Learning to Stop: A Simple yet Effective Approach to Urban Vision-Language Navigation
This addresses a specific bottleneck in VLN for urban navigation, offering an incremental improvement over existing methods.
The paper tackles the problem of agents failing to stop at correct destinations in urban Vision-and-Language Navigation by proposing Learning to Stop (L2Stop), a policy module that differentiates STOP from other actions, achieving a 6.89% absolute improvement in SED on the Touchdown dataset.
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).