发表机构
National Research Tomsk Polytechnic University（国立研究托木斯克理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对户外地面机器人地形感知，提出基于注意力与状态预测的可扩展表面分类方法，在Belyaev-Kushnarev和BorealTC数据集上分别达到98.56%和94.8%的准确率。
AI 中文摘要
对于在户外环境中运行的地面机器人，理解底层地形的属性对于确保可靠运行至关重要。在大多数基于感知的研究中，该问题被表述为在训练期间定义固定类别数量的分类任务。我们提出了一种方法，使得新的表面类别可以作为可训练向量被添加，随后可用于解决更高级的任务。通过采用基于预测机器人下一时刻状态的训练范式并使用注意力块，我们在Belyaev-Kushnarev数据集上将分类准确率提升至98.56%，在BorealTC上提升至94.8%。
英文摘要
For ground robots operating in outdoor environments, understanding the properties of the underlying terrain is essential for ensuring reliable operation. In most perception-based studies, this problem is formulated as categorical classification with a fixed number of classes defined during training. We propose an approach that enables new surface classes to be added as trainable vectors, which can subsequently be used to address higher-level tasks. By employing a learning paradigm based on predicting the robot's next state in time and using attention blocks, we improved classification accuracy to 98.56% on the Belyaev-Kushnarev dataset and 94.8% on BorealTC.
