This paper addresses the multi-faceted problem of robot grasping, where multiple criteria may conflict and differ in importance. We introduce Grasp Ranking and Criteria Evaluation (GRaCE), a novel approach that employs hierarchical rule-based logic and a rank-preserving utility function to optimize grasps based on various criteria such as stability, kinematic constraints, and goal-oriented functionalities. Additionally, we propose GRaCE-OPT, a hybrid optimization strategy that combines gradient-based and gradient-free methods to effectively navigate the complex, non-convex utility function. Experimental results in both simulated and real-world scenarios show that GRaCE requires fewer samples to achieve comparable or superior performance relative to existing methods. The modular architecture of GRaCE allows for easy customization and adaptation to specific application needs.

翻译：本文针对机器人抓取中的多目标问题展开研究，该问题涉及多个可能相互冲突且重要性各异的准则。我们提出了一种名为"抓取排序与准则评估"（GRaCE）的新方法，该方法采用分层规则逻辑和保序效用函数，基于稳定性、运动学约束、目标导向功能等多种准则对抓取进行优化。此外，我们提出了GRaCE-OPT混合优化策略，该策略结合了基于梯度与无梯度方法，能够有效探索复杂的非凸效用函数。在仿真与真实场景中的实验结果表明，与现有方法相比，GRaCE能以更少的采样次数达到相当或更优的性能。GRaCE的模块化架构支持根据具体应用需求进行灵活定制与适配。