English

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

Machine Learning 2020-06-09 v3 Computation and Language Robotics Machine Learning

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.

Keywords

Cite

@article{arxiv.2006.00697,
  title  = {Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism},
  author = {Patricio Cerda-Mardini and Vladimir Araujo and Alvaro Soto},
  journal= {arXiv preprint arXiv:2006.00697},
  year   = {2020}
}

Comments

Accepted at ACL 2020 WiNLP workshop

R2 v1 2026-06-23T15:57:03.281Z