MoSS：面向连续体机器人的单目形状感知
MoSS: Monocular Shape Sensing for Continuum Robots
AI总结：
本文提出首个眼在手外单目连续体机器人形状感知方法MoSSNet，通过深度编码器-多解码器网络从单张RGB图像提取多维度信息并拟合3D形状，实现0.91mm误差和70fps实时性能，无需标定与标记。
摘要：
连续体机器人因其独特的形状、顺应性和微型化能力，成为医疗和工业应用中交互任务的有力候选者。准确且实时的形状感知对此类任务至关重要，但仍是挑战。嵌入式形状感知硬件复杂度高且成本昂贵，而基于视觉的方法需要立体配置且难以实现实时性能。本文提出首个针对连续体机器人形状感知的眼在手外单目方法。利用深度编码器-解码器网络，我们的方法MoSSNet消除了立体匹配的计算成本，并降低了对感知硬件的要求。具体而言，MoSSNet包含一个编码器和三个并行解码器，从单张RGB图像中提取空间、长度和轮廓信息，随后通过曲线拟合获取3D形状。使用两段腱驱动连续体机器人进行数据采集与测试，在真实数据上实现了精确（平均形状误差0.91 mm，即机器人长度的0.36%）且实时（70 fps）的形状感知。此外，该方法端到端优化，无需基准标记、手动分割或相机标定。代码和数据集将在 https://github.com/ContinuumRoboticsLab/MoSSNet 发布。
英文摘要：
Continuum robots are promising candidates for interactive tasks in medical and industrial applications due to their unique shape, compliance, and miniaturization capability. Accurate and real-time shape sensing is essential for such tasks yet remains a challenge. Embedded shape sensing has high hardware complexity and cost, while vision-based methods require stereo setup and struggle to achieve real-time performance. This paper proposes the first eye-to-hand monocular approach to continuum robot shape sensing. Utilizing a deep encoder-decoder network, our method, MoSSNet, eliminates the computation cost of stereo matching and reduces requirements on sensing hardware. In particular, MoSSNet comprises an encoder and three parallel decoders to uncover spatial, length, and contour information from a single RGB image, and then obtains the 3D shape through curve fitting. A two-segment tendon-driven continuum robot is used for data collection and testing, demonstrating accurate (mean shape error of 0.91 mm, or 0.36% of robot length) and real-time (70 fps) shape sensing on real-world data. Additionally, the method is optimized end-to-end and does not require fiducial markers, manual segmentation, or camera calibration. Code and datasets will be made available at https://github.com/ContinuumRoboticsLab/MoSSNet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
