Translating Natural Language Instructions for Behavioral Robot Navigation with a Multi-Head Attention Mechanism
This work improves generalization for robot navigation systems, but it is incremental as it builds on an existing framework.
The authors tackled the problem of translating natural language instructions into a behavioral language for indoor robot navigation using a multi-head attention mechanism, achieving significant performance gains in unseen environments.
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.