Mutual Understanding between People and Systems via Neurosymbolic AI and Knowledge Graphs
Irene Celino, Mario Scrocca, Agnese Chiatti
TL;DR
This work proposes a structured framework for mutual understanding between humans and systems by integrating Neuro-symbolic AI with Knowledge Graphs. It defines three core dimensions—sharing, exchanging, and governing knowledge—and analyzes six real-world use-cases (data collection, knowledge extraction, interoperability, reproducibility, spatio-temporal world modeling, and hybrid robot deliberation) to illustrate how symbolic and neural methods complement each other. The contributions include semantic maps, knowledge graphs, retrieval-augmented generation, RO-Crates for reproducibility, and ontological smart contracts, along with a candid discussion of open challenges and future directions. The approach has practical implications for human–machine collaboration, data governance, interoperability across systems, and trustworthy, explainable robot behavior in complex environments.
Abstract
This chapter investigates the concept of mutual understanding between humans and systems, positing that Neuro-symbolic Artificial Intelligence (NeSy AI) methods can significantly enhance this mutual understanding by leveraging explicit symbolic knowledge representations with data-driven learning models. We start by introducing three critical dimensions to characterize mutual understanding: sharing knowledge, exchanging knowledge, and governing knowledge. Sharing knowledge involves aligning the conceptual models of different agents to enable a shared understanding of the domain of interest. Exchanging knowledge relates to ensuring the effective and accurate communication between agents. Governing knowledge concerns establishing rules and processes to regulate the interaction between agents. Then, we present several different use case scenarios that demonstrate the application of NeSy AI and Knowledge Graphs to aid meaningful exchanges between human, artificial, and robotic agents. These scenarios highlight both the potential and the challenges of combining top-down symbolic reasoning with bottom-up neural learning, guiding the discussion of the coverage provided by current solutions along the dimensions of sharing, exchanging, and governing knowledge. Concurrently, this analysis facilitates the identification of gaps and less developed aspects in mutual understanding to address in future research.