Underwater Robotics Semantic Parser Assistant
This addresses the challenge of human-robot interaction in underwater robotics, though it appears incremental by applying existing sequence-to-sequence methods to this specific domain.
The paper tackles the problem of converting natural language instructions into machine-readable logic for underwater robotics by developing a sequence-to-sequence model that translates utterances to lambda calculus expressions and then to XML format, achieving high accuracy to bridge communication gaps between technical and non-technical users.
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.