| Challenge: | Despite significant advances, few previous works are able to fully utilize the strong correspondence between visual and textual sequences. |
| Approach: | They propose to provide agents with fine-grained annotations during training and provide them with sub-instructions and their corresponding paths. |
| Outcome: | The proposed method improves the performance of four state-of-the-art agents in a room-to-room (R2R) benchmark dataset. |
Similar Papers
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation (P19-1)
Copied to clipboard
| Challenge: | Existing metrics for vision-and-language navigation focus on goal completion rather than the sequence of actions corresponding to the instructions. |
| Approach: | They propose to use a room-to-room dataset to measure the length of instruction followed by agents. |
| Outcome: | The proposed metric outperforms existing metrics for Room-to-Room tasks because it is direct-to goal shortest. |
VLN-Trans: Translator for the Vision and Language Navigation Agent (2023.acl-long)
Copied to clipboard
| Challenge: | We observe two kinds of instructions that make the grounding in the vision-and-language navigation task quite challenging. |
| Approach: | They propose to use a translator module to convert instructions into easy-to-follow sub-instruction representations at each step. |
| Outcome: | The proposed model is based on a Room2Room (R2R), Room4room (R4R), and Room2room Last (R1R-Last) datasets and achieves state-of-the-art results on multiple benchmarks. |
Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing vision language navigation tasks require soft attention over words to locate instructions . a new approach uses syntax information to ground instructions with visual information . |
| Approach: | They propose a vision language navigation agent that utilizes syntax information to enhance alignment between the instruction and the current visual scenes. |
| Outcome: | The proposed agent outperforms the baseline model that does not use syntax information on the Room-to-Room dataset, especially in the unseen environment. |
CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations (2022.findings-naacl)
Copied to clipboard
| Challenge: | Using multilingual instructions to learn a better cross-lingual representation is challenging for multilingual agents. |
| Approach: | They propose to use multilingual instructions to learn a shared cross-lingual language representation for the three languages in a Room-Across-Room dataset. |
| Outcome: | The proposed model improves on the room-Across-room and vision-and-dialogue navigation tasks by maximizing similarity between semantically aligned image pairs from different environments. |
ULN: Towards Underspecified Vision-and-Language Navigation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing vision-and-language navigation models are brittle to multi-level language underspecification. |
| Approach: | They propose to use multi-level underspecified instructions to guide agents . they propose to learn GSS for navigation agent to ground multi- level instructions . experimental results show existing VLN models are still brittle to multi-language underspecification . |
| Outcome: | Experimental results show that the proposed framework outperforms baselines on ULN by 10% relative success rate across all levels. |
Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Vision-and-Language Navigation (VLN) is a subfield of embodied AI that integrates natural language understanding, visual perception, and sequential decision-making to allow autonomous agents to navigate and interact within visual environments. |
| Approach: | They propose a modular framework that introduces structured, skill-based reasoning into Transformer-based VLN agents. |
| Outcome: | The proposed framework decomposes navigation into atomic skills handled by a specialized agent. |
Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding (2020.emnlp-main)
Copied to clipboard
| Challenge: | Room-Across-Room (RxR) is a vision-and-language navigation dataset that addresses gaps in existing ones by addressing known biases in paths and eliciting more references to visible entities. |
| Approach: | They introduce a new Vision-and-Language Navigation (VLN) dataset that addresses biases in paths and elicits more references to visible entities. |
| Outcome: | The proposed model learns from synchronized pose traces by focusing only on portions of the panorama attended to in human demonstrations. |
Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a new evaluation framework for vision-language navigation is proposed . current evaluation standards hinge on endpoint success rates and path alignment metrics . |
| Approach: | They propose a semi-automatic method for CFG construction with Large-Language Models . they induct data spanning five principal instruction categories and analyze them . |
| Outcome: | The proposed framework diagnoses current models for the Vision-Language Navigation task at a finer-grained level. |
LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing Transformer-based VLN agents entangle orientation and vision information, which limits the learning of each information source. |
| Approach: | They propose to design a navigation agent with explicit Orientation and Vision modules . they use a set of pre-training tasks to feed the modules into the model . |
| Outcome: | The proposed model improves on R2R and R4R datasets and achieves state-of-the-art results. |
Robust Navigation with Language Pretraining and Stochastic Sampling (D19-1)
Copied to clipboard
Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah A. Smith, Yejin Choi
| Challenge: | Existing methods to learn visual representations and action decoding schemes are limited to previously unseen instructions and environments. |
| Approach: | They propose a stochastic sampling scheme to reduce the gap between the expert actions in training and sampled actions in test to correct its own mistakes. |
| Outcome: | The proposed methods achieve 6% absolute gain over the previous best results on the Room-to-Room benchmark. |