MBZUAI researchers are developing LAIKA, an autonomous quadruped robot for hazardous industrial environments, integrating vision-language AI models with 360-degree imaging. LAIKA can operate in operator-assist mode via natural language or autonomously to inspect, detect anomalies like leaks, and generate structured reports. The robot is designed for versatile tasks in industrial inspection, emergency response, and facility monitoring, with future versions integrating multi-robot collaboration. Why it matters: This technology demonstrates AI's potential to enhance industrial safety, reduce risks to human workers, and improve response times in critical situations within the region's vital energy and manufacturing sectors.
Saudi startup Firnas Aero, founded in 2018, offers drone-based inspection services targeting aviation, security, industrial, and delivery sectors. The company develops its own drones and AI-equipped software for faster and more accurate inspections than manual methods. Their solution involves drones capturing high-resolution images analyzed by AI to pinpoint issues, enhancing speed and accuracy. Why it matters: This showcases Saudi Arabia's growing entrepreneurial interest in drone technology and AI-powered solutions for industrial applications, potentially improving efficiency and safety across sectors.
This paper presents a 2-D convolutional neural network (CNN) approach for damage detection in steel frame structures, using raw acceleration signals as input. The method employs a network of lightweight CNNs, each optimized for a specific element, to enhance accuracy and speed. The proposed framework is validated using the Qatar University Grandstand Simulator (QUGS) benchmark data. Why it matters: The research offers a promising AI-driven solution for real-time structural health monitoring, with potential applications for infrastructure maintenance and safety in the GCC region.
This paper introduces BRIQA, a new method for automated assessment of artifact severity in pediatric brain MRI, which is important for diagnostic accuracy. BRIQA uses gradient-based loss reweighting and a rotating batching scheme to handle class imbalance in artifact severity levels. Experiments show BRIQA improves average macro F1 score from 0.659 to 0.706, especially for Noise, Zipper, Positioning and Contrast artifacts.
A team of KAUST graduates at the Saudi Aramco Intelligent Systems Team designed and built a robotic crawler for visual and ultrasonic inspection of Aramco’s steel assets. The crawler, developed from 2012-2014, can wirelessly inspect curved surfaces for corrosion in hard-to-reach locations. The team won the Industry Glory Medal from the International Federation of Inventors Association in 2013 for this industry-first achievement. Why it matters: This highlights KAUST's role in producing talent that contributes directly to Saudi Aramco's technological advancements in critical infrastructure inspection.
Michael Hickner, an Associate Professor from Penn State University, visited KAUST as part of the CRDF-KAUST-OSR Visiting Scholar Fellowship Program. Hickner specializes in Materials Science and Engineering, Chemistry, and Chemical Engineering. The visit was documented with photos by Meres J. Weche. Why it matters: Such programs foster international collaboration and knowledge exchange in science and engineering between KAUST and other leading institutions.
This article discusses the increasing concerns about the interpretability of large deep learning models. It highlights a talk by Danish Pruthi, an Assistant Professor at the Indian Institute of Science (IISc), Bangalore, who presented a framework to quantify the value of explanations and the need for holistic model evaluation. Pruthi's talk touched on geographically representative artifacts from text-to-image models and how well conversational LLMs challenge false assumptions. Why it matters: Addressing interpretability and evaluation is crucial for building trustworthy and reliable AI systems, particularly in sensitive applications within the Middle East and globally.