multi-agent systems
3 articles · search the full text for this term
-
Autonomous Agentic AI for Adaptive Cure Optimization and Defect Prevention in Thermoset Polymer Composite Manufacturing
Abstract: Thermoset polymer composites occupy a central position in modern structural manufacturing, from aircraft fuselages to wind-turbine blades. Despite progress in resin chemistry and fiber architecture, the “cure process” that transforms compliant preforms into load-bearing structures remains difficult to manage. Manufacturers encounter ‘voids’, “interlaminar delaminations”, and “spring-back distortion” when curing complex or thick-section parts. The cause is not ignorance of the relevant physics, but rather that ‘temperature’, ‘chemistry’, ‘rheology’, and ‘mechanics’ …
Published in Journal of Polymer & Composites · Vol. 14, Issue 2, 2026 · pp. 301–320 Read article
-
Autonomous Agent Contracts for Adaptive Supply Chains
Abstract: This paper proposes a novel agent-driven, on-chain coordination layer for manufacturer–distributor–retailer handoffs that automates release, transfer, receipt, and state validation across the supply network. This approach combines belief–desire–intention (BDI) agents with narrowly scoped smart contracts to capture role responsibilities, capacity checks, and escalation policies. It aims to enhance conformance, traceability, and cycle-time reliability without relying on central intermediaries. This proof of concept links supply chain states—such as production-ready, packaged, listed, …
Published in Journal of Artificial Intelligence Research & Advances · Vol. 13, Issue 1, 2025 · pp. 52–60 Read article
-
An Integrated Autonomous Rover-Drone System for Intelligent Exploration and Environmental Monitoring
Abstract: This paper presents a hybrid autonomous exploration platform integrating a ground rover and aerial drone, enhanced by swarm intelligence and a custom-trained YOLO V8 object detection model. The rover is equipped with GPS, IMU, and environmental sensors (DHT11, MQ135, BMP180), while the drone performs real-time aerial mapping and obstacle prediction. A YOLO V8 model, trained on 500 annotated terrain images (six classes: rocks, pits, trees, water, animals, vegetation), achieves a …
Published in International Journal of Mechanical Dynamics and Systems Analysis · Vol. 3, Issue 2, 2025 · pp. 43–61 Read article