A Collaborative Reasoning Framework for Anomaly Diagnostics in Underwater Robotics
Markus Buchholz, Ignacio Carlucho, Yvan R. Petillot

TL;DR
This paper presents AURA, a collaborative framework combining AI, digital twins, and human input for real-time anomaly detection and diagnosis in underwater robotics, enhancing safety and adaptability.
Contribution
Introduces AURA, a novel hybrid system integrating LLMs, digital twins, and human-in-the-loop for adaptive anomaly diagnostics in robotics.
Findings
Effective real-time anomaly detection in underwater robots.
Continuous learning through human feedback improves diagnostic accuracy.
Framework establishes a pattern for trustworthy human-robot collaboration.
Abstract
The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, especially when anomalies are unforeseen. We introduce AURA (Autonomous Resilience Agent), a collaborative framework for anomaly and fault diagnostics in robotics. AURA integrates large language models (LLMs), a high-fidelity digital twin (DT), and human-in-the-loop interaction to detect and respond to anomalous behavior in real time. The architecture uses two agents with clear roles: (i) a low-level State Anomaly Characterization Agent that monitors telemetry and converts signals into a structured natural-language problem description, and (ii) a high-level Diagnostic Reasoning Agent that conducts a knowledge-grounded dialogue with an operator to identify root causes, drawing on external sources. Human-validated diagnoses are then converted…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMaritime Navigation and Safety · Underwater Vehicles and Communication Systems · AI-based Problem Solving and Planning
