TEA-AgriVLN: Traversability Estimation Alarm for Agricultural Vision-and-Language Navigation

TEA-AgriVLN: Traversability Estimation Alarm for Agricultural Vision-and-Language Navigation

|Authors: Xiaobei Zhao, Xingqi Lyu, Xin Chen, Xiang Li

|Venue: arXiv preprint | Year: 2026

|arXiv: 2607.28474v1

Abstract

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow a natural language instruction, predicting a sequence of low-level actions to navigate a robot from a starting point to a target location. The A2A benchmark and the AgriVLN method pioneeringly extended VLN-CE from indoor scenes to agricultural scenes, while we observed a challenging distinction: In indoor scenes, whether a zone is traversable tends to be clear to classify, such as wood floors are traversable but concrete walls are not. In agricultural scenes, however, this issue tends to be ambiguous, such as an unripe cornfield might be traversable for a robotic dog but might be non-traversable for a human. To address this issue, we propose the TEA module, which estimates the traversability of the camera image, then alarm the decision-maker for rethinking when the predicted action does not align with the traversability map. We integrate it into the AgriVLN backbone to build our TEA-AgriVLN method. When evaluated on A2A, it improves Success Rate (SR) from 0.47 to 0.54 and Navigation Error (NE) from 2.91 m to 2.70 m, showing the state-of-the-art performance in the agricultural VLN-CE domain. We further implement the ablation studies and the case study, discussing the effectiveness and limitations of TEA on different ground categories and scene classes. Code: https://github.com/AlexTraveling/TEA-AgriVLN.

Key Contributions

• Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an agent to follow a …
• The A2A benchmark and the AgriVLN method pioneeringly extended VLN-CE from indoor scenes to agric…
• In agricultural scenes, however, this issue tends to be ambiguous, such as an unripe cornfield mi…
• To address this issue, we propose the TEA module, which estimates the traversability of the camer…
• We integrate it into the AgriVLN backbone to build our TEA-AgriVLN method

Topics

• vision
• planning
• benchmark

Code & Data

• GitHub repository: https://github.com/AlexTraveling/TEA-AgriVLN

BibTeX

@article{Zhao2026_260728474v1,
  title     = {TEA-AgriVLN: Traversability Estimation Alarm for Agricultural Vision-and-Language Navigation},
  author    = {Xiaobei Zhao and Xingqi Lyu and Xin Chen and Xiang Li},
  year      = {2026},
  eprint    = {2607.28474v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2607.28474v1}
}