Underwater Robotics Semantic Parser Assistant

TL;DR

This paper presents a sequence-to-sequence semantic parser that converts natural language commands into lambda calculus and XML formats, facilitating better understanding in underwater robotics applications.

Contribution

It introduces a novel sequence-to-sequence model for semantic parsing in underwater robotics, enabling nontechnical users to interact effectively with robotic systems.

Findings

High accuracy in converting natural language to lambda calculus

Effective bridging of technical and nontechnical user communication

Potential for improved human-robot interaction

Abstract

Semantic parsing is a means of taking natural language and putting it in a form that a computer can understand. There has been a multitude of approaches that take natural language utterances and form them into lambda calculus expressions -- mathematical functions to describe logic. Here, we experiment with a sequence to sequence model to take natural language utterances, convert those to lambda calculus expressions, when can then be parsed, and place them in an XML format that can be used by a finite state machine. Experimental results show that we can have a high accuracy model such that we can bridge the gap between technical and nontechnical individuals in the robotics field.