Soft robotic grippers are essential for grasping delicate, geometrically complex objects in manufacturing, healthcare and agriculture. However, existing designs struggle to grasp feature-rich objects with high topological variability, including gears with sharp tooth profiles on automotive assembly lines, corals with fragile protrusions, or vegetables with irregular branching structures like broccoli. Unlike simple geometric primitives such as cubes or spheres, feature-rich objects lack a clear "optimal" contact surface, making them both difficult to grasp and susceptible to damage. Safe handling of such objects therefore requires specialized soft grippers whose morphology is tailored to the object's features. Topology optimization offers a promising approach for producing specialized grippers, but its utility is limited by the need for pre-defined load cases. For soft grippers, these loads arise from hundreds of unpredictable gripper-object contact forces during grasping and are unknown a priori. To address this problem, we introduce SimTO, a two-stage, simulation-driven topology optimization framework that automatically extracts load cases from a dynamic, contact-rich grasping simulation before performing classical topology optimization, eliminating the need for manual load specification. Given an arbitrary feature-rich object, SimTO produces highly customized soft grippers with fine-grained morphological features tailored to the object geometry. Physical experiments confirm that our specialized grippers achieve higher grasp forces than a generalist design produced by conventional topology optimization methods, while numerical experiments show that they achieve high grasp success rates across varying object poses and strong generalization to a set of unseen objects.

翻译：软体夹爪在制造业、医疗和农业领域中，对于抓取易碎且几何形状复杂的物体至关重要。然而，现有设计难以处理具有高拓扑多样性的特征丰富物体，包括汽车装配线上带有尖锐齿廓的齿轮、带有脆弱凸起的珊瑚，或类似西兰花这类具有不规则分支结构的蔬菜。与立方体或球体等简单几何体不同，特征丰富物体缺乏明确的"最优"接触面，这使其既难以抓取又易受损伤。因此，安全处理此类物体需要形态针对物体特征定制的专用软体夹爪。拓扑优化为制造专用夹爪提供了有前景的方法，但其应用受限于需预定义载荷工况。对于软体夹爪而言，这些载荷源自抓取过程中数百个不可预测的夹爪-物体接触力，且先验未知。为解决此问题，我们提出SimTO——一个两阶段仿真驱动拓扑优化框架，该框架在执行经典拓扑优化前，能从动态、富含接触的抓取仿真中自动提取载荷工况，从而消除手动指定载荷的需求。给定任意特征丰富物体，SimTO能生成高度定制化的软体夹爪，其具备针对物体几何结构定制的精细形态特征。物理实验证实，相较于传统拓扑优化方法生成的通用设计，我们的专用夹爪能实现更高抓取力；同时数值实验表明，这些夹爪在多种物体姿态下均能实现高抓取成功率，并展现出对一组未见物体的强泛化能力。