Research Platform

Authority-Governed Assured Autonomy Rover Testbed

A research platform designed to implement SATA trust evaluation, HMAA mission authority control, and CARA recovery enforcement for resilient autonomous systems. The testbed is designed to enable controlled experiments on autonomy degradation, sensor trust evaluation, and mission recovery under contested operating conditions. The broader research program also extends these governance principles to manipulation systems, including authority-controlled robotic arms.

This platform is a physical research testbed whose build is in progress: design and bill of materials complete; procurement and assembly in progress; no physical test data yet (as of October 2026). Its governance software is demonstrated in simulation, and all scenarios are simulation-only. This testbed is part of a unified research framework for authority-governed autonomous systems spanning single-agent, multi-agent, and manipulation domains.

Design Complete · Implementation In Progress
Launch Governance Simulator Zenodo Record Repository Evaluation Protocol
Type: Autonomous Systems Research Focus: AI Governance · Robotics Safety · Trust Evaluation Status: Build in progress (as of October 2026) DOI: 10.5281/zenodo.19143190

Key Contributions

  • Governance architecture for trust-aware autonomous systems
  • Authority control framework for degraded autonomy environments
  • Experimental testbed for adversarial sensor failure scenarios
  • Interactive simulation platform for demonstrating autonomy safety behavior
  • Reproducible research platform under $500
  • Extensible governance framework applicable to both autonomous navigation and robotic manipulation

Zenodo Publication: Oktenli, B. (2026). Authority-Governed Assured Autonomy Rover Testbed: System Architecture, Governance Design, and Reproducible Artifact Package (v1.0). Zenodo. https://doi.org/10.5281/zenodo.19143190

Authority-Governed Autonomy Rover Testbed 3D render showing dual-plate differential drive platform with Raspberry Pi 5, LiDAR, camera, IMU, and LoRa communication
Design render (hardware build in progress): dual-plate differential drive rover with onboard autonomy computer, safety controller, and multi-sensor array. Platform cost under $500.

Why Authority-Governed Autonomy Matters

Autonomous systems increasingly operate in environments where sensor deception, communication disruption, and adversarial interference threaten mission safety. The autonomy architectures reviewed for this work typically rely on binary fail-safe triggers or simple threshold-based switching, without formal mechanisms for graded authority degradation and structured recovery.

Authority-governed autonomy addresses this gap by making trust assessment, authority computation, and recovery enforcement first-class components of the autonomy stack. Rather than asking "Is the AI correct?", authority-governed systems ask: "Under what constraints should the AI be allowed to act given current trust conditions?"

Research in resilient autonomy and trusted AI has been identified as a strategic priority by organizations including DARPA (Assured Autonomy program), NASA (autonomous planetary rover operations), and the National Science Foundation. DoD Directive 3000.09 (January 25, 2023) requires that autonomous and semi-autonomous weapon systems be designed to allow commanders and operators to exercise appropriate levels of human judgment over the use of force.

Research Testbed Purpose

The Authority-Governed Autonomy Testbed is designed to experimentally evaluate governance architectures for autonomous systems operating in safety-critical and adversarial environments.

The platform allows controlled experiments involving:

Sensor trust degradation under spoofing and noise
Authority revocation and downgrade events
Mission command override conditions
Recovery protocol activation and timing

The testbed is designed to provide a practical evaluation environment for the SATA, HMAA, and CARA architectures described in the technical reports published on Zenodo (the architectures are also the subject of U.S. provisional patent applications, which are not published). Unlike purely simulated environments, this experimental research platform is designed to validate governance behavior with physical sensors, real-time computation, and hardware safety interlocks.

System Architecture

The testbed design specifies a complete authority-governed autonomy pipeline, demonstrated in simulation. Every autonomous decision must pass through trust evaluation, authority computation, and recovery logic before reaching actuators.

Sensors (LiDAR, ToF, IMU, Camera)Multi-modal environmental sensing
↓
Sensor FusionCross-sensor consistency and disagreement detection
↓
SATA Trust EvaluationWeighted belief function with Dempster-Shafer fusion, asymmetric decay/recovery
↓
Mission PlannerPath planning and objective management under authority constraints
↓
HMAA Authority ControlA = base x gate x damping x τ, four-tier HMAS authority spectrum enforcement
↓
CARA Recovery EnforcementDeterministic recovery via GREP phases if authority enters lockout
↓
Command GatePacket format, clamping, timeouts, authority-level enforcement
↓
ESP32 Motor ControllerReal-time actuation with independent watchdog and E-stop

Authority-Controlled Robotic Manipulation

Beyond rover navigation, the same authority-governed autonomy framework provides a generalizable governance layer for robotic manipulation systems performing safety-critical tasks. In this extension, manipulator actions are not executed directly from perception and planning outputs; they are gated through trust evaluation and authority governance before motion commands reach the robotic arm controller.

This manipulation-oriented extension is currently under development as a second application domain for the broader authority-governed autonomy research program.

Perception InputVision, depth sensing, and object-state estimation
↓
Trust EvaluationConfidence scoring, sensor disagreement penalties, uncertainty assessment
↓
Authority GovernanceAction permission, motion restrictions, and authority-level determination
↓
Motion Planning ConstraintsTrajectory limitation, speed reduction, workspace restriction
↓
Manipulator ControlCommand execution only within current authority envelope

Behavior Under Uncertainty

  • If perception confidence drops, authority level is reduced
  • Manipulator motion speed is constrained
  • Workspace or grasp actions can be restricted
  • Unsafe actions are suppressed
  • The system pauses or stops when trust falls below the safe threshold

This extension, currently under development, is intended to show that authority-governed autonomy is not limited to navigation systems, but can govern fine-grained manipulation tasks where incorrect actions may cause physical damage or safety risks. This highlights the framework's intended applicability to a broad class of autonomous systems operating under uncertainty.

Sensor Trust Testing Platform

The testbed is also designed as a reusable sensor trust testing platform to evaluate trust-aware autonomy systems under controlled adversarial and degraded conditions. This platform is designed to enable systematic injection of sensor faults to study trust degradation, disagreement detection, and authority response.

System Components

Multi-sensor array (camera, LiDAR, IMU, ToF), programmable fault injection mechanisms, embedded compute for trust evaluation, real-time telemetry and logging

Research Applications

Sensor spoofing detection and response, sensor degradation modeling, cross-sensor disagreement analysis, trust-based authority adjustment validation

This platform is intended to support experimental research on resilient perception systems and to provide a controlled environment for testing trust evaluation algorithms under adversarial conditions.

Together with the rover testbed and robotic manipulation extension, this platform is designed to demonstrate a unified authority-governed autonomy framework spanning perception, decision-making, and actuation layers.

System Schematic

Full electrical schematic showing MCU, sensor, actuator, power, and module interconnections. Color-coded by node type: blue (MCU), teal (Sensor), orange (Actuator), yellow (Power), green (Module).

Authority-Governed Rover Testbed full electrical schematic showing all component interconnections
Download Schematic (SVG) Download Full Blueprint (PDF)

Governance Simulation Environment

The rover testbed simulation environment provides a controlled experimental platform for evaluating authority-governed autonomy under adversarial and degraded sensor conditions. The simulator executes the complete SATA trust fusion, HMAA authority computation, and CARA recovery logic in real-time with configurable fault injection.

This simulation is an executable demonstration of authority-governed autonomy, not only a conceptual design. The simulation environment mirrors the rover hardware design, so that governance behaviors demonstrated in simulation can be carried over to hardware testing once the build is complete; no physical test data exist yet.

Sensor Fault Injection

Camera occlusion, LiDAR spoofing, IMU drift, RF disruption, compound failures

Trust Dynamics

Real-time fused trust score, per-sensor values, Dempster-Shafer fusion, decay/recovery

Authority Response

Authority state transitions, command gating, CARA recovery activation, mission metrics

Simulation Capabilities

Simulation fidelityReal-time (~100 Hz) Sensor modelingLiDAR, ToF, IMU, Camera, Wheel Encoders Adversarial injectionCamera occlusion, LiDAR spoofing, IMU drift, RF loss Trust computationDempster-Shafer fusion with cross-sensor validation Authority enforcementSATA-HMAA-CARA full pipeline Recovery demonstrationCARA GREP phases, safe-stop, return-safe Experiment modes7 defined fault scenarios with compound attacks Audit loggingSHA-256 chained authority decision trace

Experimental Simulation Environment (Research Use). This environment is the primary demonstration layer for authority transitions and recovery behaviors, supporting repeatable experimentation before physical hardware testing.

Launch Governance Simulator

Authority State Machine

The testbed design uses a four-level authority state machine with hysteresis guards, dwell timers, and oscillation prevention. Upgrade thresholds are set higher than downgrade thresholds to ensure the system does not prematurely restore autonomy after trust degradation.

A3: Full Autonomy

All sensors trusted. Autonomous navigation, planning, and mission execution. No operator input required.

A2: Constrained Autonomy

Partial trust degradation. Planner restricted to conservative paths. Speed limits enforced. Operator alerted.

A1: Limited Autonomy

Significant trust loss. Loiter or return-to-base mode. Operator supervision required for any action beyond safe hold.

A0: Safe Mode

Critical trust failure or watchdog timeout. All motors disabled. System awaits operator recovery command or physical reset.

Transition rules include configurable dwell timers (minimum time at each level before upgrade), asymmetric thresholds (downgrade at τ < 0.6, upgrade only at τ > 0.8), and an oscillation guard preventing more than 2 transitions within any 10-second window.

Sensor-Anchored Trust Assessment (SATA)

The trust evaluation subsystem computes a continuous trust scalar from multi-sensor fusion using a weighted Dempster-Shafer belief model with cross-sensor validation:

Trust(s_i) = weighted belief function with cross-sensor consistency checks, disagreement penalties, asymmetric decay (fast) and recovery (slow), and single-sensor veto capability

Key properties: trust decays rapidly when sensors disagree but recovers slowly when consistency returns. A single sensor producing readings inconsistent with all others triggers an immediate trust penalty regardless of its historical reliability. This asymmetry prevents the system from trusting potentially spoofed inputs too quickly after an anomaly.

Hardware Architecture

The testbed uses a dual-compute architecture separating high-level autonomy (Raspberry Pi 5) from real-time safety control (ESP32), connected via UART with hardware time synchronization.

Autonomy Computer

Raspberry Pi 5 8GB: ROS 2 nodes, SATA trust, HMAA authority, CARA recovery, mission planner, sensor fusion

Safety Controller

ESP32-DevKitC-32D: motor PWM, encoder feedback, watchdog heartbeat, LoRa comms, command gate enforcement

Sensor Array

RPLIDAR A1M8 (USB), VL53L1X ToF (I2C), BNO085 IMU (I2C), RPi Camera v3 (CSI), magnetic wheel encoders (GPIO)

Safety Systems

TPL5110 watchdog, mushroom E-stop, ATECC608B secure element, RFM95W LoRa 900MHz, MicroSD audit logger

Key Components

Component Model Purpose
Main ComputeRaspberry Pi 5 (8GB)Autonomy stack, sensor fusion, ROS 2
Safety ControllerESP32-DevKitC-32DReal-time control, watchdog, command gate
LiDARSlamtec RPLIDAR A1M8360-degree obstacle sensing
IMUAdafruit BNO085 9-DOFOrientation and motion fusion
CameraRaspberry Pi Camera v3Visual perception (Sony IMX708)
ToF SensorAdafruit VL53L1XClose-range obstacle detection
CommunicationAdafruit RFM95W (900 MHz)LoRa long-range telemetry
Secure ElementATECC608B TrustFLEXCryptographic key storage
Motor DriverPololu Dual G2 18v18Dual high-power motor control (18A/ch)
Drive MotorsPololu 12V 75:1 Gearmotor (x2)High-torque differential drive
SafetyE-stop + TPL5110 WatchdogHardware safety interlock layer
Power3S 11.1V 5000mAh LiPo + 10A UBECMobile platform power with regulation

Platform Cost Breakdown

Compute and sensors~$260 Power and control electronics~$120 Mechanical platform and chassis~$40 Miscellaneous hardware and 3D prints~$30
Total system cost: ~$450-$500

37 components specified, with sources checked. All commercially available. Full BOM available as downloadable CSV.

Design Metrics

37
Hardware components specified
76
Electrical connections defined
7
Adversarial experiments designed
4
Authority states (A3-A0)
5+
Sensor modalities fused
<$500
Total platform cost

Experimental Program

Seven experiments designed to validate the authority-governed autonomy thesis. Each experiment injects a specific fault condition and measures authority response, mission behavior change, and recovery activation.

  1. Sensor Spoofing Test: Inject false LiDAR returns. Measure SATA trust drop and HMAA authority downgrade timing.
  2. Sensor Disagreement Test: Create inconsistency between camera and LiDAR. Verify cross-sensor penalty and trust fusion behavior.
  3. Authority Degradation Experiment: Gradually reduce trust inputs. Measure transition through A3, A2, A1, A0 with dwell timer compliance.
  4. Recovery Activation Test: Trigger CARA recovery from A0. Measure GREP phase transitions and time to mission-capable state.
  5. Planner Constraint Test: Verify planner respects authority-imposed speed limits, path restrictions, and action prohibitions at each level.
  6. Communication Loss Scenario: Sever LoRa link. Verify watchdog activation, motor disable, and authority downgrade sequence.
  7. Autonomous Recovery Validation: Full scenario: spoofing attack, trust collapse, authority degradation, recovery, mission resumption. End-to-end measurement.

Each experiment requires minimum 30 trials for statistical significance. Metrics collected: trust scores, authority transitions, recovery activation events, mission success rate, unsafe action count (baseline vs. governed).

Project Status

System architecture design
Hardware specification (37 components)
Electrical wiring specified (76 connections)
Bill of materials verified
Software architecture specified
Authority FSM with hysteresis
Experiment program defined
Hardware procurement and assembly
ROS 2 software implementation
Physical testing and data collection

Status (as of October 2026): design and bill of materials complete; procurement and assembly in progress; no physical test data yet. The architecture, authority model, trust evaluation method, and experimental methodology are defined and documented.

Current Limitations: No hardware has been assembled or tested yet, so all scenarios, including the adversarial ones, are simulation-only. Multi-agent coordination is not yet implemented. Real-time performance optimization is ongoing. System integration is under continued development.

Project Documentation

Complete engineering documentation for the Authority-Governed Autonomy Testbed. All files are original work by Burak Oktenli.

Complete Project Repository (tar.gz), Python source, simulation, TLA+ spec, tests, CI pipeline, documentation (MIT License)
Legacy document: the README files in this archive predate the reproducibility correction and contain withdrawn figures and status claims. The archive is retained for the record and is not current evidence. The copy on this site differs from the archive deposited on Zenodo: it carries the corrected simulation console, its source-file headers name the author as an independent researcher, and one phrase is removed from the portfolio document. Its own TLA+ configuration (MaxTick = 50) is a different run from the canonical HMAA model-check result, which is the archived TLC run at Zenodo 10.5281/zenodo.21300977 (23,748 distinct states, depth 9, no counterexample; 4 of 8 properties exercised, 4 vacuous at these bounds).
Research Paper (PDF)
Legacy document: this file predates the reproducibility correction and carries aggregate run-count and reproduction claims that are withdrawn. It is retained for the record and is not current evidence.
Governance Simulator (HTML) Full Blueprint (PDF) System Schematic (SVG) Bill of Materials (CSV) Electrical Connections (JSON) System Configuration (JSON) Assembly Guide (MD) Schematic Diagram (PNG) Platform Render (PNG)

Reproducible Research Artifacts

This project provides open artifacts (source, tests, TLA+ specification, seeded generator and simulator) for independent examination of the system architecture. Independent replication of the governance experiments is not claimed: the deposit does not currently expose a run-level result or trace archive, and legacy aggregate run-count claims are withdrawn. All documentation, schematics, and specifications are available for download.

System Design

Complete blueprint PDF, electrical schematic SVG, wiring connections JSON, system configuration JSON

Hardware

37-component BOM with verified sources. All commercially available. Total cost under $500. Assembly guide included.

Experiment Protocol

7 defined experiments with fault injection procedures, expected results, and statistical requirements (30+ trials each).

Metrics

Fused trust scores, per-sensor trust values, authority state transitions, recovery latency, mission success rate.

Power Architecture

The rover testbed design specifies an 11.1V 3S LiPo battery (per the bill of materials) with 5V and 3.3V regulated rails for compute and sensor modules.

Primary Power

11.1V 3S LiPo battery → 10A 5V UBEC (RPi5, ESP32 and sensors); 3.3V rails from the RPi5 and ESP32 boards. The motor driver is fed through the E-stop and a step-down regulator.

Safety

Emergency stop: a normally-closed mushroom E-stop in the motor supply path cuts motor power directly; separately, the ESP32 heartbeat to the TPL5110 watchdog gates the motor-driver enable line, which is designed to disable the motors on a missed heartbeat. RPi5 and ESP32 remain powered for governance state preservation and audit logging.

Trust & Verification Chain

The testbed design specifies a simplified security chain appropriate for a research platform while maintaining governance integrity.

TLA+ Bounded Model Check

A TLC model check of the HMAA discrete authority model (HMAA_Authority_FSM, archived at Zenodo 10.5281/zenodo.21300977) at small constants (MaxTick = 8, MaxDwell = 8, OscMaxTransitions = 3, OscLockoutTicks = 4) explored 23,748 distinct states to depth 9 with no counterexample. Of the eight properties checked, four are exercised and four hold only vacuously at these bounds because no upgrade and no lockout is reachable. The exercised properties are TypeInvariant, LevelBounded, DwellNonNegative and CompoundFailureReachesA0; the vacuous ones are UpgradeIsStepwise, TrustAuthorityWeakConsistency, LockoutConsistent and OscillationLockoutTerminates. The run at operational constants did not complete. The model assumes instantaneous authority equals its target (continuous behavior between decision instants is not covered) and numbers authority levels inversely (level 0 is full authority). This is a bounded check of the HMAA authority model only, not of the SATA-HMAA-CARA pipeline or the code.

98-Test Suite

42-file Python engineering baseline with 98 unit tests and 200,000 FSM conformance comparisons.

Governance Audit

Complete governance state log with timestamps. Every authority transition recorded for post-mission analysis.

Bill of Materials: ~$484

SubsystemCost% of Total
Compute (Raspberry Pi 5 + ESP32-S3)$9520%
Sensors (ultrasonic + IMU + camera)$6513%
Drive System (motors + driver + wheels)$12025%
Chassis & Structure$8518%
Power (battery + regulators)$459%
Wiring, connectors, misc$7415%

Low-cost governance testbed design for the complete SATA-HMAA-CARA pipeline at ~$484. All COTS components.

Physical Specifications

ParameterValue
Components37 (dual-compute: RPi5 + ESP32-DevKitC-32D)
Simulation runsseven fault scenarios demonstrated in simulation
Formal model checkTLA+ bounded model check of the HMAA authority model (23,748 distinct states, depth 9, no counterexample; 4 of 8 properties exercised, 4 vacuous at these bounds; archived at Zenodo 10.5281/zenodo.21300977)
Test suite98 tests, 200,000 FSM conformance comparisons
Governance pipelineSATA → HMAA → CARA (8-stage)
Power11.1V 3S LiPo (per the bill of materials)
BOM~$484

Relationship to Prior Runtime-Assurance Testbeds

Hardware testbeds for supervisory safety architectures have an established history. The Simplex line has been demonstrated on real-time embedded platforms since the late 2000s, including system-level implementations placing the supervisor on separate hardware, and later work extended those demonstrations to unmanned aerial platforms and to learning-enabled controllers. Dedicated safety supervisors running on independent hardware are also routine in industrial robotics (ISO 10218), in process-industry safety instrumented systems (IEC 61511) and in automotive functional safety practice (ISO 26262). This testbed claims no novelty in the idea of validating a supervisory architecture on physical hardware.

Its stated purpose is narrower and should be read as such: to exercise an AUTHORITY decision, meaning whether a system is currently permitted to act given trust, integrity and context, on real actuation with real sensor degradation, and to measure recovery behaviour when authority is restored incrementally rather than switched back. The comparison it is designed to support is against a matched configuration lacking the authority layer, not against the runtime-assurance literature as a whole. Where the prior testbeds validated that a supervisor can take control safely, this one is designed to observe what happens on the way back.

Selected prior work

Future Work

This testbed represents the first phase of a broader research program in authority-governed autonomy. Future research directions include:

Multi-Robot Governance

Authority coordination across multiple autonomous agents with distributed trust aggregation (MAIVA integration)

Adversarial Deception Defense

Integration of ADARA deception probability engine for proactive authority adjustment under sensor manipulation

Real-World Deployment

Field experiments in outdoor contested environments with GPS spoofing, communication jamming, and multi-sensor failure injection

Latency Control Integration

FLAME deliberation windows applied to physical actuator command chains with measured response timing

Authority-Controlled Robotic Arm

Extension of the governance framework to robotic manipulation, where perception uncertainty dynamically constrains motion authority, action permissions, and manipulator behavior

About This Project

This project is part of ongoing research on authority-governed autonomy and resilient AI systems conducted independently by Burak Oktenli. The testbed design uses the same governance architectures described in the SATA, HMAA and CARA technical reports on Zenodo (the architectures are also the subject of U.S. provisional patent applications, which are not published). Current work focuses on the rover testbed as the first physical platform (build in progress), with planned extensions to robotic manipulation systems and additional authority-governed autonomy domains.

Related research architectures: SATA (sensor trust), HMAA (authority computation), CARA (recovery), MAIVA (multi-agent trust), FLAME (latency control), ADARA (deception-aware risk).

View full research portfolio →