Skip to content

Revolutionising Asset Performance Management Through Autonomous Robotics and Integrated Digital Platform Intelligence: First Deployment of an ATEX/IECEX-Rated Quadruped Robot in Kuwait

Nov 2026 · ADIPEC · 0 citations · 4 references

TL;DR

The design and first deployment of an integrated autonomous inspection and asset performance management solution at a Kuwait Oil Company (KOC) facility, delivered through a tripartite collaboration between KOC, SLB and ANYbotics, demonstrated that fusing autonomous robotic inspection data with ERP and DCS sources on a single intelligent platform produces a qualitative shift in asset performance management capability.

Abstract

Reliability engineers in operating facilities are increasingly burdened by the manual aggregation of asset health data from disparate sources — process historians, ERP systems, and periodic inspection records — leaving limited capacity for higher-value analysis and decision-making. This paper presents the design and first deployment of an integrated autonomous inspection and asset performance management solution at a Kuwait Oil Company (KOC) facility, delivered through a tripartite collaboration between KOC, SLB and ANYbotics. The core objective was to demonstrate that continuous, robot-acquired inspection data — fused with existing ERP and DCS data on SLB's platform — could enable AI and physics-based models to autonomously generate asset health and maintenance actions, fundamentally augmenting the role of the reliability engineer. The solution architecture comprises three integrated layers. First, the ANYmal X quadruped robot — certified for Zone 1 and Zone 2 explosive atmospheres — was deployed to conduct autonomous inspection rounds across the KOC facility. The quadruped's terrain mobility across stairs, gratings, elevated structures, and confined walkways enabled coverage of approximately 70–80% of total inspection routes, including persistent monitoring of identified bad actor assets responsible for disproportionate unplanned downtime. The robot's multi-modal payload captures thermal anomalies, acoustic signatures, visual data with AI-based interpretation, and gas leak detection at frequencies unachievable through manual rounds. Due to the applicable explosive-atmosphere standards were written for fixed installations and manned mobile plants rather than for autonomous legged machines, the paper also sets the challenges in the design and realization of an Ex-product for such applications. Second, this continuous stream of inspection data is ingested into SLB's asset performance management platform; OptiSite - alongside existing asset health data — real-time process values from the DCS and equipment history and work orders from the ERP — creating a unified, continuously enriched data foundation for each asset. Third, SLB's AI models and physics-based models operate on this fused dataset to automatically generate prioritised maintenance recommendations, failure risk assessments, and asset health scores. The system was designed to take on a significant portion of the routine analytical workload traditionally performed by KOC's reliability engineers, allowing them to focus on complex exception handling and strategic decision-making. The deployment demonstrated that fusing autonomous robotic inspection data with ERP and DCS sources on a single intelligent platform produces a qualitative shift in asset performance management capability. Coverage of 70–80% of inspection rounds — with targeted monitoring of bad actor assets — provided reliability teams with a continuous, objective view of asset condition that manual inspection cycles cannot sustain. AI and physical model outputs translated this enriched data into actionable maintenance recommendations, measurably reducing the analytical burden on reliability engineers and shortening the time from anomaly detection to intervention. Personnel exposure in hazardous zones was also substantially reduced, improving HSE performance at the KOC facility. This paper presents the first deployment of the ATEX/IECEx-rated quadruped in an Ex-rated operational environment in Kuwait and the first documented implementation of a fully integrated solution combining quadruped robotic inspection — thermal, acoustic, visual interpretation, and gas detection — with ERP, DCS and AI-driven asset performance models on a single platform. The novelty lies not in any individual component, but in the end-to-end architecture: robot-acquired field data continuously enriching a digital asset health foundation, with AI and physical models closing the loop from data to action. This model represents a scalable blueprint for augmenting reliability engineering workflows across GCC operating facilities. The paper closes with a discussion of the deployment's limitations, challenges, and future work as the programme moves into its Expand and Commit phases.

View source

Similar papers

Open access Oct 2026

AI-Powered Robotics for Reliable, Stable, and Robust Operation and Maintenance of Power Systems: Architecture, Unified Modeling, and Quantitative Evaluation

Robotic inspection and artificial intelligence (AI) are increasingly used in power-system operation and maintenance (O&M), yet they are usually evaluated in isolation—by image-detection accuracy or robot mobility—rather than by their effect on the quantities utilities are regulated on. This paper proposes AIRO-PS, a st...

Mohammad Ali · 0 citations
Open access Sep 2026

From Single Platforms Towards Coordinated Fleets: Safety- and Security-Bounded Autonomous Multi-Robot Systems for Nuclear Decommissioning in Europe

Europe’s ageing nuclear fleet creates a growing need for repeated radiological characterisation of contaminated, GPS-denied facilities where human access must be kept to a minimum. However, most deployed robotic systems remain limited to a single platform with a narrow task range. Methods: Building on two earlier confe...

Abdenour BENKRID, Omar Zahra, Ankur Shukla et al. · 0 citations

First Global Deployment of a Closed-Loop AI Drilling Optimizer Integrated with Rig Control Systems

The rapid advancement of drilling automation is accelerating the industry's transition toward autonomous drilling systems capable of continuously optimizing performance with minimal operator intervention. AI-based drilling optimization has already demonstrated measurable improvements in drilling efficiency through cl...

A. O. Akinlosotu, R. Al-Rahma, M. Taha et al. · 0 citations
Review Open access Sep 2026

Autonomous Robot Networks for Infrastructure Inspection: A Literature-informed Conceptual Framework for Predictive Monitoring, Asset-specific Adaptation, and Safety Assurance

Aging infrastructure systems, including bridges, roads, tunnels, pipelines, substations, and utility corridors, present growing inspection and maintenance challenges for public agencies and asset owners, particularly under conditions of deferred maintenance, aging assets, and constrained renewal budgets (American Socie...

Kiran Kumar Banisetti, Padma Banisetti, Raghavendra Maganti · 0 citations
Open access 2026

AI4U: Metadata-Driven Modular Design for Cyber-Physical Autonomous Systems

The paper clarifies the current scope of AI4U and introduces a conceptual perception-chain reconfiguration example to show how future module replacement can be represented as a localized and checkable operation.

Kamil Wołoszyn, Krzysztof Turchan, Krzysztof Piotrowski et al. · 0 citations
#large language models Conference Oct 2026

Towards Future-Fit Asset Management: AI-Enabled Optimization of Event-Based Maintenance Strategies for High-Reliability Drilling Operations

Achieving cost-efficient and high-reliability operations is increasingly critical as the energy industry advances toward greater digitalization and sustainability. Drilling services fleets alone account for substantial annual maintenance expenditures, highlighting the need for data-driven approaches that improve asse...

Junko Hutahaean, S. Postovalov, M. Tergeist · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.