Strong-AI Autoepistemic Robots Build on Intensional First Order Logic

TL;DR

This paper proposes a neuro-symbolic AI framework using intensional First Order Logic (IFOL) for robots to communicate, reason, and learn about their knowledge and self-awareness through multi-level language grounding.

Contribution

It introduces a novel multi-level knowledge structure for robots grounded in IFOL, integrating natural language, semantic logic, and neuro-symbolic concepts for advanced reasoning.

Findings

Grounded robot language through neuro-symbolic experience

Implementation of modal logic operators in IFOL for reasoning

Example of robot autoepistemic deduction with temporal predicates

Abstract

Neuro-symbolic AI attempts to integrate neural and symbolic architectures in a manner that addresses strengths and weaknesses of each, in a complementary fashion, in order to support robust strong AI capable of reasoning, learning, and cognitive modeling. In this paper we consider the intensional First Order Logic (IFOL) as a symbolic architecture of modern robots, able to use natural languages to communicate with humans and to reason about their own knowledge with self-reference and abstraction language property. We intend to obtain the grounding of robot's language by experience of how it uses its neuronal architectures and hence by associating this experience with the mining (sense) of non-defined language concepts (particulars/individuals and universals) in PRP (Properties/Relations/Propositions) theory of IFOL.\\ We consider the robot's four-levels knowledge structure: The syntax level of particular natural language (Italian, French, etc..), two universal language levels: its semantic logic structure (based on virtual predicates of FOL and logic connectives), and its corresponding conceptual PRP structure level which universally represents the composite mining of FOL formulae grounded on the last robot's neuro-system level. Finally, we provide the general method how to implement in IFOL (by using the abstracted terms) different kinds of modal logic operators and their deductive axioms: we present a particular example of robots autoepistemic deduction capabilities by introduction of the special temporal $Konow$ predicate and deductive axioms for it: reflexive, positive introspection and distributive axiom.