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

2026-07-30

AI Summary

This work addresses the challenge of semantic ambiguity in traversability within agricultural Vision-and-Language Navigation (VLN-CE), where inconsistent judgments about passable regions arise across different agents. To resolve this, the paper introduces, for the first time, a Traversability Estimation and Alert (TEA) mechanism integrated into the AgriVLN backbone. TEA combines image-level traversability estimation, action–traversability consistency verification, and a replanning strategy to trigger alerts and guide decision adjustments whenever predicted actions conflict with the traversability map. Evaluated on the A2A benchmark, the proposed approach improves task success rate from 0.47 to 0.54 and reduces navigation error from 2.91 meters to 2.70 meters, significantly outperforming existing methods and establishing a new paradigm for agricultural VLN-CE tasks.

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.

Problem

• Traversability Estimation
• Agricultural Vision-and-Language Navigation
• VLN-CE
• Navigation Ambiguity
• Continuous Environments

Innovation

• Traversability Estimation
• Vision-and-Language Navigation
• Agricultural Robotics
• Navigation Alarm Mechanism
• Continuous Environments