CogTwin: A framework for adaptable digital twins

Summary

CogTwin, presented at IJCAI 2025, is a hybrid cognitive architecture framework designed to bring autonomous reasoning and real-time adaptation to digital twins. It addresses the gap in current digital twins that are largely reactive, relying on pre-programmed rules and static models, and thus struggle with unforeseen events. By integrating symbolic AI, sub-symbolic AI, and neuro-symbolic AI, CogTwin aims to equip digital twins with human-like cognitive abilities, enabling them to perceive, reason, learn, and act autonomously in dynamic environments. The architecture features dual knowledge graphs—a static domain knowledge repository (DKR) and a dynamic internal knowledge graph (DIKG)—to balance stability and adaptability, along with a hybrid attention mechanism for focusing on relevant data. This approach shifts the emphasis from simulation and monitoring to genuine intelligence and adaptability, aiming for true cognition in digital twins.