# Embodied Vision-and-Language Navigation with Dynamic Convolutional Filters

arXiv: https://arxiv.org/abs/1907.02985 · HTML: https://mlsanity.com/paper/1907.02985/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2019.

## Built on by (most cited first, 9 of 9)

- [Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2203.12667/) (2022)
- [Neighbor-view Enhanced Model for Vision and Language Navigation](https://mlsanity.com/paper/2107.07201/) (2021)
- [Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents](https://mlsanity.com/paper/2308.07241/) (2023)
- [Vision-Language Navigation with Embodied Intelligence: A Survey](https://mlsanity.com/paper/2402.14304/) (2024)
- [Multi-Level Compositional Reasoning for Interactive Instruction Following](https://mlsanity.com/paper/2308.09387/) (2023)
- [Find a Way Forward: a Language-Guided Semantic Map Navigator](https://mlsanity.com/paper/2203.03183/) (2022)
- [AIGeN: An Adversarial Approach for Instruction Generation in VLN](https://mlsanity.com/paper/2404.10054/) (2024)
- [Following Route Instructions using Large Vision-Language Models: A Comparison between Low-level and Panoramic Action Spaces](https://mlsanity.com/paper/2508.02917/) (2025)
- [Bear the Query in Mind: Visual Grounding with Query-conditioned Convolution](https://mlsanity.com/paper/2206.09114/) (2022)

## Abstract (arXiv)

In Vision-and-Language Navigation (VLN), an embodied agent needs to reach a target destination with the only guidance of a natural language instruction. To explore the environment and progress towards the target location, the agent must perform a series of low-level actions, such as rotate, before stepping ahead. In this paper, we propose to exploit dynamic convolutional filters to encode the visual information and the lingual description in an efficient way. Differently from some previous works that abstract from the agent perspective and use high-level navigation spaces, we design a policy which decodes the information provided by dynamic convolution into a series of low-level, agent friendly actions. Results show that our model exploiting dynamic filters performs better than other architectures with traditional convolution, being the new state of the art for embodied VLN in the low-level action space. Additionally, we attempt to categorize recent work on VLN depending on their architectural choices and distinguish two main groups: we call them low-level actions and high-level actions models. To the best of our knowledge, we are the first to propose this analysis and categorization for VLN.