A new dataset and model for learning to understand navigational instructions

TL;DR

This paper introduces a new dataset generator and a state-of-the-art model for grounded language learning in navigation tasks, addressing dataset limitations and improving instruction understanding.

Contribution

It presents SAILx, a synthetic dataset generator, and a new model with enhanced perceptual capabilities for better navigation instruction comprehension.

Findings

The new model outperforms previous models on the SAIL dataset.

SAILx allows controlled experiments on dataset size and balance.

Performance on small datasets is insufficient for evaluating models.

Abstract

In this paper, we present a state-of-the-art model and introduce a new dataset for grounded language learning. Our goal is to develop a model that can learn to follow new instructions given prior instruction-perception-action examples. We based our work on the SAIL dataset which consists of navigational instructions and actions in a maze-like environment. The new model we propose achieves the best results to date on the SAIL dataset by using an improved perceptual component that can represent relative positions of objects. We also analyze the problems with the SAIL dataset regarding its size and balance. We argue that performance on a small, fixed-size dataset is no longer a good measure to differentiate state-of-the-art models. We introduce SAILx, a synthetic dataset generator, and perform experiments where the size and balance of the dataset are controlled.