Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation

Vision-and-Language Navigation (VLN) is a natural language grounding task where an agent learns to follow language instructions and navigate to specified destinations in real-world environments. A key challenge is to recognize and stop at the correct location, especially for complicated outdoor environments. Existing methods treat the STOP action equally as other actions, which results in undesirable behaviors that the agent often fails to stop at the destination even though it might be on the right path. Therefore, we propose Learning to Stop (L2Stop), a simple yet effective policy module that differentiates STOP and other actions. Our approach achieves the new state of the art on a challenging urban VLN dataset Touchdown, outperforming the baseline by 6.89% (absolute improvement) on Success weighted by Edit Distance (SED).

PDF Abstract Findings of 2020 PDF Findings of 2020 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Vision and Language Navigation Touchdown Dataset ARC + L2STOP Task Completion (TC) 16.68 # 3
Vision and Language Navigation Touchdown Dataset ARC Task Completion (TC) 14.13 # 6

Methods


No methods listed for this paper. Add relevant methods here