Formalising Natural Language Quantifiers for Human-Robot Interactions

TL;DR

This paper introduces a formal method for representing natural language quantifiers in human-robot interactions using extended first-order logic, enabling robots to interpret and act on quantified statements.

Contribution

It presents a novel formalisation approach for natural language quantifiers and an end-to-end system for interpreting and executing such commands in robotic contexts.

Findings

Successfully formalised natural language quantifiers for robots

Developed an end-to-end system for language understanding and execution

Demonstrated effective interpretation of quantified commands in simulation

Abstract

We present a method for formalising quantifiers in natural language in the context of human-robot interactions. The solution is based on first-order logic extended with capabilities to represent the cardinality of variables, operating similarly to generalised quantifiers. To demonstrate the method, we designed an end-to-end system able to receive input as natural language, convert it into a formal logical representation, evaluate it, and return a result or send a command to a simulated robot.