SAGE: Ergodic Control for Autonomous and Adaptive Inspection of Subsea Infrastructure

2026-08-20

AI Summary

为解决海底阀门不同风险需差异化检查的问题，提出SAGE系统，通过自适应控制方法动态调整检查频率，相比固定路线更及时发现泄漏。

Abstract

Subsea Christmas Trees (XTs) are underwater structures that use valves for directing oil flow, needing constant inspection. But not every valve carries the same risk at the same time: a valve with a suspected leak needs to be revisited far more often than one with a clean history, and that risk picture changes during the mission as new leaks are found. To handle this, we present SAGE (Semantic and Adaptive Generative Ergodicity), an ergodic-control architecture that allocates vehicle time in proportion to a live, sensor-derived risk distribution rather than a scripted route. We study a two-XT scenario, with five valves in total, and compare a fixed-loop A* tour against SAGE. Both methods can be tuned to spend similar total time near a high-risk valve, but only ergodic control also checks it more often: in simulation, a dominant-risk valve was revisited every 5.8 s under ergodic control against a fixed 8.1 s for every valve under A*, regardless of risk, so a leak can go unnoticed for barely two-thirds as long. Because the tracked distribution is recomputed rather than planned once, a newly detected leak shifts vehicle behavior on the next control cycle with no explicit re-planning step and no operator in the loop, which a fixed tour cannot do without a discrete re-route. We derive the ergodic control law behind this behavior and report simulation results on the five-valve scenario.

Problem

• Subsea Infrastructure
• Ergodic Control
• Risk Distribution
• Autonomous Inspection
• Adaptive

Innovation

• Ergodic Control
• Autonomous Inspection
• Adaptive Risk Management
• Subsea Infrastructure