Authority-Governed Assured Autonomy Rover Testbed

National Importance of Authority-Governed Autonomy

Autonomous systems increasingly operate in environments where sensor deception, communication disruption, and adversarial interference threaten mission safety. Current autonomy architectures typically rely on binary fail-safe triggers or simple threshold-based switching, lacking 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. The DoD Directive 3000.09 explicitly requires autonomous weapons systems to maintain 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:

The testbed provides a practical evaluation environment for the SATA, HMAA, and CARA architectures described in the associated patent disclosures and technical reports published on Zenodo. 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 implements a complete authority-governed autonomy pipeline. Every autonomous decision must pass through trust evaluation, authority computation, and recovery logic before reaching actuators.

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.

This extension demonstrates 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 applicability to a broad class of autonomous systems operating under uncertainty.

Sensor Trust Testing Platform

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

This platform supports experimental research on resilient perception systems and provides a controlled environment for validating trust evaluation algorithms under adversarial conditions.

Together with the rover testbed and robotic manipulation extension, this platform demonstrates 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).

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 demonstrates executable validation of authority-governed autonomy rather than conceptual design alone. The simulation environment mirrors the physical rover hardware architecture, enabling direct transfer of validated governance behaviors from simulation to hardware testing.

Experimental Simulation Environment (Research Use). This environment serves as a primary validation layer for testing authority transitions and recovery behaviors, enabling repeatable experimentation prior to physical hardware deployment.

Authority State Machine

The testbed implements 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.

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.

Key Components

Validation Metrics

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

The platform design and specification are complete. Hardware procurement and implementation are currently underway. The architecture, authority model, trust evaluation method, and experimental methodology are fully defined and documented.

Project Documentation

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

Reproducible Research Artifacts

This project provides reproducible artifacts enabling researchers to replicate the autonomy governance experiments and system architecture. All documentation, schematics, and specifications are available for download.

Power Architecture

The rover testbed operates from a 7.4V 2S LiPo battery with 5V and 3.3V regulated rails for compute and sensor modules.

Trust & Verification Chain

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

Bill of Materials: ~$484

Lowest-cost governance testbed demonstrating the complete SATA-HMAA-CARA pipeline at ~$484. All COTS components.

Physical Specifications

Future Work

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

About This Project

This project is part of ongoing research on authority-governed autonomy and resilient AI systems conducted by Burak Oktenli at Georgetown University (M.P.S. Applied Intelligence). The testbed implements the same governance architectures published in the SATA, HMAA, and CARA patent disclosures and technical reports on Zenodo. Current work focuses on the rover testbed as an early physical platform, 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 →