从语言先验到领域自适应：用于可通行性估计的偏好学习

中文摘要 AI 辅助

基于图像的可通行性估计本质上依赖于机器人平台、部署领域和任务偏好，这限制了专用训练模型的适用性。为促进领域自适应，本工作旨在通过样本高效的偏好学习减少目标领域所需的标注数量。我们的方法在冻结的视觉-语言特征空间中，通过冯·米泽斯-费雪混合原型来表示可通行性。相对自然语言规则提供了常识先验，而稀疏的相对图像标注通过计算和样本高效的微调，将原型方向和效用调整到目标领域。在WayFAST上的实验表明，其精度可与端到端训练的估计器相媲美，同时实现了样本高效的基于图像的适应。定性实验进一步展示了语言先验的零样本适用性以及微调估计器在语义地图上改进的稠密预测。通过剖析语义相近的自然语言提示，对学习到的原型进行语义解释，从而补充了评估。代码和训练好的估计器可在该https URL获取。

英文摘要

Image-based traversability estimation is inherently dependent on the robot platform, deployment domain, and mission preferences, which limits the applicability of purpose-trained models. To facilitate domain adaptation, this work aims to reduce the number of required annotations in the target domain using sample-efficient preference learning. Our method represents traversability through von Mises-Fisher mixture prototypes in a frozen vision-language feature space. Relative natural-language rules provide a commonsense prior, while sparse relative image annotations adapt the prototype directions and utilities to a target domain through computationally and sample-efficient fine-tuning. Experiments on WayFAST demonstrate accuracy competitive with end-to-end trained estimators while enabling sample-efficient image-based adaptation. Qualitative experiments further demonstrate the language prior's zero shot applicability and the fine-tuned estimator's improved dense prediction on semantic maps. Evaluation is complemented via semantic interpretation of learned prototypes by dissecting semantically close natural language prompts. Code and trained estimators available at https://resireg.github.io

发表机构

• Graz University of Technology（格拉茨技术大学）
• University of Applied Sciences Technikum Wien（维也纳技术应用科学大学）
• University of Alicante（阿利坎特大学）
• University of Natural Resources and Life Sciences（自然资源与生命科学大学）

机构由 AI 辅助整理，请以论文原文为准。