Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism

TL;DR

This paper introduces a multi-head attention mechanism in a neural network to improve the translation of natural language instructions into behavioral commands for indoor robot navigation, enhancing generalization to unseen environments.

Contribution

It presents a novel multi-head attention blending layer that significantly improves instruction translation accuracy in unseen environments for robot navigation.

Findings

Enhanced translation accuracy in new environments

Significant performance improvements over previous models

Better generalization capabilities

Abstract

We propose a multi-head attention mechanism as a blending layer in a neural network model that translates natural language to a high level behavioral language for indoor robot navigation. We follow the framework established by (Zang et al., 2018a) that proposes the use of a navigation graph as a knowledge base for the task. Our results show significant performance gains when translating instructions on previously unseen environments, therefore, improving the generalization capabilities of the model.