通过 Soner 边界条件在不规则域中测地距离的数据增强学习
Data-augmented Learning of Geodesic Distances in Irregular Domains through Soner Boundary Conditions
AI总结:
针对神经网络求解 Eikonal 方程时训练不稳定的问题,提出使用 Soner 边界条件学习不规则域测地距离的框架,并引入数据损失,显著提升了收敛鲁棒性和求解可靠性。
摘要:
测地距离在机器人技术中起着基础性作用,因为它能高效编码域的全局几何信息。近期方法通过物理信息方法求解 Eikonal 方程,利用神经网络近似测地距离。虽然有效,但这些方法在复杂环境中训练时常常出现收敛不稳定的问题。我们提出了一个使用 Soner 边界条件在不规则域中学习测地距离的框架,并系统评估了数据损失对训练稳定性和求解精度的影响。实验表明,引入数据损失显著提升了收敛鲁棒性,降低了训练不稳定性和对初始化的敏感性。这些发现表明,混合数据与物理的方法能有效提升基于学习的稀疏数据测地距离求解器的可靠性。
英文摘要:
Geodesic distances play a fundamental role in robotics, as they efficiently encode global geometric information of the domain. Recent methods use neural networks to approximate geodesic distances by solving the Eikonal equation through physics-informed approaches. While effective, these approaches often suffer from unstable convergence during training in complex environments. We propose a framework to learn geodesic distances in irregular domains by using the Soner boundary condition, and systematically evaluate the impact of data losses on training stability and solution accuracy. Our experiments demonstrate that incorporating data losses significantly improves convergence robustness, reducing training instabilities and sensitivity to initialization. These findings suggest that hybrid data-physics approaches can effectively enhance the reliability of learning-based geodesic distance solvers with sparse data.
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。