Conventional wheeled robots are unable to traverse scientifically interesting, but dangerous, cave environments. Multi-limbed climbing robot designs, such as ReachBot, are able to grasp irregular surface features and execute climbing motions to overcome obstacles, given suitable grasp locations. To support grasp site identification, we present a method for detecting rock cracks and edges, the SKeleton Intersection Loss (SKIL). SKIL is a loss designed for thin object segmentation that leverages the skeleton of the label. A dataset of rock face images was collected, manually annotated, and augmented with generated data. A new group of metrics, LineAcc, has been proposed for thin object segmentation such that the impact of the object width on the score is minimized. In addition, the metric is less sensitive to translation which can often lead to a score of zero when computing classical metrics such as Dice on thin objects. Our fine-tuned models outperform previous methods on similar thin object segmentation tasks such as blood vessel segmentation and show promise for integration onto a robotic system.

翻译：传统轮式机器人无法穿越具有科学价值但危险的洞穴环境。采用多肢体攀爬设计的机器人（如ReachBot）能够在合适抓取点支撑下，通过抓取不规则表面特征执行攀爬动作以克服障碍。为辅助抓取点识别，本文提出一种岩石裂缝与边缘检测方法——骨架交并差损失（SKIL）。SKIL是一种针对薄目标分割设计的损失函数，通过利用标注数据的骨架信息实现检测。我们收集了岩石表面图像数据集，进行人工标注并通过生成数据增强。针对薄目标分割，提出新型评估指标组LineAcc，可最小化目标宽度对评分的影响。该指标对平移不敏感，克服了传统指标（如Dice）计算薄目标时因微量位移导致得分为零的问题。经微调的模型在血管分割等类似薄目标分割任务中优于现有方法，展现出集成至机器人系统的应用潜力。