# Robust Navigation with Language Pretraining and Stochastic Sampling

arXiv: https://arxiv.org/abs/1909.02244 · HTML: https://mlsanity.com/paper/1909.02244/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 30 of 77)

- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [History Aware Multimodal Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2110.13309/) (2021)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [NaVILA: Legged Robot Vision-Language-Action Model for Navigation](https://mlsanity.com/paper/2412.04453/) (2024)
- [Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2202.11742/) (2022)
- [MultiBench: Multiscale Benchmarks for Multimodal Representation Learning](https://mlsanity.com/paper/2107.07502/) (2021)
- [Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.02764/) (2022)
- [Airbert: In-domain Pretraining for Vision-and-Language Navigation](https://mlsanity.com/paper/2108.09105/) (2021)
- [MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices](https://mlsanity.com/paper/2312.16886/) (2023)
- [Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2203.12667/) (2022)
- [NavGPT-2: Unleashing Navigational Reasoning Capability for Large Vision-Language Models](https://mlsanity.com/paper/2407.12366/) (2024)
- [Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models](https://mlsanity.com/paper/2407.07035/) (2024)
- [PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation](https://mlsanity.com/paper/2305.19195/) (2023)
- [Bird's-Eye-View Scene Graph for Vision-Language Navigation](https://mlsanity.com/paper/2308.04758/) (2023)
- [Vision-Language Navigation with Random Environmental Mixup](https://mlsanity.com/paper/2106.07876/) (2021)
- [HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.11591/) (2022)
- [A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning](https://mlsanity.com/paper/2210.03112/) (2022)
- [SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation](https://mlsanity.com/paper/2110.14143/) (2021)
- [Neighbor-view Enhanced Model for Vision and Language Navigation](https://mlsanity.com/paper/2107.07201/) (2021)
- [Learning from Unlabeled 3D Environments for Vision-and-Language Navigation](https://mlsanity.com/paper/2208.11781/) (2022)
- [On the Evaluation of Vision-and-Language Navigation Instructions](https://mlsanity.com/paper/2101.10504/) (2021)
- [ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts](https://mlsanity.com/paper/2205.15509/) (2022)
- [Lana: A Language-Capable Navigator for Instruction Following and Generation](https://mlsanity.com/paper/2303.08409/) (2023)
- [Reinforced Structured State-Evolution for Vision-Language Navigation](https://mlsanity.com/paper/2204.09280/) (2022)
- [Diagnosing Vision-and-Language Navigation: What Really Matters](https://mlsanity.com/paper/2103.16561/) (2021)
- [On Transforming Reinforcement Learning by Transformer: The Development Trajectory](https://mlsanity.com/paper/2212.14164/) (2022)
- [Vision-Language Navigation: A Survey and Taxonomy](https://mlsanity.com/paper/2108.11544/) (2021)
- [Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information](https://mlsanity.com/paper/2104.09580/) (2021)
- [Core Challenges in Embodied Vision-Language Planning](https://mlsanity.com/paper/2106.13948/) (2021)

## Abstract (arXiv)

Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report two simple but highly effective methods to address these challenges and lead to a new state-of-the-art performance. First, we adapt large-scale pretrained language models to learn text representations that generalize better to previously unseen instructions. Second, we propose a stochastic sampling scheme to reduce the considerable gap between the expert actions in training and sampled actions in test, so that the agent can learn to correct its own mistakes during long sequential action decoding. Combining the two techniques, we achieve a new state of the art on the Room-to-Room benchmark with 6% absolute gain over the previous best result (47% -> 53%) on the Success Rate weighted by Path Length metric.