UAV Platform (HMAA-UAV) program, carrying the shared SATA-HMAA-CARA governance lineage from one autonomously governed drone to coordinated swarms of N = 10 to N = 500 agents; the two platforms are intended to complement each other, HMAA-UAV as the single-agent foundation and BLADE-SWARM as the multi-agent extension.

Single-agent foundation: Authority-Governed UAV Platform (HMAA-UAV) · Authority-Governed Rover Testbed

Citation

If you reference BLADE-SWARM in scholarly or policy work, please cite as follows.