2000 character limit reached
Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism (2006.00697v3)
Published 1 Jun 2020 in cs.LG, cs.CL, cs.RO, and stat.ML
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.