This paper proposes a new approach to achieve direct visual servoing (DVS) based on discrete orthogonal moments (DOM). DVS is conducted whereby the extraction of geometric primitives, matching and tracking steps in the conventional feature-based visual servoing pipeline can be bypassed. Although DVS enables highly precise positioning, and suffers from a small convergence domain and poor robustness, due to the high non-linearity of the cost function to be minimized and the presence of redundant data between visual features. To tackle these issues, we propose a generic and augmented framework to take DOM as visual features into consideration. Through taking Tchebichef, Krawtchouk and Hahn moments as examples, we not only present the strategies for adaptive adjusting the parameters and orders of the visual features, but also exhibit the analytical formulation of the associated interaction matrix. Simulations demonstrate the robustness and accuracy of our method, as well as the advantages over the state of the art. The real experiments have also been performed to validate the effectiveness of our approach.

翻译：本文提出了一种基于离散正交矩（DOM）实现直接视觉伺服（DVS）的新方法。DVS的实施能够绕过传统基于特征的视觉伺服流程中的几何基元提取、匹配与跟踪步骤。尽管DVS能够实现高精度定位，但由于待最小化代价函数的高度非线性以及视觉特征间存在的冗余数据，该方法存在收敛域较小且鲁棒性较差的问题。为解决这些难题，我们提出了一种通用的增强框架，将DOM作为视觉特征纳入考量。以Tchebichef矩、Krawtchouk矩和Hahn矩为例，我们不仅提出了自适应调整视觉特征参数与阶次的策略，还给出了关联交互矩阵的解析表达式。仿真实验验证了该方法的鲁棒性与精度，以及与现有最优方法相比的优越性。实际实验也进一步验证了该方法的有效性。