Grounding from an AI and Cognitive Science Lens
This work addresses the grounding problem for collaborative agents, but it is incremental as it reviews and compares existing approaches without presenting new empirical results.
The paper tackles the problem of grounding by exploring it from cognitive science and machine learning perspectives, identifying its subtleties and significance for collaborative agents, and examining neuro-symbolic approaches as a potential solution.
Grounding is a challenging problem, requiring a formal definition and different levels of abstraction. This article explores grounding from both cognitive science and machine learning perspectives. It identifies the subtleties of grounding, its significance for collaborative agents, and similarities and differences in grounding approaches in both communities. The article examines the potential of neuro-symbolic approaches tailored for grounding tasks, showcasing how they can more comprehensively address grounding. Finally, we discuss areas for further exploration and development in grounding.